FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots

Botian Xu, Haoyang Weng, Qingzhou Lu, Yang Gao, Huazhe Xu
Proceedings of The 9th Conference on Robot Learning, PMLR 305:705-720, 2025.

Abstract

Reinforcement learning (RL) has made significant strides in legged robot control, enabling locomotion across diverse terrains and complex loco-manipulation capabilities. However, the commonly used position or velocity tracking-based objectives are agnostic to forces experienced by the robot, leading to stiff and potentially dangerous behaviors and poor control during forceful interactions. To address this limitation, we present Force-Adaptive Control via Impedance Reference Tracking (FACET). Inspired by impedance control, we use RL to train a control policy to imitate a virtual mass-spring-damper system, allowing fine-grained control under external forces by manipulating the virtual spring. In simulation, we demonstrate that our quadruped robot achieves improved robustness to large impulses (up to 200 Ns) and exhibits controllable compliance, achieving an 80% reduction in collision impulse. The policy is deployed to a physical robot, demonstrating both compliant behavior, such as initiation/cessation of movement with finger tip, and the ability to pull payloads up to 10kg. Further extension to a legged loco-manipulator and a humanoid shows the applicability of our method to more complex settings to enable whole-body compliance control.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-xu25c, title = {FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots}, author = {Xu, Botian and Weng, Haoyang and Lu, Qingzhou and Gao, Yang and Xu, Huazhe}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {705--720}, year = {2025}, editor = {Lim, Joseph and Song, Shuran and Park, Hae-Won}, volume = {305}, series = {Proceedings of Machine Learning Research}, month = {27--30 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v305/main/assets/xu25c/xu25c.pdf}, url = {https://proceedings.mlr.press/v305/xu25c.html}, abstract = {Reinforcement learning (RL) has made significant strides in legged robot control, enabling locomotion across diverse terrains and complex loco-manipulation capabilities. However, the commonly used position or velocity tracking-based objectives are agnostic to forces experienced by the robot, leading to stiff and potentially dangerous behaviors and poor control during forceful interactions. To address this limitation, we present Force-Adaptive Control via Impedance Reference Tracking (FACET). Inspired by impedance control, we use RL to train a control policy to imitate a virtual mass-spring-damper system, allowing fine-grained control under external forces by manipulating the virtual spring. In simulation, we demonstrate that our quadruped robot achieves improved robustness to large impulses (up to 200 Ns) and exhibits controllable compliance, achieving an 80% reduction in collision impulse. The policy is deployed to a physical robot, demonstrating both compliant behavior, such as initiation/cessation of movement with finger tip, and the ability to pull payloads up to 10kg. Further extension to a legged loco-manipulator and a humanoid shows the applicability of our method to more complex settings to enable whole-body compliance control.} }
Endnote
%0 Conference Paper %T FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots %A Botian Xu %A Haoyang Weng %A Qingzhou Lu %A Yang Gao %A Huazhe Xu %B Proceedings of The 9th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Joseph Lim %E Shuran Song %E Hae-Won Park %F pmlr-v305-xu25c %I PMLR %P 705--720 %U https://proceedings.mlr.press/v305/xu25c.html %V 305 %X Reinforcement learning (RL) has made significant strides in legged robot control, enabling locomotion across diverse terrains and complex loco-manipulation capabilities. However, the commonly used position or velocity tracking-based objectives are agnostic to forces experienced by the robot, leading to stiff and potentially dangerous behaviors and poor control during forceful interactions. To address this limitation, we present Force-Adaptive Control via Impedance Reference Tracking (FACET). Inspired by impedance control, we use RL to train a control policy to imitate a virtual mass-spring-damper system, allowing fine-grained control under external forces by manipulating the virtual spring. In simulation, we demonstrate that our quadruped robot achieves improved robustness to large impulses (up to 200 Ns) and exhibits controllable compliance, achieving an 80% reduction in collision impulse. The policy is deployed to a physical robot, demonstrating both compliant behavior, such as initiation/cessation of movement with finger tip, and the ability to pull payloads up to 10kg. Further extension to a legged loco-manipulator and a humanoid shows the applicability of our method to more complex settings to enable whole-body compliance control.
APA
Xu, B., Weng, H., Lu, Q., Gao, Y. & Xu, H.. (2025). FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:705-720 Available from https://proceedings.mlr.press/v305/xu25c.html.

Related Material