Quadruped Locomotion

Follow this topic Ask about this topic

Quadruped locomotion research develops ways for four-legged robots to walk, run, jump, climb, and move through unfamiliar environments. Common approaches include reinforcement and imitation learning, model-predictive and whole-body control, and perception systems that use cameras, depth, LiDAR, or foot sensors to guide movement. Researchers also study hardware such as compliant feet and active spines, alongside sim-to-real transfer, adaptation to payloads or damage, and safety and energy constraints. Policies are increasingly tested on real robots and challenging terrain, but reliable transfer remains difficult when contact, sensing, or robot dynamics differ from training conditions.

Latest papers

121 papers22 papers in the last four weeks, up 29% on the four weeks before. 0.1% of all new papers.

PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots
Jul 5, 2024Zhiyuan Xiao, Xinyu Zhang, Xiang Zhou +1RL for Legged Locomotion Quadruped Locomotion
School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen 518107, P.R. China.

Jul 5, 2024J/K move · Enter open · S save

PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots

Zhiyuan Xiao, Xinyu Zhang, Xiang Zhou, Qingrui Zhang

School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen 518107, P.R. China.

RL for Legged Locomotion Quadruped Locomotion Learning Using Privileged Information Robust RL Residual Policy Learning

Open paper AskPDF arXiv

Numerous locomotion controllers have been designed based on Reinforcement Learning (RL) to facilitate blind quadrupedal locomotion traversing challenging terrains. Nevertheless, locomotion control is still a challenging task for quadruped robots traversing diverse terrains amidst unforeseen disturbances. Recently, privileged learning has been employed to learn reliable and robust quadrupedal locomotion over various terrains based on a teacher-student architecture. However, its one-encoder structure is not adequate in addressing external force perturbations. The student policy would experience inevitable performance degradation due to the feature embedding discrepancy between the feature encoder of the teacher policy and the one of the student policy. Hence, this paper presents a privileged learning framework with multiple feature encoders and a residual policy network for robust and reliable quadruped locomotion subject to various external perturbations. The multi-encoder structure can decouple latent features from different privileged information, ultimately leading to enhanced performance of the learned policy in terms of robustness, stability, and reliability. The efficiency of the proposed feature encoding module is analyzed in depth using extensive simulation data. The introduction of the residual policy network helps mitigate the performance degradation experienced by the student policy that attempts to clone the behaviors of a teacher policy. The proposed framework is evaluated on a Unitree GO1 robot, showcasing its performance enhancement over the state-of-the-art privileged learning algorithm through extensive experiments conducted on diverse terrains. Ablation studies are conducted to illustrate the efficiency of the residual policy network.