SP10 at the interdisciplinary college

We present a poster and host an interactive demo session during this year’s annual interdisciplinary college (IK), which takes place from 9-16th March.

Find out more here: https://www.interdisciplinary-college.de

Register now!

(Image taken from the link above)

Advertisements

Learning to walk

Favorit Bar + Kunstverein München, in collaboration with the TU München and the Human Brain Project, present

Learning to Walk: Künstliche Intelligenz und Körper

Performance and grand finale at Kunstverein München: Learning to Walk: 42nd Street of 2018 takes place on 26th January.

Find out more here: http://www.kunstverein-muenchen.de/en/program/events/2017/learning-to-walk

and here https://www.facebook.com/events/168991993875889/?active_tab=about

 

 

HBP_Primary_RGB_BlackText

 

HBP Innovation Day

The HBP Innovation Day will take place in Munich on 15.12.2017!

For registering to the event, please send an Email with the title “HBP innovation Day” and stating your full name and affiliation to: events@bicc-net.de

Learn more here: https://www.humanbrainproject.eu/en/follow-hbp/events/hbp-innovation-day-neuroscience-driven-innovation-and-path-forward-ai-and-robotics/

 

HBP_Primary_RGB_BlackText

 

 

 

HBP Summit 2017

Date: 17.10.2017
Venue: Glasgow

Duration: 4 days

The Human Brain Project (HBP) Summit is a unique forum for the HBP Consortium and its Partnering Projects to come together to present and learn about the latest scientific results and other project achievements, as well as to develop new ideas, plan next steps and network. The event consists of a 3-day interactive scientific programme, comprising plenary sessions, external keynote presentations, hackathons, demos, scientific highlight sessions and cross-disciplinary workshops.

https://www.humanbrainproject.eu/en/follow-hbp/news/5th-annual-human-brain-project-summit/

Summit.jpg

NRP presented at Digital Summit in Tallinn

We presented the ongoing work in the HBP in Tallin at the Digital Summit. We were one of the main topics during this presentation to show the constantly improving NRP and its many possible applications.

Find out more here: https://www.humanbrainproject.eu/en/follow-hbp/news/the-hbp-at-the-tallinn-digital-summit/

Below you can see the latest addition to our project, a biologically inspired robotic mouse to further close the gap between biological and robotic systems.

Image from https://m.facebook.com/story.php?story_fbid=10156614926684325&id=390693124324

 

FB_IMG_1506769838371

User Workshop @ FZI Karlsruhe

Date: 24.07.2017
Venue: FZI, Karlsruhe, Germany
Duration: 3 Days

Thanks to all of the 17 participants for making this workshop a great time.

We held a successful Neurorobotics Platform (NRP) User Workshop in FZI, Karlsruhe.  We welcomed 17 attendants over three days, coming from various sub-projects (such as Martin Pearson, SP3) and HBP outsiders (Carmen Peláez-Moreno and  Francisco José Valverde Albacete). We focused on hands-on sessions so that users got comfortable using the NRP themselves.

IMG_1183IMG_1185

Thanks to our live boot image with the NRP pre-installed, even users who did not follow the local installation steps beforehand could run the platform locally in no time. During the first day, we provided a tutorial experiment, exclusively developed for the event, which walked the users through the many features of the NRP. This tutorial experiment is inspired from the baby playing ping pong video, which is here simulated with an iCub robot. This tutorial experiment will soon get released with the official build of the platform.

IMG_20170724_120245.jpg

On the second and third days, more freedom was given to the users so that they could implement their own experiments. We had short hands-on sessions on the Robot Designer as well as Virtual Coach, for offline optimization and analysis. Many new experiments were successfully integrated into the platform: the Miro robot from Consequential Robotics,  a snake-like robot moving with Central Patterns Generators (CPG), revival of the Lauron experiment, …

IMG_20170725_094219.jpg

We received great feedback from the users. We are looking forward for the organization of the next NRP User Workshop!

Upcoming Developer Workshop

We are pleased to announce our next developer Workshop at Fortiss in Munich!

It will be held from 4.10.-6.10. and will give our development the chance to plan the next release (2.0) in great detail and work out any remaining issues during these days of concentrated work. In the image below you can see our latest virtual room.

Holodeck.PNG

AI at TUM in german television

The well known german television series “Tatort” is currently filming an episode on a 10 year research project on artificial intelligence. They chose TUM in Munich as location. This just goes to show again how popular AI has become and how important it is to continue our research on AI combined with robotics.

The episode is now completed, find out more here: http://www.daserste.de/unterhaltung/krimi/tatort/specials/dreh-tatort-muenchen-ki100.html

Tatort_AI.jpeg

 

Publication

title = {The Neurorobotics Platform: A simulation environment for brain-inspired robotics},

link = {https://abstracts.g-node.org/conference/BC17/abstracts#/uuid/cdb88f26-cff3-483d-86e7-e02adc2d511f},

author = {M. Akl, HBP Neurorobotics Team},

journal = {Bernstein Conference 2017},

year = {2017}

Publication

title = {Hebbian Learning Based Sensorimotor Association in a Closed-Loop Neurorobotic Experiment},

link = {https://abstracts.g-node.org/conference/BC17/abstracts#/uuid/13b7df35-b597-4fb4-aa3c-dca3759e4501},

author = {B. Feldotto, F. Walter, F. Röhrbein},

journal = {Bernstein Conference 2017},

year = {2017}

We are presenting at the Bernstein Conference!

Flyer_BC17_final_200217_web

Colleagues from HBP neurorobotics are presenting 3 posters at the Bernstein Conference 2017 in Göttingen:

  1. Hebbian Learning Based Sensory to Motor Association in a Closed-Loop Neurorobotic Experiment
  2. The Neurorobotics Platform: A simulation environment for brain-inspired robotics
  3. Simple mathematical model of delay eyeblink conditioning in the cerebellum

Come talk to us and learn more about our project!

Lisl_header_2017.jpg

(images taken from http://www.bernstein-conference.de)

New publication

title = {Spiking Cooperative Stereo-Matching at 2 ms Latency with Neuromorphic Hardware},

author = {G. Dikov, M. Firouzi, F. Röhrbein, J. Conradt,  C. Richter},

 

journal = {Living Machines 2017: Biomimetic and Biohybrid Systems},

year = {2017}

link = {https://www.researchgate.net/publication/318449954_Spiking_Cooperative_Stereo-Matching_at_2_ms_Latency_with_Neuromorphic_Hardware}

User Workshop In Karlsruhe!

The Neurorobotics User Workshop will take place at FZI, Karlsruhe, from the 24th to the 26th of July. This workshop is a great opportunity for new users to integrate with the  community and make progress with their own experiments.

HBP_Primary_RGB_BlackText

Bringing Technology and People Closer Together

With our brain inspired robots being a relatively young development, it is of utmost importance to make them more approachable to the public. Amongst other technology trends, we represented our project in the course of the third future congress hosted by the Bundesministerium für Bildung und Forschung (BMBF).

IMG_2521

New publication

title = {A Scalable Neuro-inspired Robot Controller Integrating a Machine Learning Algorithm and a Spiking Cerebellar-like Network},

author = {I. Ojeda, S. Tolu, H. Lund},

journal = {Living Machines Conference},

year = {2017},

link = {https://link.springer.com/chapter/10.1007/978-3-319-63537-8_31}

3rd Japan-EU Workshop

Date: 15.06.2017
Venue: Biotech Campus Geneva
Duration: 1 day
In conjunction with the symposium „Building Bodies for Brains & Brains for Bodies“ on June 16 we had our 3rd Japan-EU Workshop on Neurorobotics in Geneva.
Speakers included:
Yoshihiko Nakamura (University of Tokyo)
Satoshi Oota (RIKEN)
Poramate Manoonpong (University of Southern Denmark),
Aaron Sloman (University of Birmingham)
It was the third in a hopefully now established series of workshops. For the past two workshops in this series in 2015 and 2016 see:
IMG_2871

Symposium: Building Bodies for Brains & Brains for Bodies

Date: 16.06.2017
Venue: Biotech Campus Geneva
Duration: 1 day

It was a one-day symposium in the field of neurorobotics with the goal of improving robot behavior by exploiting ideas from neuroscience and investigating brain function using real physical robots or simulations thereof.
Contributions to this workshop focussed on (but not limited to) the relation between neural systems – artificial or biological – and soft-material robotic platforms, in particular the “control” of such systems by capitalizing on their intrinsic dynamical characteristics like stiffness, viscosity and compliance.

HBP_Primary_RGB_BlackText.png

Building Bodies for Brains & Brains for Bodies

This extraordinary event with world-famous speakers including Masayuki Inaba, Yasuo Kuniyoshi, Minoru Asada and Norman Packard will take place in Geneva on June 16th, 2017.

It is a one-day symposium in the field of neurorobotics with the goal of improving robot behavior by exploiting ideas from neuroscience and investigating brain function using real physical robots or simulations thereof. Contributions to this workshop will focus on (but are not limited to) the relation between neural systems – artificial or biological – and soft-material robotic platforms, in particular the “control” of such systems by capitalizing on their intrinsic dynamical characteristics like stiffness, viscosity and compliance.

hbp-logo

The symposium will take place at the coordination site of the Human Brain Project in Geneva at Campus Biotech, Chemin des Mines 9, see also http://www.campusbiotech.ch/en

Pint of Science

Florian Röhrbein from our Subproject of Neurorobotics gave a fascinating talk at the first Pint of Science of 2017 in Munich, which dealt with the question “How are neuroscience, robotics, and artificial intelligence linked and how far have computers, robots and artificial intelligence already come in the world of medicine? ”

You can find impressions below and even more on Facebook: https://www.facebook.com/PoS.Munich

Find out more about this event here: https://pintofsciencede.wixsite.com/pintofsciencede/copy-of-2016m2

2017-05-15_0442017-05-15_055

HBP at the ISCAS 2017!

We attended the ISCAS 2017 (50th Anniversary) together with colleagues from SP9 to represent the HBP and to identify possible collaborations with other projects like the US BRAIN project which was featured in a keynote.

