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
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...
FWBC‑VLA is a force‑aware framework that links vision‑language‑action (VLA) models with whole‑body compensation control for wheeled‑legged robots. It introduces HSR‑Force, a sensorless residual‑torque estimator that infers contact strength and encodes this information as tokens for the VLA action decoder, allowing the policy to detect contact onset, loading, and release. The system fine‑tunes a pretrained VLA backbone on a large WL&Arm dataset, combines proprioceptive, Jacobian‑derived force, and contact estimates to generate corrective actions, and demonstrates effectiveness in real‑world tasks such as whiteboard wiping and door opening.
By Yutian Zhang, Siyuan Ma, Liwen Yang, Yang Li, Ce Hao, Haozhen Chi, Dong We, Qiaojun Yu, Dibo Hou
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.
DexPort is a portable interface that lets operators collect high‑quality dexterous hand demonstrations without a full robot setup. By using the same hand hardware for both collection and deployment, it records joint targets and states while allowing operators to specify wrist motion and select from a small set of coordinated finger skills. The authors collected over 2,500 demonstrations across four real‑world tasks, showing significant performance gains when using recorded robot commands and in‑the‑wild data.
By Amber Xie, Jiawei Fu, Xiaofeng Guo, Carmelo Sferrazza, Guanya Shi, 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
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
PiHand is a physics‑based framework that learns latent hand‑object interaction priors for dexterous manipulation. It first trains expert policies to track motion capture demonstrations, then distills these into a goal‑conditioned VAE that captures coupled hand‑object motion. Using bounded residual exploration in this latent space, PiHand produces general tabletop manipulation policies that generalize to unseen objects and trajectories, outperforming baselines across multiple tasks.
By Niklas Berndt, Xianghui Xie, Enes Duran, Yixiao Wang, Gerard Pons-Moll
ULTRA is a unified framework for autonomous humanoid whole-body locomotion and manipulation that overcomes limitations of prior methods by combining a physics-driven neural retargeting algorithm with a multimodal controller. The retargeting algorithm translates large-scale motion capture data into physically plausible humanoid motions, while the controller learns to handle both dense motion references and sparse task specifications using a range of sensory inputs, from accurate motion-capture states to noisy egocentric vision. In simulation and on a real Unitree G1 humanoid, ULTRA demonstrates improved generalization and robustness, enabling coordinated whole-body behavior from sparse intent without relying on test-time reference motions.
By Xialin He, Sirui Xu, Xinyao Li, Runpei Dong, Liuyu Bian, Yu-Xiong Wang, Liang-Yan Gui
PiHand is a physics‑based policy learning framework that synthesizes realistic hand‑object interactions for dexterous manipulation. It first trains expert policies to track motion capture data, then distills these into a goal‑conditioned VAE that captures coupled hand‑object motion. Using bounded residual exploration in this latent space, PiHand produces general tabletop manipulation policies that generalize to unseen objects and trajectories, outperforming baselines across multiple tasks.
VioLA is a generalist humanoid control policy that predicts body and hand motion latents instead of joint commands, enabling a pretrained controller to execute these latents on a robot. By aligning human and robot motion in shared latent spaces, the policy can be trained on a large dataset of 140.6 million frames, 93.2% of which are human demonstrations. As a result, VioLA can follow locomotion and manipulation instructions on a real robot zero‑shot, achieving 100% locomotion success and 88.6% manipulation success without task‑specific fine‑tuning.
By Mert Albaba, Jens Bei{\ss}wenger, Anna Manasyan, Daniel Marta, Michael J. Black, Wieland Brendel, Andreas Krause, Georg Martius, Martin Riedmiller
arXiv:2606. 06493v1 Announce Type: cross Abstract: For a humanoid robot to be deployed in the real world, the choice of command space (i.
By Lizhi Yang, Junheng Li, Nehar Poddar, Yiling Hou, Gio Huh, Robert Griffin, Georgia Gkioxari, Aaron Ames