Connecting Artificial Brains to Robots in a Comprehensive Simulation Framework: The Neurorobotics Platform

Combined efforts in the fields of neuroscience, computer science, and biology allowed to design biologically realistic models of the brain based on spiking neural networks. For a proper validation of these models, an embodiment in a dynamic and rich sensory environment, where the model is exposed to a realistic sensory-motor task, is needed. Due to the complexity of these brain models that, at the current stage, cannot deal with real-time constraints, it is not possible to embed them into a real-world task. Rather, the embodiment has to be simulated as well. While adequate tools exist to simulate either complex neural networks or robots and their environments, there is so far no tool that allows to easily establish a communication between brain and body models. The Neurorobotics Platform is a new web-based environment that aims to fill this gap by offering scientists and technology developers a software infrastructure allowing them to connect brain models to detailed simulations of robot bodies and environments and to use the resulting neurorobotic systems for in silico experimentation. In order to simplify the workflow and reduce the level of the required programming skills, the platform provides editors for the specification of experimental sequences and conditions, environments, robots, and brain–body connectors. In addition to that, a variety of existing robots and environments are provided. This work presents the architecture of the first release of the Neurorobotics Platform developed in subproject 10 “Neurorobotics” of the Human Brain Project (HBP).1 At the current state, the Neurorobotics Platform allows researchers to design and run basic experiments in neurorobotics using simulated robots and simulated environments linked to simplified versions of brain models. We illustrate the capabilities of the platform with three example experiments: a Braitenberg task implemented on a mobile robot, a sensory-motor learning task based on a robotic controller, and a visual tracking embedding a retina model on the iCub humanoid robot. These use-cases allow to assess the applicability of the Neurorobotics Platform for robotic tasks as well as in neuroscientific experiments.

[1]  Pierre Yger,et al.  PyNN: A Common Interface for Neuronal Network Simulators , 2008, Front. Neuroinform..

[2]  J. M. Singer,et al.  IEEE Recommended Practice for Software Requirements SpeciÞcations , 1993 .

[3]  Andrew Howard,et al.  Design and use paradigms for Gazebo, an open-source multi-robot simulator , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[4]  Eduardo Ros,et al.  Real-time computing platform for spiking neurons (RT-spike) , 2006, IEEE Trans. Neural Networks.

[5]  Johannes Schemmel,et al.  The high-conductance state enables neural sampling in networks of LIF neurons , 2015, BMC Neuroscience.

[6]  Charles J. Wilson,et al.  Chaotic decorrelation of Globus Pallidus by periodic forcing: a possible mechanism for the therapeutic effects of deep brain stimulation , 2011, BMC Neuroscience.

[7]  Monica Reggiani,et al.  Simulation, Modeling, and Programming for Autonomous Robots , 2010, Lecture Notes in Computer Science.

[8]  Rob Knight,et al.  Two Simulation Tools for Biologically Inspired Virtual Robotics , 2006 .

[9]  Ying Zhu,et al.  AnimatLab: A 3D graphics environment for neuromechanical simulations , 2010, Journal of Neuroscience Methods.

[10]  Luis A. Plana,et al.  SpiNNaker: Mapping neural networks onto a massively-parallel chip multiprocessor , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[11]  Stefan Ulbrich,et al.  A Framework for Coupled Simulations of Robots and Spiking Neuronal Networks , 2016, J. Intell. Robotic Syst..

[12]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[13]  Ann C. Benefiel,et al.  Effects of Experience and Environment on the Developing and Mature Brain: Implications for Laboratory Animal Housing. , 1998, ILAR journal.

[14]  Mikael Djurfeldt,et al.  Closed Loop Interactions between Spiking Neural Network and Robotic Simulators Based on MUSIC and ROS , 2016, Front. Neuroinform..

[15]  Stefan Ulbrich,et al.  OpenGRASP: A Toolkit for Robot Grasping Simulation , 2010, SIMPAR.