The ISCAS is described as “The world’s premier networking and exchange forum for leading researchers in the highly active fields of theory, design and implementation of circuits and systems. ” (from http://iscas2017.org/)

Learn more at http://iscas2017.org/

iscas2017-logo-2-final-w-text-web_artboard_2_copy

Neurorobotics Platform at “50 Jahre Informatik München”

The Neurorobotics Platform was featured in a publication in a special issue of Informatik Spektrum here: http://link.springer.com/article/10.1007/s00287-017-1031-8

During the celebration of 50 years of informatics at the TUM, we had a booth to present our neurorobotics platform to students and researchers. We were able to show the ongoing research and the platform’s features to the interested public.

 

20170512_103313.jpg

NRP version 1.2 released!

The 1.2 version of the Neurorobotics Platform has been released! As usual, you can access it from:
https://collab.humanbrainproject.eu/#/collab/71/nav/405
or from our website
http://neurorobotics.net

This versions adds:

Support for bigger brain models
Graphical transfer functions editor
Basic brain visualization
Python API for batch simulations (Virtual Coach)
Object scaling
New template experiments
Camera Streaming
Object Scaling
Environment Enhancements

and updated documentation and video tutorials.

Known issues are slow access on private collabs, which should be fixed soon, and some experiments not automatically switching to 3D view, which we are working on.

We are naturally moving to our next 1.3 release cycle, which will add even more great features and enhancements. These will be announced on the website roadmap shortly.

virtualLab.png

The picture shows a redesigned virtual lab, featuring the mouse experiment and our new brain visualizer.

Developer Workshop 1.3 at Fortiss

Date: 06.04.2017
Venue: Fortiss
Duration: 2 days

As the NRP development team is in the process of releasing 1.2, it holds on 6th and 7th April its 6-monthly developer workshop, this time at fortiss in Munich. This workshop closes the 1.2 release cycle with technical presentations of the new features by developers, updates from our scientistific coordinator and a scrum release retrospective. It also opens the new 1.3 release cycle with new epics presentation by the product owner and scrum client followed by a full day of backlog grooming and road mapping for the next 6 months.
Moreover, this event is an occasion for developers to meet all in one place and exchange views and issues.

20170406_163424

20170406_153750.jpg

NRP Install Party

Date: 04.04.2017
Venue: Fortiss, Munich
Duration: 2 days

Selected SP10 scientists from all over Europe came to Fortiss for hands-on sessions with NRP developers and advanced help from scientific experts for their simulated experiments. With one expert dedicated to helping one researcher, we were able to adapt these user experiments to our platform while using it to its full potential during these two days in Munich.
In a continuing effort to use scientific requirements as the driving force behind our platform development, we were able to use this event to collect feature requests and problems to be addressed.

20170404_134219

Japan-EU Workshop in Geneva

In conjunction with the symposium „Building Bodies for Brains & Brains for Bodies“ on June 16 we will have our 3rd Japan-EU Workshop on Neurorobotics at the same location the day before.
speakers include:
Yoshihiko Nakamura (University of Tokyo)
Satoshi Oota (RIKEN)
Poramate Manoonpong (University of Southern Denmark),
Aaron Sloman (University of Birmingham)
For the past two workshops in this series in 2015 and 2016 see:
hbp_small

Developer Workshop in Pisa

Date: 17.10.2016
Venue: Pisa
Duration: 2 days

The developer workshop in Pontedera brought together the developers of our subproject. In a 2 day workshop, the recent Summit was discussed to draw conclusions from the feedback we had received.
Addressing the most pressing issues that had been discussed during the Summit was only part of that workshop. Another important aspect was to align the development with what users actually need by inviting a couple of researchers and making sure our plans were in alignment with theirs.
Then, working together, our roadmap was refined to ensure good progress for the months to come.hbp_small

NEST Workshop in Karlsruhe

Date: 03.11.2016
Venue: FZI, Karlsruhe
Duration: 2 days

The NEST workshop in Karlsruhe received a lot of attention with significantly more attendees than expected.

Presentations covered topics such as
– NEST: Current Developments (Hans Ekkehard Plesser & Susanne Kunkel)
– Neurorobotics and NEST in the HBP (Marc-Oliver Gewaltig)
– Modeling the Cerebellum (Egidio d’Angelo)
– Cerebellum Modelling with NEST (Alberto Antonietti)
– Interfacing the Neurorobotics Platform using MUSIC (Martin Schulze)
– The Potjans-Diesmann local microcircuit model using different neuron classes for excitatory and inhibitory neurons (Nilton Kamiji)
– Interactive visualization and steering of structural plasticity in NEST (Sandra Diaz)
– NestMC: A new multi-compartment neuron simulator (Alex Peyser)
– NEST, MUSIC, and ROS (Philipp Weidel)
– Porting WaveScales to NEST (Elena Pastorelli)

 

You can find more on the workshop website here: https://indico-jsc.fz-juelich.de/event/26/

HBP_NEST_cutfzi_logo_square

Hack Roboy!

Hack Roboy is a robotics hackathon taking place in Garching on April, 28 – May, 1.

We provide our robots and tech hardware for you to create ingenious robotics projects without any topic or purpose constrains. Hack Roboy is a conjunction point for people passionate about engineering, it’s a place where innovative ideas are getting born and implemented.

Learn more and apply at www.hackroboy.com!

HackRoboy.jpg

New publication

@article{knoll2017neurorobotics,
author = {A. Knoll, F. Röhrbein, A. Kuhn, M. Akl, K. Sharma},
year = {2017},
title = {Neurorobotics},
journal = {Informatik-Spektrum},
issn = {0170-6012},
doi = {10.1007/s00287-017-1031-8},
link= {https://dx.doi.org/10.1007/s00287-017-1031-8},
abstract = {The field of neurorobotics encompasses the intersection of computational neuroscience and robotics. The TUM-led neurorobotics subproject of the Human Brain Project is actively researching concepts within the field and developing the tools to allow researchers to fully explore simulated robotics driven by computational neuroscience models. Further, the development of biologically inspired, tendon-driven robotics systems provides a unique research platform. These efforts allow researchers to explore the interesting space from computational neuroscience to intelligent robots and back.}
}

NRP Install Party

After the successful user workshop in January, it is now time to guide researchers in a small hands-on workshop through the local installation of our platform. Once this is done, they will have the chance to explore the NRP’s many features and use it to its full potential while being guided by experienced developers. At the end, the participants should be able to run their own, customized experiments on our platform.

If this concept proves to be successful, we will organize more events of that kind.

 

mouse.PNG

Developer Workshop at Fortiss

The developer team will release the 1.2 version of the NRP end of March. On 6/7 April, it will meet in a developer workshop at Fortiss, Munich, to define the work plan of the next release cycle (1.3), discuss the roadmap and major technical questions. User support will be part of the discussions.

 

 

fortiss_square

Brain Awareness Week

Next week is Brain Awareness Week, which goes to show once more just how important our work in the HBP is in working towards a better understanding of our brain.
bernstein-network-computational-neuroscience.jpeg.png
“The Brain Awareness Week (BAW) is the global campaign to increase public awareness of the progress and benefits of brain research.”

 

 

Image from http://www.research-in-germany.org/mediaObject/en/Logos-News/bernstein-network-computational-neuroscience/original/bernstein-network-computational-neuroscience.jpeg.png

New publication

@ARTICLE{10.3389/fnbot.2017.00016,

author={G. Urbain, J. Degrave, B. Carette, J. Dambre, F. wyffels},

title={Morphological Properties of Mass-Spring Networks for Optimal Locomotion Learning},

journal={Frontiers in Neurorobotics, Vol. 11},

pages={16},

year={2017},

link={http://journal.frontiersin.org/article/10.3389/fnbot.2017.00016},

DOI={10.3389/fnbot.2017.00016},

ISSN={1662-5218},

HBP Exhibition

date: 29.11.2016
venue: European Parliament
duration: 2 days
The first Human Brain Project exhibition took place at the European Parliament on 29 – 30 November 2016.

hbp_booklet.png

The HBP exhibition highlights the unique contributions HBP is making to brain research and how these contributions are benefiting European science, competitiveness and society and positioning Europe promanently among the growing number of large-scale brain initiatives worldwide. The exhibition was created as part of HBP’s participation in the workshop Understanding the Human Brain – A New Era of Big Neuroscience, organised by the European Parliament’s Science Technology Options Assessment group (STOA) on 29 November 2016.

The text and image above are taken from a booklet that you can find here: stoa_booklet-v-final_digital

Experienced Simulation Software Engineer – Neurorobotics

TUM_logo_square.pngembedded_systemshbp_small

date = {19.01.2017},
start = {as soon as possible},
type = {perm},
contactName = {Florian Röhrbein},
contactMail = {florian.roehrbein@in.tum.de},
background = {The Human Brain Project (HBP) is an ambitious, large-scale, research initiative funded by the European Commission with global recognition. More than a 100 research institutes from various disciplines all over Europe cooperate intensively to achieve a multi-level, integrated understanding of brain structure and function through the development and use of information and communication technologies (ICT). The project will run for about 10 years and during this time six ICT platforms will be developed. The Neurorobotics Platform (NRP) is a web-based platform for the design and performance of neurorobotics experiments, and is built under the direction of Prof. Alois Knoll. It grants neuroscientists easy access to state-of-the-art simulators: spiking neural networks, robotics and physics. These simulators are connected together and coordinated within a closed loop. They run on high performance computing resources and on neuromorphic hardware. The NRP also provides tools to create neurorobotics experiments, namely designers for the creation of brain-body interfaces, virtual worlds and robot models.},
description = {To strengthen our Neurorobotics team at TUM we are looking for an Experienced Simulation Software Engineer (Neurorobotics) with a Master’s degree in software engineering or similar (Bachelors if proven relevant professional experience) and a minimum of 3 years of experience and successful development track record for simulation-based software projects. Preferredly, the candidate will have experience with Agile Methodologies and SaaS environmen, be familiar withPython, HTML, Javascript languages; WebGL, ThreeJS, AngularJS frameworks and have experience with neural networks, NEST simulator. We offer a prestigious project of global prominence in simulation-based neuroscience, a dynamic, interdisciplinary, and motivated team. Furthermore, we offer remuneration in line with the current German public service salary scale TV-L and a modern working environment based at the TUM Campus in Garching / Munich. Starting date ASAP, applicants should submit a cover letter and a detailed CV in PDF format with file name “_HBP_SW_cover” and “_HBP_ SW_CV” to florian.roehrbein@in.tum.de},
requirements = {# Experience in robotics on the software layer or 3D simulation development
# Good familiarity with 3D simulators / libraries and either ROS, Gazebo or other robotic simulator
# Strong experience in C++ or other object oriented programming language
# Strong motivation to learn the other languages / technologies that we use, in particular spiking neural networks
# Very good familiarity with team work and modern software development life-cycle
# Flexible, good team player and fluent in written and spoken English, German a plus}
tasks = {# Development of our graphical Robot Designer application (Python / Blender / Javascript)
# Gazebo plugins development (C++, ROS)
# Frontend development of rich, highly interactive 3D web interfaces (HTML5, CSS, Javascript)
# Backend development at the brain simulator level (Python, C++ / MPI)
# All aspects of the modern software development lifecycle: unit testing, continuous integration, version control, debugging, documentation
# Support to the users for setting up new neurorobotics experiments},

pdf = {https://hbpneurorobotics.files.wordpress.com/2017/01/experienced-simulation-software-engineer-neurorobotics.pdf}

