Neurorobotics Platform - EBRAINS

The Neurorobotics Platform, NRP, is an integrative simulation framework that enables in silico experimentation and embodiment of brain models inside virtual agents interacting with realistic simulated environments. Conceived by the HBP Partners as an open access, open source tool, the NRP can be used by users with different scientific background and level of expertise.

Thanks to its direct connection to both Neuroscience research in the Human Brain Project and the EBRAINS HPC infrastructure, the NRP is the best available platform for scientific exploration and development of neuromorphic computing applications.

In silico neuroscience: Improve and refine novel models of brain functions and architecture
Co-design of robotic body and controller: Design tools for advanced robotics
Cognitive robotics: Robots with enhanced decision-making capabilities and contextual awareness, for use in autonomous exploration (deep sea, space), search-and-rescue in disaster areas, and more
Testing and verification of robotic behaviour: Implement testing, even under safety-critical situations

Drawing upon the potential of both neuroscience and Artificial Intelligence in robotics, the NRP is the EBRAINS service that allows users to observe, analyse and test the emergence of behavioural patterns in virtual agents controlled by state-of-the-art models of brain architecture and functions. The result is an unprecedented approach to simulation, in which theoretical brain models can be checked against data-driven models thanks to simulations that take into account the dynamics of both the environment and the agent itself. This approach is essential to develop novel robotic control technologies that are robust, adaptable and comparable to biological systems.

The NRP is the only open source platform with concrete ties to neuroscience and the only one aiming to run large-scale simulations of spiking neural networks.

Access the NRP

Download our brochure

Read our Publications

Contact us

Simulation is used in neuroscience as a tool to improve and refine brain models. By enabling the creation of closed action-perception-cognition loops in embodied settings, the NRP allows neuroscientists to observe and analyse emergent behavioural patterns in virtual agents controlled by specific models of brain architecture and functions. This provides them with the extraordinary opportunity to test and refine these models iteratively, without the many approximations entailed by simulating the brain decoupled from the body.

Neuroscientists are using the NRP for:

Replicating a sensory-motor experiment in simulation
Iterative testing and refining of functional brain models
Implementing learning paradigms in large-scale parallel simulations

Read the Publication

With the NRP, testing procedures that can otherwise be costly or difficult to implement on a physical setup - like testing of safety-critical situations or scenarios that could result in damage to the robot - can be performed without incurring any risk.

Inspired by biological architectures and with the possibility to reproduce any desired environment or experimental condition in the virtual space of the NRP, roboticists using our platform can test and develop new robotic controllers that will bring us the next generation of safe and adaptable robotic systems with enhanced cognitive abilities, such as contextual awareness and decision-making.

The NRP Docker technology makes it ideal for distributed / parallel learning and optimisation.

Roboticists are using the NRP for:

Generating synthetic data for AI research
In silico evaluation of the functional performance of control architectures
Implementing learning / optimisation frameworks in embodied simulation

Examples of NRP experiments

Join us

A service cannot improve, evolve or fix what is not working without open communication with its users. For this reason, besides the dedicated EBRAINS High Level Support Team which provides you with technical support, we are also here to hear your feedback, discuss suggestions and develop ideas together on how we can make the NRP the most reliable and innovative tool for your needs.

Join our Neurorobotics Forum or drop us an e-mail at neurorobotics@ebrains.eu for general queries about the project, our research goals, or media enquiries and we will do our best to address your request in the shortest time possible.

Amunts, K., Knoll, A.C., Lippert, T., Pennartz, C.M.A., Ryvlin, P., Destexhe, A., Jirsa, V.K., D'Angelo, E., Bjaalie, J.G. (2019) The Human Brain Project—Synergy between neuroscience, computing, informatics, and brain-inspired technologies. PLoS Biol. 17(7): e3000344. https://doi.org/10.1371/journal.pbio.3000344

Knoll, A., Röhrbein, F., Kuhn, A., Akl, M., Sharma, K. (2017). Neurorobotics: From computational neuroscience to intelligent robots and back. Informatik-Spektrum. 40, 161-164. https://doi.org/10.1007/s00287-017-1031-8

Falotico E., et al. (2017) Connecting Artificial Brains to Robots in a Comprehensive Simulation Framework: The Neurorobotics Platform. Front. Neurorobot. 11:2. https://doi.org/10.3389/fnbot.2017.00002

Vasquez-Tieck J.C., et al. (2017) Towards Grasping with Spiking Neural Networks for Anthropomorphic Robot Hands. In: Lintas A., Rovetta S., Verschure P., Villa A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2017. ICANN 2017. Lecture Notes in Computer Science, vol. 10613. Springer, Cham. https://doi.org/10.1007/978-3-319-68600-4_6

Knoll, A., & Gewaltig, M.O. (2016) Neurorobotics: A Strategic Pillar of the Human Brain Project. Science Robotics.

2021

All versions of version 3 of the NRP (v3.0.5, 3.1 and 3.2 – the latter available in the second half of September) will be available to our users as an online tool for research, teaching, and community building. This is made possible by a new CI/CD process that provides EBRAINS with the capacity to offer several versions of the NRP concurrently at all times for our users to work with.

A major revamp of the documentation for the NRP 3.x will be completed and made available in the fall.

Our developers will prepare the future and create a fundamentally new evolution of the NRP: this evolution will be fully modular in terms of the simulators that it can orchestrate, and will rely on industry-standard frameworks (e.g. REACT for the frontend as a replacement for AngularJS) to make it future-proof and ensure its sustainability.

2022

By mid-2022, this new version of the NRP will be made available to the public. This release will take place after multiple demonstrators have been shared internally inside HBP, to gather user feedback and co-design meaningful experiments with the HBP scientists.

In the second half of 2022, two new EBRAINS services will also come into production and will be integrated to all infrastructure-specific EBRAINS facilities available at that time (e.g. user resource management, SWIFT secure storage, etc.). The first such service will be a Neurorobotics Public Library that will extend the capabilities of the current online NRP to share complete experiments. The second service will be browser-accessible large-scale embodied NEST simulations, demonstrating interactive computing features on the Piz Daint HPC cluster. This service will be the first and only service supporting embodied closed-loop research on large-scale spiking neural networks, with full brain models available off-the-shelf for users to start working with.

2023

All NRP-based services offered by EBRAINS will be consolidated, and all operation-critical processes transferred to EBRAINS (e.g. control of code repositories, CI/CD process, etc.).

Access all EBRAINS services