The paper introduces FLORE, a framework for learning force‑reactive humanoid loco‑manipulation. It uses robot‑free demonstrations with force‑sensing grippers and wearable trackers to train a diffusion policy that predicts actions and per‑hand force commands from vision, proprioception, and measured wrenches. A hybrid compliance whole‑body controller then executes these commands, achieving accurate force tracking and maintaining balance, outperforming a position‑only policy on three contact‑rich tasks.
By Sihang Li, Xiaofeng Guo, Jinkun Cao, Charlie Cheng, Ruihan Yang, Chen Feng, Guanya Shi, Haozhi Qi
arXiv:2611.05507v1 Announce Type: cross
Abstract: Humanoid motion tracking has scaled to general policies that reproduce diverse human motion, but the resulting behavior is in free-space: the tracker...
By Mengjie Zhao, Yuxin Chen, Yiyang Shao, Chuye Hong, Jiakang Chen, Koushil Sreenath, Masayoshi Tomizuka
Learning humanoid-object interaction requires coordinating whole-body balance, locomotion, and dexterous hand contact to control both robot and object motion. Human demonstrations provide examples of...
arXiv:2609.16683v1 Announce Type: cross
Abstract: Learning humanoid-object interaction requires coordinating whole-body balance, locomotion, and dexterous hand contact to control both robot and objec...
By Liu Cao, Xingze Wu, Jingzhi Cui, Botian Xu, Mingzhi Pei, Ruoqu Chen, Mengdi Xu
ForceFlow is a force-aware reactive framework that uses flow matching to improve contact-rich manipulation. It fuses force signals asymmetrically, treats force as a global regulator, and employs a joint prediction paradigm to couple force and motion. The approach splits tasks into a vision-dominant localization stage and a touch-dominant execution stage, using a Vision-to-Force handover to separate spatial generalization from contact regulation.
By Shuoheng Zhang, Yifu Yuan, Hongyao Tang, Yan Zheng, Qiaojun Yu, Pengyi Li, Guowei Huang, Helong Huang, Xingyue Quan, Jianye Hao
arXiv:2607. 11874v1 Announce Type: cross Abstract: Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them.
By Yunhai Feng, Natalie Leung, Jiaxuan Wang, Lujie Yang, Haozhi Qi, Preston Culbertson
Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation?
Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's center of mass and impose sustained loads across the u...
arXiv:2610.08970v1 Announce Type: cross
Abstract: Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's cen...
By An Dang, Arturo Flores Alvarez, Yu-Ming Chen, Conor Mc Gartoll, Helen Sun, Aaron Ames, Nima Fazeli, Manikantan Nambi
Humanoid loco-manipulation is often simplified into a stop-and-go process: walking to an object, stopping to manipulate it, and then resuming locomotion. It also commonly relies on low degree-of-freedom (DoF) end effectors that behave like an open-close grasp primitive.
arXiv:2610.17161v1 Announce Type: cross
Abstract: Teleoperation is widely used to collect high-quality demonstrations for robot learning. Dexterous manipulation, however, requires coordinated control...
By Ying Yuan, David Held, Jitendra Malik, Haozhi Qi
arXiv:2609.24660v2 Announce Type: cross
Abstract: Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot...
By Shengcheng Luo, Xiaoyang Cheng, Hong Ying, Xiaoying Zhou, Jiaming Jiang, Haoran Guo, Wanlin Li, Ziyuan Jiao, Chenxi Xiao