Publication

@ARTICLE{10.3389/fnbot.2017.00002,

author={E. Falotico, L. Vannucci, A. Ambrosano, U. Albanese, S. Ulbrich, J. Vasquez, G. Hinkel, J. Kaiser, I. Peric, O. Denninger, N. Cauli et al.},
title={Connecting artificial brains to robots in a comprehensive simulation framework: the Neurorobotics Platform},
journal={Frontiers in Neurorobotics, Vol. 11},
year={2017},
link={http://journal.frontiersin.org/article/10.3389/fnbot.2017.00002},
}

First NRP User Workshop

Date: 11.01.2017
Venue: TU München
Duration: 1 Day

With the NRP running very smoothely, it was now time to invite actual external users to show our platform to them. A second part of this workshop was to understand their research requirements and get feedback from them. This helped us to understand what we need to implement in order for them to really use our product.

Below, you can see an impression from one of the presentations.

20170112_103307.jpg

Publication in a Supplement to Science on Brain-Inspired Intelligent Robotics

The article “Neurorobotics: A strategic pillar of the Human Brain Project” was released in a Science Supplement on “Brain-inspired intelligent robotics: The intersection of robotics and neuroscience”, explaining the importance of our subproject and its research.

Read it here: http://www.sciencemag.org/sites/default/files/custom-publishing/documents/Brain-inspired-robotics-supplement_final.pdf?_ga=1.158217660.785230381.1481986150

science.jpg

(image source: http://www.sciencemag.org/sites/all/themes/science/images/facebook-share.jpg)

Publication

@article{Knoll2016,
title={Neurorobotics: A strategic pillar of the Human Brain Project},
author={A. Knoll, M.-O. Gewaltig},
journal={Supplement to Science},
year={2016},
link = {http://www.sciencemag.org/sites/default/files/custom-publishing/documents/Brain-inspired-robotics-supplement_final.pdf}
}

 

Publication

@inproceedings{kaiser2016,
title={Towards a Framework for End-To-End Control of a Simulated Vehicle with Spiking Neural Networks},
author={J.Kaiser, J.C. Tieck, J. Hubschneider, P. Wolf, M. Weber, M. Hoff, A. Friedrich, K. Wojtasik, A. Roennau, R. Kohlhaas, R. Dillmann, J. Zöllner},
journal={International Conference on Simulation, Modeling, and Programming for Autonomous Robots},
year={2016},
pages={Forthcoming},
organization={IEEE},
link={https://www.researchgate.net/publication/309558315_Towards_a_framework_for_end-to-end_control_of_a_simulated_vehicle_with_spiking_neural_networks}
}

Assistant to the Software Development Director

TUM_logo_square.pngembedded_systems

hbp_small

date = {13.12.2016},
start = {15.02.2017 or later},
type = {perm},
contactName = {Florian Röhrbein},
contactMail = {florian.roehrbein@in.tum.de},
background ={The Human Brain Project (HBP) is an ambitious large-scale research  initiative funded by the European Commission with a high worldwide visibility. About 100 research institutes from different disciplines all over Europe cooperate intensively to  achieve a multi-level, integrated understanding of brain structure and function through the development and use of information and communication technologies (ICT). The project will run for about 10 years and during this time six ICT platforms will be developed. The Neurorobotics Platform (NRP) is a web-based platform for the design and performance of neurorobotics experiments, and is built under the aegis of Prof. Alois Knoll. It grants  neuroscientists easy access to state-of-the-art simulators: spiking neural networks,  robotics and physics. These simulators are connected together and coordinated within a closed loop. They run on high performance computing resources and on neuromorphic hardware. The NRP also provides tools to create neurorobotics experiments, namely designers for the creation of brain-body interfaces, virtual worlds and robot models. To strengthen our Neurorobotics team at TUM we are looking for an Assistant to the Software Development Director.},
description = {We are looking for someone with a Ph.D. or similar experience in a subject which is relevant to the direction of the project such as robotics, autonomous systems, computer science, mathematics, engineering or a related field. We offer a responsible position with interesting and challenging tasks in an interdisciplinary scientific and management team, Worldwide networking opportunities with leading robotics and neuroscience experts, The opportunity to grow the role and the responsibility through the development of new project opportunities, Remuneration in line with the current German public service salary scale TV-L, level E13/14, A modern working environment based at the TUM Campus in Garching / Munich. Applicants should submit a cover letter and a detailed CV in PDF format only, with file name “<surname>_HBP_Assistant_cover” and “<surname>_HBP_ Assistant_CV” electronically to florian.roehrbein@in.tum.de. Duration of contract: 31.03.2018. See assistant_to_the_software_development_director for the pdf version.

},
tasks = {# Supporting the Software Development Director of the HBP
# Carrying out project related work including work package related tasks and reporting
# Developing concepts for future directions for software adaptation and improvement of
development processes of HBP software as a whole
# Supervision of scientific advancement of the software tools and processes for the whole of HBP},
requirements = {# Very good knowledge of software engineering, robotics and model-based development
# Experience in developing robotics software, e.g., kinematics/dynamics, control of actuators/sensors, world models, ontologies, distributed systems
# Fluency in spoken and written German and English
# High motivation and willingness to work in an international and interdisciplinary team
# Willingness to travel}

pdf = {https://hbpneurorobotics.files.wordpress.com/2016/12/assistant_to_the_software_development_director.pdf}

HBP Summit 2016

Date: 12.10.2016
Venue: Florence

Duration: 3 days

The HBP held its 4th annual Summit on 12 to 15 October in the vibrant city of Florence, Italy. The event was hosted by Laboratorio Europeo di Spettroscopie Non Lineari (European Laboratory for Non-Linear Spectroscopy; LENS), one of the key European institutions for light wave research, which has been a centre of excellence at the University of Florence since 1991.
The 2016 HBP was launched with ‘Open Day’ to enable dialogue and collaboration between the HBP, other scientific communities and the public. The Open Day took place on 12 October—for more information, please see the Open Day webpage.

Nearly 450 members of the HBP consortium, representatives of HBP’s first Partnering Projects, National Research Funding Agencies, and representatives from Italy’s national research council participated in the Summit. The programme featured a diverse mixture of plenary sessions, parallel working group meetings, a poster session with over 100 posters and networking opportunities. The sessions covered an array of scientific themes, a town hall meeting, an introduction to HBP’s first Partnering Projects, a young investigator’s plenary session, and a panel debate on “the Conscious Computer.” In a dedicated session on “the local context”, representatives of Italy’s National Research Council, the University of Florence and the Ministry of Research and Education provided insights about the role of the Flagship and benefits of a large science project for science and research in Italy. For more information on the sessions, please see the programme.

Florence, the capital of the Tuscany region of Italy, is considered one of the world’s most beautiful cities. It is particularly noted for its Renaissance art and architecture, and its historic centre was declared a World Heritage Site by UNESCO in 1982.

The HBP was proud to hold its Summit in such a magnificent location.

summit.jpeg

(Text and image from https://www.humanbrainproject.eu/hbp-summit-2016)

Understanding the human brain

Date: 29.11.2016
Venue: European Parliament Brussels

At the event “Understanding the human brain – a new era of big neuroscience” hosted by the European Parliament in Brussels this week, the HBP sent delegates to present our work. The SP10 did not miss out on this opportunity either.

The picture shows Prof. Alois Knoll with Tetsuo Yamamori and Roboy, a cutting edge technology robot in the HBP.

brussels_29-11

Click here to learn more about Roboy: http://roboy.org/

Click this link to learn more about the event: http://www.europarl.europa.eu/stoa/cms/home/workshops/neuroscience2016

Neuroscience 2016 in San Diego

The SP10 will have a booth in San Diego to present our platform to the neuroscience community.

Learn more about the event here: https://www.sfn.org/annual-meeting/neuroscience-2016

“SfN’s 46th annual meeting is the premier venue for neuroscientists to present emerging science, learn from experts, collaborate with peers, explore new tools and technologies, and advance careers.

