Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs
This work demonstrates a novel dexterous manipulation capability for quadrupedal robots, which traditionally excel only at locomotion, opening new possibilities for their application in complex environments.
This paper addresses the lack of dexterous manipulation skills in quadrupedal robots by training a deep policy using model-free reinforcement learning. The robot, ANYmal, learned to balance and manipulate a lightweight ball with its limbs, achieving a maximum rotation speed of 15 deg/s and robust recovery from external disturbances in hardware experiments.
Quadrupedal robots are skillful at locomotion tasks while lacking manipulation skills, not to mention dexterous manipulation abilities. Inspired by the animal behavior and the duality between multi-legged locomotion and multi-fingered manipulation, we showcase a circus ball challenge on a quadrupedal robot, ANYmal. 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. In the hardware experiments, dynamic performance is achieved with a maximum rotation speed of 15 deg/s, and robust recovery is showcased under external poking. To our best knowledge, it is the first work that demonstrates the dexterous dynamic manipulation on a real quadrupedal robot.