Valency Hub
alphaFeedback

WorksComputer Science

Learning Force-Reactive Humanoid Loco-Manipulation

Sihang Li, Xiaofeng Guo, Jinkun Cao, Charlie Cheng, Ruihan Yang

Published Fresh — added to the Hub within the last 30 daysv11 min read

AI contributions
Not recorded for this paper
View details

Abstract

Many everyday tasks require controlling contact force as well as motion. On a humanoid, this force must often be coordinated across both hands and the whole body, and cannot be specified by kinematic trajectories alone. Therefore, we present FLORE, a framework for learning force-reactive humanoid loco-manipulation. We collect robot-free demonstrations using two force-sensing UMI-style handheld grippers for hand motion and contact wrenches, and wearable trackers for body motion. A force-reactive diffusion policy takes vision, proprioception, and measured wrenches as input, then predicts actions and per-hand force commands. A hybrid compliance whole-body controller with force tracking executes these commands while maintaining balance: an integral of the force error measured by real force/torque (F/T) sensors lets each hand track force accurately along the commanded direction and remain compliant along the others. In simulation, the controller tracks per-hand force commands of varied magnitude and direction, with little loss in whole-body motion accuracy. Across three contact-rich tasks on the robot, the force-reactive policy succeeds in 80% of rollouts, compared with 26.7% for a position-only policy trained on the same demonstrations and executed by the same controller. For more details, please visit our website: https://louis-leee.github.io/FLoRe/.

Figure 1, panel 1Figure 1, panel 2

Figure 1. FLoRe is a framework that learns force-reactive loco-manipulation from robot-free demonstrations. (a)~Two handheld UMI-style grippers carrying 6-axis F/T sensors and three trackers record hand/torso motion, gripper width and contact forces. From these demonstrations, we train a force-reactive diffusion policy that predicts per-hand force commands. A unified force-position whole-body controller then executes the motion and force together, enabling the following capabilities: (b)~robustness to force variation: the robot walks a heavy wheeled gantry forward with both hands; (c)~bimanual coordination: the robot rotates a heavy box (12\,kg) while dragging it across the table without tipping or lifting it; (d)~sustained contact: one hand presses an eraser against a whiteboard and holds a steady normal force through the stroke. The overlaid curves trace the hand keypoints and the arrows mark the commanded force at its peak; the traces below show the commanded (dashed) and measured (solid) force per hand and axis.