Neuroscience 2016 will take place November 12-16 at the San Diego Convention Center. Join more than 30,000 colleagues from more than 80 countries at the world’s largest marketplace of ideas and tools for global neuroscience.”

sfn.png

(Text and image from the link above)

Design of a Robot Mouse

description = {Currently, running, monitoring and debuggin neural networks on SpiNNaker is a complex process based on many different tools. A task-specific prototype for interactive development ad debugging is already available. Your task will be to start extending this prototype to an Integrated Development Environment (IDE) based on a thorough requirements analysis.(Photo: http://apt.cs.manchester.ac.uk/projects/SpiNNaker/hardware/) },

background = {The Neurorobotics subproject of the Human Brain Project is developing the tools and the theory to connect state of the art simulations of highly realistic brain models to robots. A central goal of this effort is to enable meaningful interaction between the simulated brains and the environment through realistic bodies. As stated in the theory of embodiment, the structure and the physical properties of these bodies have a huge impact on brain development and neural information processing. For example, the specific properties of the morphology of human and animal bodies like softness and compliance simplify the control task whcih has to be computed by the brain. With intelligent co-design of robot bodies and brain inpired neural control systems being a promising approach for both robotics and neuroscience, we are currently designing a low-cost biomimetic robot mouse.},
type = {student},

furtherLinks = {# http://www.humanbrainproject.eu
# http://www.neurorobotics.net
# Pfeifer, R. & Bongard, J. (2006). How the Body Shapes the Way We Think: A New View of Intelligence. MIT Press.},

requirements = {# Interest in biomimetic robotics
# Good knowledge of CAD (depending on the selected task)
# Experience with rapid prototyping tools may be of advantage},

date = {14.10.2016},
start = {Now},
type = {student},
contactName = {Florian Walter},
contactMail = {florian.walter@tum.de},
pdf = {https://hbpneurorobotics.files.wordpress.com/2016/10/robot_mouse.pdf}

tum_logo_squareembedded_systems

Sample student job offer

TUM_logo_square.pngembedded_systems

date = {14.10.2016},
start = {Now},
type = {student},
contactName = {Florian Röhrbein},
contactMail = {florian.roehrbein@in.tum.de},

background = {Spiking neural networks are detailed models of the biological neural circuitry found in the brains of humans and animals. Unlike highly simplified neuron models used in artificial neural networks, spiking neurons exhibit complex dynamics and exchange information via discrete impulses called spikes. In the Neurorobotics subproject of the Human Brain Project, researchers develop the tools required to connect highly realistic spiking neuron-based models of the brain to robots. However, standard PCs are too slow to execute the models in real-time. Controlling robots based on on the outputs of simulated brains therefore requires specialized neuromorphic hardware like SpiNNaker which is tailored to the simulation of spiking neural networks. The SpiNNaker architecture is based on standard ARM cores, but features an efficient hardware-based modular routing system whcih transmits spikes between different chips and enables the simulation of spiking neural networks in biological real-time},
description = {Currently, running, monitoring and debuggin neural networks on SpiNNaker is a complex process based on many different tools. A task-specific prototype for interactive development ad debugging is already available. Your task will be to start extending this prototype to an Integrated Development Environment (IDE) based on a thorough requirements analysis.(Photo: http://apt.cs.manchester.ac.uk/projects/SpiNNaker/hardware/) },
requirements = {- master’s degree in mathematics, computer science, physics, or similar
– knowledge in graph theory and its application to measured data
– very good programming skills
– fluent in written and spoken English
– ability to work independently as well as in international teams
– knowledge in (computational) neuroscience and neural networks is helpful
– Matlab and Python skills are helpful},
tasks = {- taks1
– task2
– task3}

Publication

@inproceedings{kirtay2016sequential,
title={Sequential Decision Making Based on Emergent Emotion for a Humanoid Robot},
author={Kirtay, Murat and Vannucci, L. and Falotico, E. and Oztop, Erhan and Laschi, C.},
booktitle={2016 16th IEEE-RAS International Conference on Humanoid Robots (Humanoids)},
link = {http://muratkirtay.com/pdfs/humanoids2016_Sequential.pdf},
pages={},
year={To appear 2016},
organization={IEEE}
}

Publication

@ARTICLE{Ambrosano201616,
title={Retina color-opponency based pursuit implemented through spiking neural networks in the neurorobotics platform},
author={Ambrosano, A., Vannucci, L., Albanese, U., Kirtay, M., Falotico, E., Martínez-Cañada, P., Hinkel, G., Kaiser, J., Ulbrich, S., Levi, P., Morillas, C., Knoll, A., Gewaltig, M.-O., Laschi, C.},
link = {http://muratkirtay.com/pdfs/LivingMachines2016_Retina.pdf},
journal={Lecture Notes in Computer Science},
year={2016},
volume={9793},
pages={16-27},
doi={10.1007/978-3-319-42417-0_2},
document_type={Conference Paper},
}

Publication

@ARTICLE{Vannucci2016341,
author={Vannucci, L., Falotico, E., Tolu, S., Dario, P., Lund, H.H., Laschi, C.},
title={Eye-head stabilization mechanism for a humanoid robot tested on human inertial data},
link = {http://muratkirtay.com/pdfs/LivingMachines2016EyeHead.pdf},
journal={Lecture Notes in Computer Science},
year={2016},
volume={9793},
pages={341-352},
doi={10.1007/978-3-319-42417-0_31},
document_type={Conference Paper},
}

Publication

@ARTICLE{Kirtay2016119,
author={Kirtay, M., Falotico, E., Ambrosano, A., Albanese, U., Vannucci, L., Laschi, C.},
title={Visual target sequence prediction via hierarchical temporal memory implemented on the iCub robot},
link = {http://muratkirtay.com/pdfs/LivingMachines2016_HTM.pdf},
journal={Lecture Notes in Computer Science},
year={2016},
volume={9793},
pages={119-130},
doi={10.1007/978-3-319-42417-0_12},
document_type={Conference Paper},
}

Publication

@CONFERENCE{Vannucci201625,
author = {Vannucci, L., Tolu, S., Falotico, E., Dario, P., Lund, H.H., Laschi, C.},
title = {Adaptive gaze stabilization through cerebellar internal models in a humanoid robot},
journal = {Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics},
year = {2016},
volume = {2016-July},
pages = {25-30},
doi={10.1109/BIOROB.2016.7523593},
document_type={Conference Paper},
link={http://ieeexplore.ieee.org/document/7523593/}
}

More for less – Energy Efficiency in Neural Locomotion – Workshop

Date: 21.09.2016
Venue: Berlin

During September 21-23, 2016 as part of the Bernstein Conference in Berlin, the workshop for “Energy Efficiency in Neural Locomotion” (Stratmann, Röhrbein) will take place.

The following links will give you more detail about the event.

http://www.in.tum.de/index.php?id=6814

www.bernstein-conference.de
http://www.nncn.de/en/bernstein-conference/2016/satellite-workshops/more-for-less-energy-efficiency-in-neural-locomotion-control-stratmann-rohrbein-1

Permanent job offer template

TUM_logo_square.pngdlrlundembedded_systems

date = {14.10.2016},
start = {2 Months after acceptance},
type = {perm},
contactName = {Florian Röhrbein},
contactMail = {florian.roehrbein@in.tum.de},
background = {Background on the project},
description = {We are seeking an enthusiastic and talented PhD student to join the Robotics and Embedded Systems group in the Department of Informatics at the Technical University of Munich (TUM). The successful candidate is supposed to extract the adjacency matrix describing the functional connectivity of the spinal cord circuitry. While our general project is based on electrophysiological patch clamp measurements, the candidate will focus on graph theoretical analysis. The results are expected to be integrated into the Human Brain Project, a €1bn flagship project of the European Commission, as an interface that connects brain simulations with robotic platforms. The student will work in an enriching, interdisciplinary, and international collaborative framework at the leading department of informatics in Germany (cf. the Shanghai and the QS ranking). Partners of our project include the chair of Sensor Based Robotic Systems and Intelligent Assistance Systems at TUM, members of The Human Brain Project, and the Institute of Robotics and Mechatronics at the German Aerospace Center (DLR). The student is furthermore expected to complete some of his work in the Department of Experimental Medical Science at Lund University. We offer a competitive funding at 100% on the German employee scale TV-L 13. Interested applicants should provide florian.roehrbein@in.tum.de with a cover letter, a CV, and the contact information of reference letter writers. Please don’t hesitate to contact us in case of questions. },
requirements = {# master’s degree in mathematics, computer science, physics, or similar
# knowledge in graph theory and its application to measured data
# very good programming skills
# fluent in written and spoken English
# ability to work independently as well as in international teams
# knowledge in (computational) neuroscience and neural networks is helpful
# Matlab and Python skills are helpful}
tasks = {# Supporting the Software Development Director of the HBP
# Carrying out project related work including work package related tasks and reporting
# Developing concepts for future directions for software adaptation and improvement of
development processes of HBP software as a whole
# Supervision of scientific advancement of the software tools and processes for the whole of HBP},

New publication!

@article{test,
author = {G. Hinkel, H. Groenda, S. Krach, L. Vannucci, O. Denninger, N. Cauli, S. Ulbrich, A. Roennau, E. Falotico, M.-O. Gewaltig, A. Knoll, R. Dillmann, C. Laschi and R. Reussner},
title = {A Framework for Coupled Simulations of Robots and Spiking Neuronal Networks},
journal = {Journal of Intelligent & Robotic Systems manuscript},
year = {2016},
link = {http://www6.in.tum.de/Main/Publications/HBP2016Framework.pdf}
}

Publication Announcement

@article{richter2016musculoskeletal,
title={Musculoskeletal Robots: Scalability in Neural Control},
author={C. Richter, S. Jentzsch, R. Hostettler, J. Garrido, E. Ros, A. Knoll, F. Röhrbein, P. van der Smagt, and J. Conradt},
journal={IEEE Robotics & Automation Magazine},
year={2016},
doi={10.1109/MRA.2016.2535081},
  issn={1070-9932},
volume={23},
issue={4},
pages={128-137},
link={http://ieeexplore.ieee.org/document/7553551/},
}

Publication

title = {Computation by time},
link = {http://link.springer.com/article/10.1007%2Fs11063-015-9478-6},
author = {Florian Walter, Florian Röhrbein, and Alois Knoll},
journal = {Neural Processing Letters, pages 1-22},
year = {2015}

Publication

title = {Learning Spiking Neural Controllers for In-Silico Navigation Experiments},
link = {https://mediatum.ub.tum.de/doc/1303900/1303900.pdf},
author = {Mahmoud Akl, Florian Walter and Florian Röhrbein},
journal = {Technical Report (TUM)},

Publication

title = {A Domain-Specific Language (DSL) for Integrating Neuronal Networks in Robot Control},
link = {http://neurorobotics.net/fileadmin/user_upload/PDF/A_Domain-Specific_Language_for_Integrating_Neuronal_Networks_in_Robot_Control.pdf},
author = {Georg Hinkel, Henning Groenda, Lorenzo Vannucci, Oliver Denninger, Nino Cauli, and Stefan Ulbrich},

Publication

title = {Real-time Cerebellar Control of a Compliant Robotic Arm},
link = {http://neurorobotics.net/fileadmin/user_upload/PDF/Poster_Real_time_Cerebellar_Control_of_a_Compliant_Robotic_Arm.pdf},
author = {Christoph Richter, Sören Jentzsch, Florian Röhrbein, Patrick van der Smagt, and Jörg Conradt},
journal = {BCCN conference, Heidelberg},
year = {2015}

