In the past few months, we have covered plenty of projecting involving ANYmal. The latest video from Robotic Systems Lab shows how this robot can be taught to manipulate a ball with its legs while on its back. As they explain:
We employ a model-free reinforcement learning approach to train a deep policy that enables the robot to balance and manipulate a light-weight ball robustly using its limbs without any contact measurement sensor. The policy is trained in the simulation, in which we randomize many physical properties with additive noise and inject random disturbance force during manipulation, and achieves zero-shot deployment on the real robot without any adjustment.
[HT]