[IEEEtran:BSTcontrol

References

  1. [1]Zhao, T. Z., Kumar, V., Levine, S., & Finn, C. (2023). Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware. RSS. https://arxiv.org/abs/2304.13705
  2. [2]Hou, Y., Liu, Z., Chi, C., Cousineau, E., Kuppuswamy, N., Feng, S., Burchfiel, B., & Song, S. (2025). Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Control. ICRA. https://arxiv.org/abs/2410.09309
  3. [3]Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI).
  4. [4]Perez, E., Strub, F., Vries, H. de ., Dumoulin, V., & Courville, A. (2018). FiLM: Visual Reasoning with a General Conditioning Layer. AAAI Conference on Artificial Intelligence (AAAI).
  5. [5]Surendran, V., Peri, N., & Watkins, D. (2026). Bridging Handheld and Teleoperated Supervision for Contact-Rich Manipulation via State-Gated Experts. arXiv:2606.26603. https://arxiv.org/abs/2606.26603
  6. [6]Liao, Q., Truong, T. E., Huang, X., Gao, Y., Tevet, G., Sreenath, K., & Liu, C. K. (2026). BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion. Science Robotics. https://arxiv.org/abs/2508.08241
  7. [7]Wang, H., Yu, C., Hu, Y., Zhang, J., Li, Y., & Luo, S. (2026). BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation. arXiv:2605.03452. https://arxiv.org/abs/2605.03452
  8. [8]Chen, S., Cao, Z.-. ang ., Luo, Z., Castañeda, F., Li, C., Wang, T., Yuan, Y., J̈imF̈an, L., Liu, C. K., & Zhu, Y. (2026). CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation. CoRL. https://arxiv.org/abs/2512.14689
  9. [9]Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. ICML.
  10. [10]Kamijo, T., Beltran-Hernandez, C. C., & Hamaya, M. (2024). Learning Variable Compliance Control From a Few Demonstrations for Bimanual Robot with Haptic Feedback Teleoperation System. IROS. https://arxiv.org/abs/2406.14990
  11. [11]Song, J., Meng, C., & Ermon, S. (2021). Denoising Diffusion Implicit Models. ICLR.
  12. [12]Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS.
  13. [13]Chi, C., Xu, Z., Feng, S., Cousineau, E., Du, Y., Burchfiel, B., Tedrake, R., & Song, S. (2023). Diffusion Policy: Visuomotor Policy Learning via Action Diffusion. RSS.
  14. [14]Xu, B., Weng, H., Lu, Q., Gao, Y., & Xu, H. (2025). FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots. CoRL. https://arxiv.org/abs/2505.06883
  15. [15]Liu, J. J., Li, Y., Shaw, K., Tao, T., Salakhutdinov, R., & Pathak, D. (2025). FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning. RSS. https://arxiv.org/abs/2502.17432
  16. [16]Zhang, Y., Yuan, Y., Gurunath, P., Gupta, I., Omidshafiei, S., Agha-mohammadi, A.-. akbar ., Vazquez-Chanlatte, M., Pedersen, L., He, T., & Shi, G. (2026). FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation. L4DC. https://arxiv.org/abs/2505.06776
  17. [17]He, H., Yan, Z., Liu, Q., Guo, N., & Lian, W. (2026). FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation. arXiv:2606.08555. https://arxiv.org/abs/2606.08555
  18. [18]He, Z., Fang, H., Chen, J., Fang, H.-S., & Lu, C. (2025). FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulation. RA-L. https://arxiv.org/abs/2411.15753
  19. [19]Portela, T., Margolis, G. B., Ji, Y., & Agrawal, P. (2024). Learning Force Control for Legged Manipulation. ICRA. https://arxiv.org/abs/2405.01402
  20. [20]Liu, W., Wang, J., Wang, Y., Wang, W., & Lu, C. (2025). ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation. ICRA. https://arxiv.org/abs/2410.07554
  21. [21]Fang, H., Tang, S., Mei, M., Qin, H., He, Z., Chen, J., Feng, Y., Wang, C., Liu, W., He, Z., Lu, C., & Wang, S. (2026). Force Policy: Learning Hybrid Force-Position Control Policy under Interaction Frame for Contact-Rich Manipulation. RSS. https://arxiv.org/abs/2602.22088
  22. [22]Lin, T., Zhang, Y., Li, Q., Qi, H., Yi, B., Levine, S., & Malik, J. (2025). Learning Visuotactile Skills with Two Multifingered Hands. ICRA. https://arxiv.org/abs/2404.16823
  23. [23]Liu, C., Lu, Q., Yang, G., Shi, X., Yang, C., Guo, Y., & Chen, J. (2026). HEFT: Heavy-Payload Full-size Humanoid Teleoperation with Privileged Motion Guidance and Windowed Payload Curriculum. arXiv:2607.02332. https://arxiv.org/abs/2607.02332
  24. [24]He, T., Xiao, W., Lin, T., Luo, Z., Xu, Z., Jiang, Z., Kautz, J., Liu, C., Shi, G., Wang, X., Fan, L., & Zhu, Y. (2025). HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots. ICRA. https://arxiv.org/abs/2410.21229
