FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation

Yuanhang Zhang, Yifu Yuan, Prajwal Gurunath, Ishita Gupta, Shayegan Omidshafiei, Ali-akbar Agha-mohammadi, Marcell Vazquez-Chanlatte, Liam Pedersen, Tairan He, Guanya Shi
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:265-281, 2026.

Abstract

Humanoid loco-manipulation holds transformative potential for daily service and industrial tasks, yet achieving precise, robust whole-body control with 3D end-effector force interaction remains a major challenge. Prior approaches are often limited to lightweight tasks or quadrupedal/wheeled platforms. To overcome these limitations, we propose FALCON, a dual-agent reinforcement-learning- based framework for robust force-adaptive humanoid loco-manipulation. FALCON decomposes whole-body control into two specialized agents: (1) a lower-body agent ensuring stable locomotion under external force disturbances, and (2) an upper-body agent precisely tracking end-effector posi- tions with implicit adaptive force compensation. These two agents are jointly trained in simulation with a force curriculum that progressively escalates the magnitude of external force exerted on the end effector while respecting torque limits. Experiments demonstrate that, compared to the base- lines, FALCON achieves 2$\times$ more accurate upper-body joint tracking, while maintaining robust lo- comotion under force disturbances and achieving faster training convergence. Moreover, FALCON enables policy training without embodiment-specific reward or curriculum tuning. Using the same training setup, we obtain policies that are deployed across multiple humanoids, enabling forceful loco-manipulation tasks such as transporting payloads (0-20N force), cart-pulling (0-100N), and door-opening (0-40N) in the real world.

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-zhang26a, title = {FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation}, author = {Zhang, Yuanhang and Yuan, Yifu and Gurunath, Prajwal and Gupta, Ishita and Omidshafiei, Shayegan and Agha-mohammadi, Ali-akbar and Vazquez-Chanlatte, Marcell and Pedersen, Liam and He, Tairan and Shi, Guanya}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {265--281}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/zhang26a/zhang26a.pdf}, url = {https://proceedings.mlr.press/v331/zhang26a.html}, abstract = {Humanoid loco-manipulation holds transformative potential for daily service and industrial tasks, yet achieving precise, robust whole-body control with 3D end-effector force interaction remains a major challenge. Prior approaches are often limited to lightweight tasks or quadrupedal/wheeled platforms. To overcome these limitations, we propose FALCON, a dual-agent reinforcement-learning- based framework for robust force-adaptive humanoid loco-manipulation. FALCON decomposes whole-body control into two specialized agents: (1) a lower-body agent ensuring stable locomotion under external force disturbances, and (2) an upper-body agent precisely tracking end-effector posi- tions with implicit adaptive force compensation. These two agents are jointly trained in simulation with a force curriculum that progressively escalates the magnitude of external force exerted on the end effector while respecting torque limits. Experiments demonstrate that, compared to the base- lines, FALCON achieves 2$\times$ more accurate upper-body joint tracking, while maintaining robust lo- comotion under force disturbances and achieving faster training convergence. Moreover, FALCON enables policy training without embodiment-specific reward or curriculum tuning. Using the same training setup, we obtain policies that are deployed across multiple humanoids, enabling forceful loco-manipulation tasks such as transporting payloads (0-20N force), cart-pulling (0-100N), and door-opening (0-40N) in the real world.} }
Endnote
%0 Conference Paper %T FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation %A Yuanhang Zhang %A Yifu Yuan %A Prajwal Gurunath %A Ishita Gupta %A Shayegan Omidshafiei %A Ali-akbar Agha-mohammadi %A Marcell Vazquez-Chanlatte %A Liam Pedersen %A Tairan He %A Guanya Shi %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-zhang26a %I PMLR %P 265--281 %U https://proceedings.mlr.press/v331/zhang26a.html %V 331 %X Humanoid loco-manipulation holds transformative potential for daily service and industrial tasks, yet achieving precise, robust whole-body control with 3D end-effector force interaction remains a major challenge. Prior approaches are often limited to lightweight tasks or quadrupedal/wheeled platforms. To overcome these limitations, we propose FALCON, a dual-agent reinforcement-learning- based framework for robust force-adaptive humanoid loco-manipulation. FALCON decomposes whole-body control into two specialized agents: (1) a lower-body agent ensuring stable locomotion under external force disturbances, and (2) an upper-body agent precisely tracking end-effector posi- tions with implicit adaptive force compensation. These two agents are jointly trained in simulation with a force curriculum that progressively escalates the magnitude of external force exerted on the end effector while respecting torque limits. Experiments demonstrate that, compared to the base- lines, FALCON achieves 2$\times$ more accurate upper-body joint tracking, while maintaining robust lo- comotion under force disturbances and achieving faster training convergence. Moreover, FALCON enables policy training without embodiment-specific reward or curriculum tuning. Using the same training setup, we obtain policies that are deployed across multiple humanoids, enabling forceful loco-manipulation tasks such as transporting payloads (0-20N force), cart-pulling (0-100N), and door-opening (0-40N) in the real world.
APA
Zhang, Y., Yuan, Y., Gurunath, P., Gupta, I., Omidshafiei, S., Agha-mohammadi, A., Vazquez-Chanlatte, M., Pedersen, L., He, T. & Shi, G.. (2026). FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:265-281 Available from https://proceedings.mlr.press/v331/zhang26a.html.

Related Material