Robot Learns Contact-Rich Assembly Processes with Model-Based Reinforcement Learning

As part of the Research Training Group "Ramp-Up Management", the Cybernetics Lab is researching the use of reinforcement learning for self-learning assembly robots. This demonstrator shows a robot that learns a torque controlled movement strategy for the assembly of contact-rich parts.

Funding: This contribution is funded by the German Research Foundation (DFG) as part of the Research Training Group "Ramp-Up Management" of the RWTH Aachen University.

Видео Robot Learns Contact-Rich Assembly Processes with Model-Based Reinforcement Learning канала Cybernetics Lab IMA & IfU