[16]  Stefan Ulbrich,et al.  Kinematic Bézier Maps , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[17]  Jonathan Bohren,et al.  The SMACH High-Level Executive [ROS News] , 2010 .

[18]  Romain Brette,et al.  Brian: a simulator for spiking neural networks in Python , 2008, BMC Neuroscience.

[19]  W. Greenough,et al.  Stability of synaptic plasticity in the adult rat visual cortex induced by complex environment exposure , 2004, Brain Research.

[20]  Giorgio Metta,et al.  YARP: Yet Another Robot Platform , 2006 .

[21]  Stefan Ulbrich,et al.  Master Motor Map (MMM) — Framework and toolkit for capturing, representing, and reproducing human motion on humanoid robots , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[22]  Rüdiger Dillmann,et al.  LAURON V: A versatile six-legged walking robot with advanced maneuverability , 2014, 2014 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[23]  Alois Knoll,et al.  Retina Color-Opponency Based Pursuit Implemented Through Spiking Neural Networks in the Neurorobotics Platform , 2016, Living Machines.

[24]  W. J. Heitler,et al.  Control of tumbling during the locust jump , 2010, Journal of Experimental Biology.

[25]  Thomas Voegtlin CLONES : a closed-loop simulation framework for body, muscles and neurons , 2011, BMC Neuroscience.

[26]  Stephane Cotin,et al.  EP4A: Software and Computer Based Simulator Research: Development and Outlook SOFA—An Open Source Framework for Medical Simulation , 2007, MMVR.

[27]  Rüdiger Dillmann,et al.  A visual tracking model implemented on the iCub robot as a use case for a novel neurorobotic toolkit integrating brain and physics simulation , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[28]  Tomoki Fukai,et al.  Spiking network simulation code for petascale computers , 2014, Front. Neuroinform..

[29]  Andraž Cej,et al.  Agile software development with Scrum , 2010 .

[30]  Stefan Ulbrich,et al.  A Domain-Specific Language (DSL) for Integrating Neuronal Networks in Robot Control , 2015 .

[31]  Steve Cousins,et al.  The SMACH High-Level Executive , 2010 .

[32]  Dylan A. Shell,et al.  Extending Open Dynamics Engine for Robotics Simulation , 2010, SIMPAR.

[33]  Frédéric Alexandre,et al.  VirtualEnaction - A Platform for Systemic Neuroscience Simulation , 2014, NEUROTECHNIX.

[34]  J. Denavit,et al.  A kinematic notation for lower pair mechanisms based on matrices , 1955 .

[35]  Örjan Ekeberg,et al.  Run-Time Interoperability Between Neuronal Network Simulators Based on the MUSIC Framework , 2010, Neuroinformatics.

[36]  D Gamez,et al.  iSpike: a spiking neural interface for the iCub robot , 2012, Bioinspiration & biomimetics.

[37]  V. Braitenberg Vehicles, Experiments in Synthetic Psychology , 1984 .

[38]  Abigail Morrison,et al.  ROS-MUSIC toolchain for spiking neural network simulations in a robotic environment , 2015, BMC Neuroscience.

[39]  Daniel Cattaert,et al.  Neural Circuit Reconfiguration by Social Status , 2012, The Journal of Neuroscience.

[40]  Pablo Martínez-Cañada,et al.  First Stage of a Human Visual System Simulator: The Retina , 2015, CCIW.

[41]  D. Dacey,et al.  Colour coding in the primate retina: diverse cell types and cone-specific circuitry , 2003, Current Opinion in Neurobiology.

[42]  Marc-Oliver Gewaltig,et al.  NEST (NEural Simulation Tool) , 2007, Scholarpedia.

[43]  Ralph Johnson,et al.  Design patterns: elements of reuseable object-oriented software , 1994 .

[44]  Pablo Martínez-Cañada,et al.  A Computational Framework for Realistic Retina Modeling , 2016, Int. J. Neural Syst..