analiza aiqbench
This is a robotics paper, but its contribution is a learning method: a teacher-student reinforcement learning setup with multiple feature encoders and a residual policy that aims to keep the student policy from degrading when external forces disturb a quadruped. The evidence is simulation results plus hardware tests on a Unitree GO1, with ablations isolating the residual network's effect. Readers should weigh the claimed robustness gains against the usual gap between simulated and real-world locomotion.
PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots
arXiv:2407.04224v2 Announce Type: replace Abstract: 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.
Abstract: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.
Robotics (cs.RO)
arXiv:2407.04224 [cs.RO]
(or arXiv:2407.04224v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2407.04224 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 327 cuvinte
Subiecte conexe
Reinforcement Learning Based Multi-Terrain Adaptive Whole-Body Control for a Quadruped Manipulator
arXiv · 19 oct. 2026
Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain
arXiv · 10 iun. 2026
An Analysis of Streaming Deep Reinforcement Learning for Adaptive Continual Learning in Robotics
arXiv · 25 sept. 2026
Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach
arXiv · 23 iul. 2026