Publication

title = {A visual tracking model implemented on the iCub robot as a use case for a novel neurorobotic toolkit integrating brain and physics simulation},
author = {L.Vannucci, A. Ambrosano, N. Cauli, U. Albanese,· E. Falotico, S. Ulbrich,  L. Pfotzer, G.Hinkel, O.Denninger, D.Peppicelli, L. Guyot, A. Von Arnim, S. Deser, ·P. Maier, · R. Dillmann, G. Klinker, P. Levi, A. Knoll, · M.-O. Gewaltig, C. Laschi},
journal = {Proceedings of the international Conference on Humanoid Robotics, Seoul, 2015},

Publication

title = {A sparse reformulation of the Green’s function formalism allows efficient simulations of morphological neuron models},
author = {Wybo, W., Boccalini, D., Torben-Nielsen, B., & Gewaltig, M. O. },
journal = {Accepted to appear in Neural Computation journal},

Publication

title = {A bio-inspired model of visual pursuit combining feedback and predictive control for a humanoid robot},
author = {Egidio Falotico, Lorenzo Vannucci, Nicola Di Lecce, Paolo Dario, Cecilia Laschi},
journal = {International Conference on Advanced Robotics (ICAR) 2015},

Publication

title = {Integrating feedback and predictive control in a bio-inspired model of visual pursuit implemented on a humanoid robot},
author = {Lorenzo Vannucci, Egidio Falotico, Nicola Di Lecce, Paolo Dario, Cecilia Laschi},
journal = {International conference on biomimetic and biohybrid systems (Living Machines) 2015},

Publication

title = {Neurorobotics – New Perspectives in the Synergy between Neuroscience and Robotics},
author = {Cecilia Laschi, Florian Walter, Egidio Falotico, Florian Röhrbein},
journal = {Workshop at the International Conference on Biomedical Robotics and Biomechatronics (Biorob), June 26th},

Publication

title = {A Framework for Coupled Simulations of Robots and Spiking Neuronal Networks},
author = {G. Hinkel, H. Groenda, L. Vannucci, O. Denninger, N.Cauli, S. Ulbrich, E. Falotico, A. Roennau, M. Gewaltig, A. Knoll and R. Dillmann, C. Laschi, R. Reussner},
journal = {Journal Intelligent & Robotic Systems, Submitted},

Neurorobotics Workshop at IROS, Daejeon, Korea

Date: 10.10.2016
Venue: Daejeon, Korea

At IROS 2016 in Daejeon, Korea, there will be an HBP workshop titled “Tutorial for IEEE/RSJ International Conference on Intelligent Robots and Systems” targeting various audiences like students, engineers and researchers of the fields of robotics and or computational neuroscience alike as well as the fields of machine learning and cognitive robotics.

More information can be found here: https://www.fzi.de/en/research/projekt-details/human-brain-project/iros-2016-neurorobotics-workshop/

 

hbp_small

 

From Rats to Robot Navigation and Beyond

Date: 04.07.2016
Venue: TUM Campus Garching

Lecture Series in Neuro-Robotics

Speaker: Prof. Michael Milford, Queensland University of Technology

Prof. Milford from Queensland University of Technology will give a talk on the topic of From Rats to Robot Navigation and Beyond here in Munich in our new lecture series in Neuro-Robotics. You are cordially invited to join his fascinating presentation.

 

Cronoshbp_small

Intelligence Emerging from Neural Activities

Date: 01.07.2016
Venue: IAS Auditorium

Lecture Series in Neuro-Robotics

Speaker: Prof. Hirokazu Takahashi, The University of Tokyo

Prof. Takahashi from The University of Tokyo will give a talk on the topic of Intelligence Emerging from Neural Activities here in Munich in our new lecture series in Neuro-Robotics. You are cordially invited to join his fascinating presentation.

 

Cronoshbp_small

ISC High Performance Event 2016

Date: 19.06.2016
Venue: Frankfurt am Main, Germany

This years ISC High Percormance Conference will focus on HPC technological development and its application in scientific fields and commercial environments. As the first speaker Dr. Florian Röhrbein will present “Neurorobotics in the Human Brain Project”, Tuesday, June 21st 2016, 11:00 am – 11:30 am, for the “Neurorobotics & Supercomputing: The Human Brain Project & Other Human & Humanoid Approaches” session.

Details:

Tuesday, June 21st, 2016, 11:00 am – 12:30 pm
Oanorama 2 Messe Frankfurt

ISC

Full-day Tutorial on „Virtual Neurorobotics in the Human Brain Project“ at IEEE/RSJ IROS

Date: 09.10.2016

Venue: Daejeon, Korea

iros_Korea_2016.png

Details:

The theme of this year’s IROS conference is ’Road to companionship with intelligent robots in everyday life and workspaces’. Stefan Ulbrich, Rüdiger Dillman, Egidio Falotico and Cecilia Laschi will present the full-day tutorial titled ‘Virtual Neurorobotics in the Human Brain Project’ divided into invited talks and a hands-on session showing the capabilities of the HBP Neurorobotics Platform.

The conference will take place in Daejeon, Korea, from 9 October to 14 October 2016.

More information can be found at http://url.fzi.de/iros-2016

2nd Japan-EU Workshop on Neurorobotics

Date: 29.04.2016
Venue: University of Tokyo

Building robots with brain-inspired control structures is one of the central goals of the members working in the Neurorobotics sub-project of the HBP. They are, however, not alone in this task and so it should come as no surprise that also other researchers have made great progress in recent years. Research teams in Japan have made astonishing discoveries and provided fascinating insights into complex matters concerning biological systems such as brain structures and musculoskeletal models.

So, with researchers both in Europe and in Japan making great steps towards a better understanding of biological systems, the Japan-EU Workshop on Neurorobotics held in Tokyo aimed at bringing those experts together. Presentations from both sides gave an overview of their work and highlighted their latest achievements. The presentations were followed by lively discussions, which allowed the participants to engage and fully comprehend the potential advantage arising from gaining access to both sides’ resources.

To give a practical impression of what the University of Tokyo brings to the table, the students presented their research and the hydraulic robot Hydra (see Figure below).

With researchers from many different backgrounds and with various fields of interest a wide foundation was laid for further ventures. And even though the research was overlapping in some aspects, the large number of areas of expertise made it apparent how both parties in this workshop might benefit from the opportunities offered by a cooperation.

A big step in the direction of working together in the future was made and it stands to reason that a joint research is not far now and that the two teams can join forces in the near future to ultimately unravel the mysteries of the human brain in all its complexity.

Pictures, presentations and links to publications relevant to the workshop can be found on the SP’s homepage http://www.neurorobotics.net

 

2016_Tokyo_group2016_Tokyo_hydra

Announcement: Release of the Neurorobotics Platform!

On March 30, all 6 platforms of the Human Brain Project will be released, including the Neurorobotics Platform. This event will be web-streamed live and thus provides an excellent opportunity to learn more about the HBP and its technology platforms

Streaming starts at 9:30, for details see https://www.humanbrainproject.eu/194 and

 

We have released the NeuroRobotics Platform 1.0. The NeuroRobotics Platform (NRP) developed in the Human Brain Project (HBP) is an Internet-accessible simulation system that allows the simulation of robots controlled by spiking neural networks. Additionally, we offer you many tutorial videos, to get you started, full documentation and access to our platform depended on your needs. Go and try it out.

csm_Header_PlatformRelease_f967987e33.jpg

SP10 workshop @BioRob 2016, Singapur

Our workshop proposal for BioRob 2016 has been accepted! The 6th International conference on Biomedical Robotics and Biomechatronics (BioRob) will take place on June 26-29 in Singapur. For more information visit the official website: http://www.ieeebiorob2016.org/

 

csm_BioRob2016_Logo_bfd723a688.jpg

Workshop title: Neurorobotics – New perspectives in the synergy between Neuroscience and Robotics

 

More information:

Neurorobotics represents the two-front approach to the study of intelligence: Neuroscience attempts to discern what intelligence consists of by investigating intelligent biological systems, while Robotics attempts to recreate intelligence through non-biological, technical methods by building artifacts provided with control based on machine learning

Neurorobotics is already an established branch of robotics that in the last years, taking advantage from an increase in the accessibility of existing neuroscientific data and knowledge, allowed building robotic systems that can exhibit robustness, adaptability and several features of the human intelligence. Reciprocally, significant developments in robotics and machine learning put robotics in the service of neuroscience as experimental platforms or test-beds of brain models.

In the last years, advanced insights and the increasing availability of cheap processing power has led Neurorobotics to follow two tracks of research with different goals and methods:

The first track focuses on neuro-inspired computing paradigms that mimic nervous system function based on Spiking Neural Networks. This not only fosters our understanding of biological systems but also contributes to future technical applications in artificial systems. In the past, limited processing power and the lack of appropriate models and tools shifted the focus of research far away from biological neural networks. Recently a number of projects like the US BRAIN Initiative and the Human Brain Project have taken up the challenge by combining efforts from the fields of neuroscience and computer science to enable the large scale modeling and simulation of biological neural networks with billions of spiking neurons.

The second track, extending the theory of classical artificial neural networks, mostly rely on simpler neuron models but integrate them in novel network architectures. These networks are extensively used in robotics, allowing mimicking the function of some brain areas in order to reproduce complex behaviors with a reduced computational cost.

This workshop seeks to present and discuss advances in neuroscientific models for cognition and new perspectives in control for robotic applications based on both biologically-inspired and artificial neural networks. The final goal is to bring together researchers from both robotics and neuroscience in order to explore how to maximize the progress at the multidisciplinary frontier evaluating the advantages of both tracks of the Neurorobotics research.

 

For more details about our workshop:

http://sssa.bioroboticsinstitute.it/workshops/biorob2016

You’re a Software Engineer and looking for a new challenge? Take a look at our job page!

We’re looking for an Experienced Software Engineer to strengthen our Neurorobotics team at TUM. We’re an interdisciplinary, dynamic and young team. The Neurorobotics Platform (NRP) is part of EU-funded Human Brain Project (HBP). You’ll participate in the development of a web-based simulation interface. Send your application to: florian.roehrbein@in.tum.de

For more details follow the linkhbp_small

A summary of our IROS workshop can be found on Robohub!

