CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller

Yuxiang Yang, Guanya Shi, Xiangyun Meng, Wenhao Yu, Tingnan Zhang, Jie Tan, Byron Boots
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2791-2806, 2023.

Abstract

We present CAJun, a novel hierarchical learning and control framework that enables legged robots to jump continuously with adaptive jumping distances. CAJun consists of a high-level centroidal policy and a low-level leg controller. In particular, we use reinforcement learning (RL) to train the centroidal policy, which specifies the gait timing, base velocity, and swing foot position for the leg controller. The leg controller optimizes motor commands for the swing and stance legs according to the gait timing to track the swing foot target and base velocity commands. Additionally, we reformulate the stance leg optimizer in the leg controller to speed up policy training by an order of magnitude. Our system combines the versatility of learning with the robustness of optimal control. We show that after 20 minutes of training on a single GPU, CAJun can achieve continuous, long jumps with adaptive distances on a Go1 robot with small sim-to-real gaps. Moreover, the robot can jump across gaps with a maximum width of 70cm, which is over $40%$ wider than existing methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-yang23b, title = {CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller}, author = {Yang, Yuxiang and Shi, Guanya and Meng, Xiangyun and Yu, Wenhao and Zhang, Tingnan and Tan, Jie and Boots, Byron}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2791--2806}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/yang23b/yang23b.pdf}, url = {https://proceedings.mlr.press/v229/yang23b.html}, abstract = {We present CAJun, a novel hierarchical learning and control framework that enables legged robots to jump continuously with adaptive jumping distances. CAJun consists of a high-level centroidal policy and a low-level leg controller. In particular, we use reinforcement learning (RL) to train the centroidal policy, which specifies the gait timing, base velocity, and swing foot position for the leg controller. The leg controller optimizes motor commands for the swing and stance legs according to the gait timing to track the swing foot target and base velocity commands. Additionally, we reformulate the stance leg optimizer in the leg controller to speed up policy training by an order of magnitude. Our system combines the versatility of learning with the robustness of optimal control. We show that after 20 minutes of training on a single GPU, CAJun can achieve continuous, long jumps with adaptive distances on a Go1 robot with small sim-to-real gaps. Moreover, the robot can jump across gaps with a maximum width of 70cm, which is over $40%$ wider than existing methods.} }
Endnote
%0 Conference Paper %T CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller %A Yuxiang Yang %A Guanya Shi %A Xiangyun Meng %A Wenhao Yu %A Tingnan Zhang %A Jie Tan %A Byron Boots %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-yang23b %I PMLR %P 2791--2806 %U https://proceedings.mlr.press/v229/yang23b.html %V 229 %X We present CAJun, a novel hierarchical learning and control framework that enables legged robots to jump continuously with adaptive jumping distances. CAJun consists of a high-level centroidal policy and a low-level leg controller. In particular, we use reinforcement learning (RL) to train the centroidal policy, which specifies the gait timing, base velocity, and swing foot position for the leg controller. The leg controller optimizes motor commands for the swing and stance legs according to the gait timing to track the swing foot target and base velocity commands. Additionally, we reformulate the stance leg optimizer in the leg controller to speed up policy training by an order of magnitude. Our system combines the versatility of learning with the robustness of optimal control. We show that after 20 minutes of training on a single GPU, CAJun can achieve continuous, long jumps with adaptive distances on a Go1 robot with small sim-to-real gaps. Moreover, the robot can jump across gaps with a maximum width of 70cm, which is over $40%$ wider than existing methods.
APA
Yang, Y., Shi, G., Meng, X., Yu, W., Zhang, T., Tan, J. & Boots, B.. (2023). CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2791-2806 Available from https://proceedings.mlr.press/v229/yang23b.html.

Related Material