Skip to main content Skip to main navigation

Project | VeryHuman

Duration:
Learning and Verifying Complex Behaviour of Humanoid Robots

Learning and Verifying Complex Behaviour of Humanoid Robots

Research Topics

Images

The validation of systems based on deep learning for use in safety-critical applications proves to be inherently difficult, since their subsymbolic mode of operation does not provide adequate levels of abstraction for representation and proof of correctness. The VeryHuman project aims to synthesize such levels of abstraction by observing and analysing the behaviour of upright walking of a two-legged humanoid robot. The theory to be developed is the starting point for the definition of an appropriate reward function to optimally control the movements of the humanoid by means of enhanced learning, as well as for verifiable abstraction of the corresponding kinematic models, which can be used to validate the behaviour of the robot more easily.

Partners

Cyber Physical Systems (CPS), DFKI Robotics Innovation Center (RIC), DFKI

Publications about the project

  1. End-to-End Reinforcement Learning for Torque Based Variable Height Hopping

    Raghav Soni; Daniel Harnack; Hannah Isermann; Sotaro Fushimi; Shivesh Kumar; Frank Kirchner

    In: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2023), October 1-5, Detroit, MI, USA, Pages 7531-7538, ISBN 978-1-6654-9190-7, IEEE Robotics and Automation Society, 10/2023.

Sponsors

BMBF - Federal Ministry of Education and Research

01IW20004

BMBF - Federal Ministry of Education and Research