Check the robohub page for a little summary of our IROS workshop in Hamburg. A link can be found here in the news item or on our workshop page. In our download section you can find the presentation slides of all talks given at our workshop. You must log-in before.

csm_IROS_logo_01_e40f52f041A summary of the workshop can be found on robohub: link

Title: Advances in Biologically Inspired Brain-Like Cognition and Control for Learning Robots

 

Organizers: Florian Walter, Florian Röhrbein, Stefan Ulbrich and Rüdiger Dillmann

Date: Friday, 02 October 2015, 8-12am

Place: Hamburg, Germany

Link: http://www.iros2015.org

For more information about the workshop, e.g. topics, invited speakers please see our workshop page.

BioRob 2016

Date: 26.06.2016
Venue: Singapore

On June 26th, 2016 a Neurorobotics workshop will take place as part of the “6th IEEE RAS & EMBS – International Conference on Biomedical Robotics and Biomechatronics”, the BioRob 2016, in Singapore.

This years motto: New perspectives in the synergy between Neuroscience and Robotics”

 

The following link will lead you to more detailed information on the event.

sssa.bioroboticsinstitute.it/workshops/biorob2016

Wo/Man, Mind, Machine

Date: 13.06.2016
Venue: Berlin-Brandenburgische Akademie der Wissenschaften (BBAW), Einstein-Saal, Jägerstr. 22/23,  10117 Berlin

In Cooperation with the “Israel Young Academy” the “Young Academy” hosts a two day conference, June 13-14, 2016 in Berlin, Germany.

The following is the timeline for the event:

 

MONDAY, 13 JUNE 2016

10:00 Welcome & Introduction

10:15 Keynote: Aldo Faisal (Neurotechnology, Imperial College London): “Perception, Action, and the Grammar of Behaviour”

11:15–11:45 Coffee Break

11:45–13:15 Session 1: The Social Brain – How We (Fail to) Understand Others. Philipp Kanske & Mona Khoury-Kassabri

13:15–15:00 Lunch Break

15:00–16:00 Session 1 (continued)

16:00–16:30 Coffee Break

16:30–18:00 Session 2: Artificial Minds in Film, Performance, and Fiction. Caspar Battegay & Nissim Otmazgin

18:15 Evening lecture: Jennifer Parker-Starbuck (Theatre & Performance Studies, University of Roehampton, London ): “Cyborg Encounters”

19:15 Reception

20:30 Dinner

TUESDAY, 14 JUNE 2016

09:30 Keynote: Alexis Kirke (Computer Music, University of Plymouth): “For entertainment purposes only? How arts can contribute directly to research into the science of computing and HCI”

10:30–11:00 Coffee Break

11:00 Session 3: Mind, Man, Machine, and Music. Miriam Akkermann & Sharon Aronson-Lehavi

13:00–14:30 Lunch Break

14:30 Session 4: Processing Information – Brains, Bodies, and Bacteria. Sibylle Baumbach & Ron Milo
With Florian Röhrbein (Informatics, Technical University of Munich) on Neurorobotics and The Human Brain Project

16:30–17:00 Coffee Break

17:00 Roundtable & Final Discussion

17:30 End of the Conference

 

For more information, you can also take a look at the flyer:

20160504_Flyer_FINAL-1

Kickoff Meeting of SGA1 2016

Date: 07.06.2016
Venue: Geneva, CBS Building B1, 9 chemin des Mines, 1202 GE

hbp_smallWe are excited to announce the following agenda for the Kickoff Meeting of SGA1 during the 7th and 8th of June 2016 in Geneva.

 

 

Tuesday:

9:15 – 10:00

General introduction (Marc-Oliver Gewaltig, EPFL)
What is SP10? What is SGA1? What is a Co-Design project?
What are the different roles in the project?
Scientific Coordinator election
10:00 – 10:15

Coffee break
10:15 – 11:45

Round table (5 minutes per institution)
UGENT, DTU, UGR, SSUP, FZI, TUM, Fortiss, EPFL-CNP,
EPFL-IRP, EPFL-BIOROB, EPFL-LPSY, EPFL-CYBERBOTICS
11:45 – 12:00

SP10 Platform demo (Igor Peric, Georg Hinkel, FZI)
Live demo and discussion
12:00 – 13:00

Lunch (CBS Cafeteria)
13:00 – 13:05

Election of the Scientific Coordinator
13:05 – 13:15

Software development road map and methodology (Axel von Arnim, Fortiss)
13:15 – 15:00

Scientific experiments: research planning (chaired by Scientific Coordinator)
Summary of proposed experiments
Small research groups draft scientific experiments that will drive the
development of the Neurorobotics platform
15:00 – 15:15

Coffee break
15:15 – 16:45

Summary of research planning (chaired by Scientific coordinator)
Presentation of collected ideas,
Consolidation, writing of roadmap
Questions and Answers
16:45 – 18:30

Second Periodic Review preparation
(review presenters only)
19:30 – 21:00

SP10 networking Diner (restaurant “La Bagatelle”)
Wednesday:

9:15 – 10:15

HBP resources
Resources (Axel von Arnim, Fortiss), visualization (Cyrille Favreau, BBP)
10:15 – 10:30

Coffee break
10:30 – 12:00

HBP services
Collab (Olivier Amblet, BBP)
12:00 – 13:00

Lunch (CBS Caféteria)
13:00 – 15:00

Epic grooming (SP10 Development Team – no researchers involved)
15:00 – 15:15

Kickoff wrap-up and closing (Prof. Alois Knoll, TUM)

 

Talk about HBP/Neurorobotics at the Queen Mary University of London

Date: 02.09.2015
Venue: Queen Mary University of London

On Wednesday 2nd September 2015, Florian Röhrbein gave a talk about the Human Brain Project and especially about the research done in the Neurorobotics subproject. In his talk, he gave an overview of the HBP, outlined the goals of the Neurorobotics subproject, and reported on our results achieved in the first phase of the project. For more information about this talk click on the Link.Queen_Mary_Logo.png

Thank you for all poster submissions!

We will check each submission and inform you as soon as possible.

We encourage the submission of poster abstracts for our IROS 2015 workshop (more information here). Accepted submitters will not only get the chance to present their posters during this exciting event and meet other experts from the field but also to publish their work in a special issue of the journal Frontiers in Neurorobotics. Submitted abstracts should be 0.5 – 2 pages long and will be reviewed by at least two peers. The selection of accepted posters will be done by the organizing committee, based on the reviews. We are looking forward to receiving your submission!

csm_IROS_logo_01_e40f52f041.jpg

Abstract Submission Deadline: August 15

Notification of Acceptance: September 07

Topics of Interest:

  • Neurorobotics
  • Spiking Neural Networks
  • Bio-Inspired Learning
  • Embodiment
  • Reservoir Computing
  • Self-Organization
  • Deep Learning

In case of further questions please contact:

Florian Walter

Department of Informatics VI
Technische Universität München
Boltzmannstr. 3, 85748 Garching


Email: florian.walter@tum.de

We have released new information about our Symposium!

New information available! Check here for the latest updates! We keep you up-to-date!

We have released new information about our Symposium! Check the PDF-file for more details about the upcoming event.

Title: Neurorobotik: Chancen und Herausforderungen interdisziplinärer Forschung in Informatik, Robotik & Neurowissenschaften

Date: October 8-9, 2015

Place: TUM Institute for Advanced Study, Munich

Neurorobotics Learning Event in Tokyo

Date: 18.04.2015
Venue: University of Tokyo

The HBP Neurorobotics Team in cooperation with the University of Tokyo organized a whole day workshop focusing on Neurorobotics. The workshop took place on the 18th of April at University of Tokyo. The workshop was sponsored by the HBP and the Global University Project, MEXT. Further details can be found on the webpages: http://www.ynl.t.u-tokyo.ac.jp/workshop/neurorobotics/home.html and http://www6.in.tum.de/japan-eu-neurorobotics-2015/

Here some impressions from the workshop:

IMAG1214IMAG1215IMAG1221

 

We have released the Neurorobotics Plattform!

Check the full article for more details about our 1st release! What is the Neurorobotics Plattform? What to expect from the first initial release? How can you contribute?

First initial release of the Neurorobotics Platform (SP10)

The internal first initial release of the Neurorobotics Platform went online this week. For this reason, we would like to invite you all, the members of the consortium, to try and test it to get a glance of the current status of development.

What is the Neurorobotics Platform?

The Neurorobotics Platform is an Internet-accessible simulation system that allows neuroscientists to validate cognitive and behavioral capabilities of brain models. There is little to no programming overhead involved for setting up and running experiments that are reproducible and can be easily shared among researchers. To this end, users can plan, run and evaluate in silico behavioral and cognitive neuroscience experiments, in which brain models are connected to a virtual body, which is then exposed to a virtual dynamic and sensory-rich environment. Scientists can then define experimental protocols and study behavioral or cognitive phenomena by running virtual experiments following these protocols. The platform will also provide detailed body-models, which are calibrated with real hardware acting in the real world. Furthermore, the NRP will easily grant access to the
high-performance computing clusters provided by the HBP as well as to neuromorphic hardware.

 

What to expect in the first initial release?

This first internal release of the NRP is targeted at all members of the HBP consortium and represents the current state of development. It will give you a first glance at how the NRP can be used to test and investigate brain or network models in closed loop experiments. Right now, the NRP is configured to run a single experiment with two different robots. In both experiments the robot is controlled by a tiny neural network, which is wired to detect the color red and to steer the robot towards this color. The experiment runs inside a virtual room with two TV screens that are attached to opposite walls. The user can change the color of the screen during the experiment and thereby decide where the robot should move. The spiking activity of the robot’s “brain” can be displayed while the experiment is running. Since the experiment is accessed from your web browser, several users can observe and join the experiment as the same time. In future releases, the platform will allow users to define and run their own experiments and to download the simulation results for off-line analysis.

How can you contribute?

Obviously, your biggest contribution to this first internal release is to report any problems you encounter and to make suggestions for future developments. In addition we are looking or scientists who are interested in helping us designing the future capabilities of the Neurorobotics Platform by providing concrete use cases and research topics involving network or brain models connected to (virtual) robots or bodies. These would help us in the following ways:

  1. by defining the experimental protocols that the Neurorobotics Platform supportsalong with the stimulation and measurement protocols
  2. by defining the body/robot and environment models that must be provided by the NRP
  3. by defining the brain models which are needed from SP6 which in turn define priorities for the types of data needed from SPs 1-3
  4. by providing data from behavioral or cognitive neuroscience experiments that helps constraining brain models from SP6 under similar experimental conditions
  5. by informing SP4 about theoretical models which will help understanding the simulated phenomena.
  6. by providing use-cases for running in silico experiments in real-time, using the neuromorphic computing systems from SP9.

