Register now After registration you will be able to apply for this opportunity online.
Reinforcement learning to reject large disturbances for a robotic arm
Quasi-direct drive robot arms experience high deflection in the presence of large end effector forces. This leads to stability issues when these forces change rapidly, such as when dropping a heavy object. Existing works use reinforcement learning to achieve end effector tracking[1] as well as force control[2]. In this project, you will extend upon this by developing a controller capable of tracking end effector poses in the presence of sudden, large changes in end effector disturbance. You will first deploy your controller on a standalone robotic arm and then work towards deployment on our ANYmal-based bimanual mobile manipulator.
[1] Martín-Martín et al., Variable Impedance Control in End-Effector Space:
An Action Space for Reinforcement Learning in Contact-Rich Tasks (IROS 2019)
[2] Portela et al., Learning Force Control for Legged Manipulation (ICRA 2024)
Keywords: reinforcement learning, robot arm, mobile manipulation, force disturbance
Not specified
- Literature research on robotic end effector tracking and disturbance rejection
- Develop a RL-based controller to reject sudden disturbances
- Deploy and test the developed controller on hardware
- (Optional) Extend the controller to a mobile manipulator on a legged base
- Literature research on robotic end effector tracking and disturbance rejection - Develop a RL-based controller to reject sudden disturbances - Deploy and test the developed controller on hardware - (Optional) Extend the controller to a mobile manipulator on a legged base
- Good knowledge in C++ and Python
- Experience/Knowledge in Reinforcement Learning
- Experience with control of robotic arms
- Good knowledge in C++ and Python - Experience/Knowledge in Reinforcement Learning - Experience with control of robotic arms
Send your CV, Transcript and Motivation Letter to olivefi@ethz.ch and mittalma@ethz.ch
Send your CV, Transcript and Motivation Letter to olivefi@ethz.ch and mittalma@ethz.ch
Reinforcement learning to reject large disturbances for a robotic arm.docx.pdf
