Video attachment for the contributed paper accepted by 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems.
Title: Run Like a Dog: Learning Based Whole-Body Control Framework for Quadruped Gait Style Transfer
Authors: Fulong Yin, Annan Tang, Liangwei Xu, Yue Cao,
Yu Zheng, Xiangyu Chen, Zhengyou Zhang
Abstract: In this paper, a learning-based whole-body locomotion controller is proposed, which enables quadruped robots to perform running in the style of real animals. We use alow-level controller based on multi-rigid body dynamics to calculate desired torques for each joint, while the high-level neural network policy planning the expected gait and foothold. The policy is trained with reinforcement learning so that the robot can track a variety of trajectories according to the gait patterns recorded from real-world dogs. We transfer the walking and running gait style to quadrupeds in simulation, involving pace, trot, high-speed gallop, and natural transitions. The performance is evaluated by the synchronization rate of the contact state between the policy result and the recorded sequence. In the experiments, the robot runs steadily at a speed of 2 m/s and showcases a notable synchronization rate of about 80%. Without prior knowledge, the policy demonstrates a realistic foothold distribution that covers the central area of the torso, which is prevalent in running animals.
Acknowledgment: This work is supported by Tencent Robotics X.
Posting Permissions
Reply With Quote
Социальные закладки