If you are interested, please note this in the survey or contact the NRP team directly by email: neurorobotics@humanbrainproject.eu

Symposium Neurorobotics: Chances and Challenges

Date:08.10.2015
Venue: TUM IAS, Munich

MaxWeber_Symposium_Logo.png

Place: TUM Institute for Advanced Study & TUM Department of Informatics, Garching (close to Munich)

 Topic (in german):

Unser Gehirn. Es ist ständig aktiv, egal ob wir wach sind oder schlafen. Es ist der Ort, an dem unsere Ideen entstehen, der uns Freude ebenso wie Angst empfinden lässt. Es vollbringt jede Sekunde kognitive Höchstleistungen und lässt uns dabei alltägliche Aufgaben ebenso erledigen wie komplexe Zusammenhänge verstehen. Doch wie funktioniert das Gehirn eigentlich?

Üblicherweise sind empirische Untersuchungen basierend auf der Analyse von Gewebeproben, bildgebenden Verfahren wie fMRT, Messungen mittels EEG oder kognitiven Experimenten die Basis moderner Neurowissenschaften. Dank der immer einfacheren und günstigeren Verfügbarkeit hoher Rechenleistung hat sich in den letzten Jahren eine neue Perspektive für die Gehirnforschung ergeben: Statt Experimenten kommen vermehrt Computersimulationen zum Einsatz, anhand derer Dynamik und Logik neuronaler Schaltkreise analysiert werden können.

Das resultierende Verhalten bei Interaktion mit der Umwelt wird in der Neurorobotik untersucht, indem die simulierten neuronalen Netze als „künstliche Gehirne“ zur Steuerung von Robotern verwendet werden.

 

Invited Speakers:

Priv.-Doz. Dr. Stefan Artmann
Nationale Akademie der Wissenschaften Leopoldina
Friedrich-Schiller-Universität Jena

Prof. Dr. Godehard Brüntrup SJ
Hochschule für Philosophie München

Priv.-Doz. Dr. Agnieszka Wykowska
LMU München

 

Schedule:


October 8, 2015 (1st day)

13:00 – 13:30 Welcome by the organizers
13:30 – 14:30 Talk by Florian Röhrbein:

Neurorobotics & the Human Brain Project

14:30 – 15:30 Talk by Godehard Brüntrup:

Was hieße es für einen Roboter, denken zu
können?

15:30 – 16:00 Coffee break & discussion time
16:00 – 17:00 Talk by Florian Röhrbein & Florian Walter:

Introduction to Neuroscience

17:00 – 18:00 Discussion
18:00 – 19:00 Dinner

October 9, 2015 (2nd day)

09:00 – 10:30 Talk by Florian Walter:

Neurorobotics – State of the Art

10:30 – 11:30 Talk by Stefan Artmann:

Künstliches Bewusstsein – ein sinnvolles Ziel der
Künstlichen Intelligenz?

11:30 – 12:30 Lunch
12:30 – 13:30 Talk by Agnieszka Wykowska:

Linking social cognitive neuroscience with
robotics for better social robots

13:30 – 14:30 World Cafe – Discussion
14:30 – 15:00 Coffee break
15:00 – 16:00 Webinar:

Brain Computer interfaces and neuroprosthetics

16:00 – 17:00 Farewell

 

You can dowload the complete schedule and information about all speaker as PDF: Download

Advances in Biologically Inspired Brain-Like Cognition and Control for Learning Robots

Date: 28.09.2015
Venue: Hamburg

!!For interest!!

A summary of the workshop can be found on robohub:

http://robohub.org/towards-building-brain-like-robotic-cognition-and-control/

robohub.png

 

Workshop for:

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems
September 28 – October 03, 2015, Hamburg, Germany

The workshop will take place on Friday, October 2, 8-12 am.

To check the proceedings for our workshop, just click on the link.

csm_IROS_logo_01_e40f52f041

Organizers:

Florian Walter (TUM)
florian.walter@tum.de

Florian Röhrbein (TUM)
florian.roehrbein@in.tum.de

Stefan Ulbrich (FZI)
stefan.ulbrich@fzi.de

Rüdiger Dillmann (KIT)
ruediger.dillmann@kit.edu

 

Objectives:

Even today’s most advanced robots perform poorly in executing simple everyday tasks carried out routinely by humans and animals. This fact has very early motivated researchers to adopt neurobiological principles of cognition and control in robotics, that resulted in numerous approaches based on artificial neural networks and machine learning. However, many originally proposed methods employ neural networks solely for the purpose of approximating and replicating standard control architectures. At the same time, research focusing more on biological plausibility severely suffered from limitations on size and accuracy of the neural simulations imposed by hardware constraints.

In the recent years, advanced insights and the increasing availability of cheap processing power have brought new momentum to the field which has evolved into two tracks of research with different goals and methods. In the new and emerging field of neurorobotics, the focus is on a close correspondence to experimental findings from neurosciences. Detailed simulations of spiking neural networks and the use of biologically plausible neural learning rules are therefore more important than mathematical tractability or implementation efficiency and enable a seamless exchange of results between both disciplines. In contrast, new approaches extending the theory of classical artificial neural networks mostly rely on simpler neuron models but integrate them at much larger scales or embed them in novel network architectures.

This workshop seeks to provide a platform to present and discuss advances in biologically inspired brain-like cognition and control for robotic applications based on both biologically plausible and artificial neural networks. By bringing together experts from both fields, we intend to foster a fruitful exchange between the different communities. Furthermore, the global scope of the workshop furthermore makes participation also equally attractive for researchers new to the field. Interactive demonstrations of tools and implementations will help to get all attendants actively involved. A dedicated poster session additionally offers enough room for individual discussion.

 

Topics of interest:

  • Neurorobotics
  • Bio-inspired learning
  • Spiking neural networks for robotic applications
  • Self-organization
  • Embodiment
  • Applications of neuromorphic hardware designs in robotics
  • Reservoir computing
  • Deep learning

This workshop is supported by Wataru Takano (University of Tokyo, Japan), Co-chair of the IEEE RAS Technical Committee on Robot Learning and by Kin Huat Low (Nanyang Technological University, Singapore), Chair of the Technical Committee on Biorobotics

 

Invited Speakers:

  1. Auke Jan Ijspeert (confirmed)
    Biorobotics Laboratory, École Polytechnique Fédérale de Lausanne, Switzerland
  2. Herbert Jäger (confirmed)
    Jacobs University, Germany
  3. Joni Dambre (confirmed)
    Reservoir Computing Lab, Ghent University, Belgium
  4. Manfred Hild (confirmed)
    Neurorobotics Research Laboratory, Beuth Hochschule für Technik Berlin,Germany
  5. Jason Yosinski (confirmed)
    Cornell Creative Machines Lab, Cornell University, USA

 

Tentative schedule:

      8:30   –     8:45 Welcome
      8:45   –     9:15 Invited Talk 1:
Auke Jan Ijspeert
      9:15   –     9:45 Invited Talk 2:
Manfred Hild
      9:45   –   10:15 Invited Talk 3:
Joni Dambre
    10:15   –   10:40 Live Demo Session: The HBP Neurorobotics Platform
    10:40   –   11:00 Coffee Break
    11:30   –   12:00 Invited Talk 4:
Herbert Jäger
    12:00   –   12:30 Invited Talk 5:
Jason Yosinski

 

Talks

Learning about Animal Locomotion Control from Robots, Auke Ijspeert

The ability to efficiently move in complex environments is a fundamental property both for animals and for robots, and the problem of locomotion and movement control is an area in which neuroscience and robotics can fruitfully interact.

Animal locomotion control is in a large part based on spinal cord circuits that combine reflex loops and central pattern generators (CPGs), i.e. neural networks capable of producing complex rhythmic or discrete patterns while being activated and modulated by relatively simple control signals. These networks are located in the spinal cord for vertebrate animals and interact with the musculoskeletal system to provide “motor primitives” for higher parts of the brain, i.e. building blocks of motor control that can be activated and combined to generate rich movements.

In this talk, I will present how we model the spinal cord circuits of lower vertebrates (lamprey and salamander) using systems of coupled oscillators, and how we test these models on board of amphibious robots. The models and robots were instrumental in testing some novel hypotheses concerning the mechanisms of gait transition, sensory feedback integration, and generation of rich motor skills in vertebrate animals.

I will also discuss how the models can be extended to control biped locomotion, and how they can help deciphering the respective roles of pattern generation, reflex loops, and descending modulation in human locomotion.

 

Self-Exploration of Autonomous Robots Using Attractor-Based Behavior Control, Manfred Hild

An autonomous robot which is equipped with sensorimotor loops and situated within a specific environment can be regarded as a dynamical system. In the language of dynamical systems theory, behavioral body postures and repetitive body motions then correspond with fixed points and quasiperiodic orbits. Both of which can either be naturally stable, i.e., attractors of the situated physical body, or be stabilized by the whole system including the sensorimotor loops.

As is well-known, even most simple two-neuron networks may already exhibit many co-existing attractors, which, if properly chosen, may nicely go along with the overt behavior of an autonomous robot. Standing and walking is one example, obstacle avoidance another one. The question arises, how larger neural networks can be found (preferable by the robot itself), that explore behavioral options, starting from scratch and getting increasingly rich over time.

Attractor-Based Behavior Control (ABC) follows the afore-mentioned path and confidently finds attractors which correspond to energy-efficient behavioral body postures, either fully alone or in gently guiding physical human-machine interaction. The latter helps protecting the robot from harming itself as it would easily happen if using, e.g., motor-babbling or homeokinetic learning rules. In addition, ABC learning does not only find behavioral attractors, but also the corresponding attractor-connecting heteroclinic orbits which can be utilized to generate stable motion trajectories.

After briefly revisiting the necessary concepts, I will introduce ABC-Learning and demonstrate how it enables an autonomous robot to self-explore its behavioral capabilities from scratch and without any given body model.