  25. [25]Xu, X., Park, J., Zhang, H., Cousineau, E., Bhat, A., Barreiros, J., Wang, D., Bohg, J., & Song, S. (2026). HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations. RSS. https://arxiv.org/abs/2603.03243
  26. [26]Nai, R., Zheng, B., Zhao, J., Zhu, H., Dai, S., Chen, Z., Hu, Y., Hu, Y., Zhang, T., Wen, C., & Gao, Y. (2026). Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations. arXiv:2602.06643. https://arxiv.org/abs/2602.06643
  27. [27]Mittal, M., Roth, P., Tigue, J., Richard, A., Zhang, O., Du, P., Serrano-Muñoz, A., Yao, X., Zurbrügg, R., Rudin, N., Wawrzyniak, L., Rakhsha, M., Denzler, A., Heiden, E., Borovicka, A., Ahmed, O., Akinola, I., Anwar, A., Carlson, M. T., … State, G. (2025). Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning. arXiv:2511.04831. https://arxiv.org/abs/2511.04831
  28. [28]Xiao, K., Xu, Z., Zhe, C., Liu, C., & Chen, Q. (2025). Kinematics-Aware Multi-Policy Reinforcement Learning for Force-Capable Humanoid Loco-Manipulation. arXiv:2511.21169. https://arxiv.org/abs/2511.21169
  29. [29]Tessler, C., Guo, Y., Nabati, O., Chechik, G., & Peng, X. B. (2024). MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting. ACM Transactions on Graphics (SIGGRAPH Asia), 43(6).
  30. [30]Luo, S., Li, Y., Hu, Y., Yu, C., Xu, C., Zhang, J., Yao, G., Huang, T., He, R., & Wang, Z. (2026). OmniUMI: Towards Physically Grounded Robot Learning via Human-Aligned Multimodal Interaction. arXiv:2604.10647. https://arxiv.org/abs/2604.10647
  31. [31]Zhou, Y., Barnes, C., Lu, J., Yang, J., & Li, H. (2019). On the Continuity of Rotation Representations in Neural Networks. CVPR.
  32. [32]Luo, Z., Yuan, Y., Wang, T., Li, C., Castañeda, F., Chen, S., Cao, Z.-A., Li, J., Minor, D., Ben, Q., Park, J., Sami, D., Wang, Z., Da, X., Ding, R., Hogg, C., Song, L., Lim, E., Jeong, E., … Zhu, Y. (2026). SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control. Science Robotics. https://arxiv.org/abs/2511.07820
  33. [33]Margolis, G. B., Wang, M., Fey, N., & Agrawal, P. (2026). SoftMimic: Learning Compliant Whole-body Control from Examples. ICRA. https://arxiv.org/abs/2510.17792
  34. [34]Niu, Y., Fang, Z., Chen, B., Zhou, S., Senthilkumaran, R. K., Zhang, H., Chen, B., Qiu, C., Tseng, H. E., Francis, J., & Zhao, D. (2026). Learning Versatile Humanoid Manipulation with Touch Dreaming. IROS. https://arxiv.org/abs/2604.13015
  35. [35]Chi, C., Xu, Z., Pan, C., Cousineau, E., Burchfiel, B., Feng, S., Tedrake, R., & Song, S. (2024). Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots. RSS. https://arxiv.org/abs/2402.10329
  36. [36]Choi, H., Hou, Y., Pan, C., Hong, S., Patel, A., Xu, X., Cutkosky, M. R., & Song, S. (2026). In-the-Wild Compliant Manipulation with UMI-FT. ICRA. https://arxiv.org/abs/2601.09988
  37. [37]Wang, Y.-J., Li, J., Chen, S., Truong, T. E., Xu, P., Abbeel, P., Duan, R., Sreenath, K., Kanazawa, A., Sferrazza, C., Shi, G., & Liu, C. K. (2026). VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes. CoRL. https://arxiv.org/abs/2606.30645
  38. [38]RoboParty Lab Team. (2026). sim2real: A Lightweight and Modular Sim2sim and Sim2real Deployment Stack. In https://github.com/EGalahad/sim2real. https://github.com/EGalahad/sim2realgithub.com/EGalahad/sim2real
  39. [39]Zhi, P., Li, P., Yin, J., Jia, B., & Huang, S. (2025). Learning a Unified Policy for Position and Force Control in Legged Loco-Manipulation. CoRL. https://arxiv.org/abs/2505.20829
  40. [40]Martín-Martín, R., Lee, M. A., Gardner, R., Savarese, S., Bohg, J., & Garg, A. (2019). Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks. IROS. https://arxiv.org/abs/1906.08880
  41. [41]Jang, J., Gu, Z., Cueva, A., Chai, Z., Sheng, J., Nguyen, T., Galundia, H., Wu, Y., Xue, H., Legene, I., Mediratta, O., Doan, D., Collins, A., Sadegh, S., Kim, K., Dhalbisoi, R., Chen, Z., & Zhao, Y. (2026). WT-UMI: Tactile-based Whole-Body Manipulation via Force-Supervised Contact-Aware Planning. CoRL. https://arxiv.org/abs/2606.13232

Paper details

Publication

vlnc:W_bfdjn3j4
v1 · latestHistory (1)

published · Fresh — added to the Hub within the last 30 days

added ·

Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

CC BY 4.0

Original source

Taxonomy

  • Computer Science

Authors

AI contributions

Not recorded for this paper · View statement →

Looking for related papers…
Contents