Practical approaches to exploiting body dynamics in robot motor control, Joni Dambre

Motor control systems in the brain of humans and mammals are hierarchically organised, with each level controlling increasingly complex motor actions. Each level is controlled by the higher levels and also receives sensory and/or proprioceptive feedback. Through learning, this hierarchical structure adapts to its body, its sensors and the way these interact with the environment.

An even more integrated view is taken in morphological or embodied computation. On the one hand, there is both biological and mechanical (robotics) evidence that a properly chosen body morphology can drastically facilitate control when the body dynamics naturally generate low level motion primitives. On the other hand, several papers have used robot bodies as reservoirs in a reservoir computing setup. In some cases, reservoir computing was used as an easy way to obtain robust linear feedback controllers for locomotion.

In other cases, the body dynamics of soft robots were shown to perform general computations in response to some input stimulation. In general, very specific highly compliant bodies were used. At Ghent University’s Reservoir Lab, we have previously used reservoir computing to generate locomotion on quite different robot platforms: the highly compliant tensegrity robot Recter and the far less compliant quadruped robot Oncilla and a new low cost modular quadruped puppy robot. In all cases, we succeeded in generating stable gaits. However, not surprisingly, not all robot bodies are equally suitable to help generating their own motor actuations. As a result, the reservoir computing principle alone was not always sufficient.

We present an overview of our experience with these different robot platforms and give practical guidelines for applying physical reservoir computing to new robots. We finally discuss some perspectives on a more systematic evaluation between body morphology, compliance and the complexity of generating stable gaits for locomotion.

Generating and Modulating Complex Motion Patterns with Recurrent Neural Networks and Conceptors, Herbert Jaeger

In biological brains “higher” cognitive control modules regulate “lower” brain layers in many ways. Examples for such top-down processing pathways include triggering motion commands (“reach for that cup”), modulating ongoing lower-level motor pattern generation (“wider steps, slooow down!”), setting attentional focus (“look closer… there!”), or predicting the next sensory impressions (“oops – that will hit me”). Not much is known about computational mechanisms which would implement such top-down governance functions on the neural level. As a consequence, in machine learning systems which are based on artificial neural networks, top-down regulation is rarely implemented.

Specifically, today’s top-performing pattern recognition systems (“deep learning” architectures) do not exploit top-down regulation pathways. This talk gives an introduction to a novel neural control mechanism which addresses such top-down governance mechanisms in modular, neural learning architectures. This computational principle, called conceptors, allows higher neural modules to control lower ones in a dynamical, online-adaptive fashion. The conceptor mechanism lends itself to numerous purposes:

  • A single neural network can learn a large number of different dynamical patterns (e.g. words, or motions).
    • After some patterns have been learnt by a neural network, it can re-generate not only the learnt “prototypes” but a large collection of morphed, combined, or abstracted patterns.
    • Patterns learnt by a neural network can become logically combined with operations AND, OR, NOT subject to rules of Boolean logic. This reveals a fundamental link between the worlds of “subsymbolic” neural dynamics and of “symbolic” cognitive operations.
    • This intimate connection between the worlds of neural dynamics and logical-symbolic operations yields novel algorithms and architectures for lifelong learning, signal filtering, attending to particular signal sources (“party talk” effect), and more.

Expressed in a nutshell, conceptors enable “top-down logico-conceptual control” of the nonlinear, pattern-generating dynamics of recurrent neural networks.

Training and Understanding Deep Neural Networks for Robotics, Design, and Perception, Jason Yosinski

Artificial Neural Networks (ANNs) form a powerful class of models with both theoretical and practical advantages. Networks with more than one hidden layer (deep neural networks) compute multiple functions on later layers that share the use of intermediate results computed on earlier layers. This compositional, hierarchical structure provides a strong bias, or regularization, toward solutions that seem to work well on a large variety of real-world problems.

In this talk we will examine this bias in action via several vignettes. First we will look at a method for using ANNs to learn fast gaits for walking robots. Second, we will see how the same method can be applied to design three dimensional solid objects. Finally we will discuss a few simple experiments that shed light on the inner workings of neural nets trained to classify images. The studies shed light on the computation performed by each layer of a network and by the network as a whole. The experiments taken together reveal some surprising behaviors of large networks and lead to a greater understanding and intuition for the computation performed by deep neural nets.

The Neurorobotics Platform of the Human Brain Project, Stefan Ulbrich

The Neurorobotics Platform (NRP) is a web-based simulation environment for neuroscientists for performing neurorobotic experiments. It is developed in the sub-project 10 “Neurorobotics” of the Future and Emerging Technologies (FET) Flagship project “The Human Brain Project” funded by the European Commission. The software grants neuroscientists painless access to sophisticated brain, robot and physical simulators and provides the necessary tools for designing brain-body interfaces, virtual world and robot modeling as well as the definition of complex experiments. The NRP is still under development and this talk presents its current state and capabilities as well as an outlook on future development.

 

Posters

1. Neurocognitive Architecture for Autonomous Task Recognition, Learning, and Execution (NARLE)

Yulia Sandamirskaya (1), Mikhail Burtsev (2)
(1) Institute of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland
(2) NBICS Centre, NRC “Kurchatov Institute”, Moscow, Russian Federation
ysandamirskaya@ini.uzh.ch

Humans and higher animals are able to solve new problems and reuse the acquired solutions later in their behaviour. This capacity of the biological neuronal systems for constant adaptation enables biological agents to refine their skills and expand their behavioural repertoire. Understanding how neuronal dynamics may be organised to enable learning new skills will enable us to build cognitive robots that are adaptive and can autonomously acquire new behaviors. Recently, we have introduced a neurocognitive architecture that addresses the problem of learning and execution of hierarchical behaviors and complex skills.

The proposed architecture uses Dynamic Neural Fields (DNFs) to implement low-level motor and perceptual behaviours and a Functional System Network (FSN) to tie these behaviors in goal-directed sequences. The DNFs enable a continuous, dynamical representation of perceptual features and motor parameters, which may be coupled to the robot’s sensors and effectors. Attractor states and instabilities of the DNFs account for segregation of discrete cognitive states and mark behaviorally relevant events in the continuous flow of the sensorimotor dynamics. The FSN, in its turn, comprises dynamical elements that can be arranged in a multilayered network by a learning process, in which new layers and elementary behaviors are added on demand.

Combination of the DNF and FSN frameworks in a neurocognitive architecture NARLE enables pervasive learning and adaptation both on the level of individual behaviors and goal-directed sequence, leading to more adaptive intelligent robotic systems, capable to learn new tasks and extend their behavioral repertoire in stochastic real-world environments. In our robotic scenario, the systems for object and scene representation, action parsing, and sequence learning are detailed and their interplay in a table-top assembly task is described. We discuss the potential of this new biologically-inspired cognitive architecture in the fields of modelling human cognition and autonomous robotics.

2. Learning Techniques for Neurorobotics – A Survey on the Role of the Factor Time

Florian Walter, Florian Röhrbein, Alois Knoll
Chair for Robotics and Embedded Systems, Technische Universität München, Germany
florian.walter@tum.de

Neurorobotics enables the interaction of simulated biological neural networks with both virtual and real environments in closed perception-action loops. Controlling robotic actuators, processing sensor readings and implementing goal-directed behavior requires the adjustment of synaptic weights by means of learning. The temporal dynamics of the detailed neural models employed in neurorobotics enable the use of learning techniques which incorporate a notion of time. This poster provides an overview of concepts and methods from this field with a special focus on prospective applications in neurorobotics.

3. Cognitive Walking: Recruitment of an Internal Body Model

Malte Schilling, Holk Cruse
Center of Excellence Cognitive Interaction Technology, University of Bielefeld, Germany
mschilli@techfak.uni-bielefeld.de

The overall goal of our approach is to understand general cognitive mechanism and to implement those in a functional minimal cognitive system. We are starting from a biological inspired hexapod walking control system and we extended this system towards a minimal cognitive system. In our understanding Cognition is understood following the notion of McFarland and Bösser (1993) as the ability to plan ahead by means of an internal simulation (Hesslow, 2002) relying on internal representation (Steels, 2003; Glenberg, 1997) which are grounded in embodied experiences (Gallese & Lakoff 2005). The extension of our system leads towards a control system for the six-legged walking robot Hector which allows the robot to deal with novel situation and to plan its behavior in advance.

Crucial to this approach is, on the one hand, the grounding of internal representation in behavior and, on the other hand, the flexible reuse of such embodied internal models in new contexts which is realized as a form of internal simulation. On the poster, we will present, first, the underlying behavior-based control system from which adaptive and well-cordinated walking behavior emerges. Second, how functional internal models are grounded in lower level behavior. As a first internal representation an internal model of the body will be introduced realized as a simple recurrent neural network. Third, we will show how this functional internal model of the body can be exploited in internal simulation for planning ahead exploiting the predictive forward function of the model.

4. Real-time Cerebellar Control of a Compliant Robotic Arm

Christoph Richter (1), Sören Jentzsch (2), Florian Röhrbein (3), Patrick van der Smagt (3), Jörg Conradt (1)
(1) Electrical and Computer Engineering, Technische Universität München, Germany
(2) fortiss GmbH, München, Germany
(3) Chair for Robotics and Embedded Systems, Technische Universität München, Germany
c.richter@tum.de

Flexible and compliant real-time control of artificial limbs is a challenging endeavor for conventional control algorithms. Conversely, the neuro-control of biological limbs is usually highly stable despite the apparent complex nonlinearities and flexibilities. Part of this is caused by cerebellar fast learning of motor actions embedded in a complex sensory feedback system.

In an attempt to exploit this flexibility in a real-time robotic setting, we apply cerebellar control mechanisms to operate a compliant, anthropomimetic robotic arm built using the Myorobotics framework. The spiking neural network we use is simulated in real-time on a SpiNNaker computer. A custom interface translates between SpiNNaker’s digital synaptic spikes and the robot’s sensors and actuators on a CAN bus. We demonstrate initial results of the implementation with a one-degree-of-freedom robotic joint as proof of principle. Here, we benefit from the modular and extensible design of both the Myorobotics framework and the SpiNNaker platform.

Contact:

Florian Walter
Institut für Informatik VI
Technische Universität München
Boltzmannstr. 3
85748 Garching bei München
Germany