paper-with-me

홈 › Papers

TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning

2025-09-15 · Jiacheng Liu, Pengxiang Ding, Qihang Zhou, Yuxuan Wu, Da Huang, Zimian Peng, Wei Xiao, Weinan Zhang, Lixin Yang, Cewu Lu, Donglin Wang arxiv

Recent Vision-Language-Action models show potential to generalize across embodiments but struggle to quickly align with a new robot's action space when high-quality demonstrations are scarce, especially for bipedal humanoids. We present TrajBooster, a cross-embodiment framework that leverages abundant wheeled-humanoid data to boost bipedal VLA. Our key idea is to use end-effector trajectories as a morphology-agnostic interface. TrajBooster (i) extracts 6D dual-arm end-effector trajectories from real-world wheeled humanoids, (ii) retargets them in simulation to Unitree G1 with a whole-body controller trained via a heuristic-enhanced harmonized online DAgger to lift low-dimensional trajectory references into feasible high-dimensional whole-body actions, and (iii) forms heterogeneous triplets that couple source vision/language with target humanoid-compatible actions to post-pre-train a VLA, followed by only 10 minutes of teleoperation data collection on the target humanoid domain. Deployed on Unitree G1, our policy achieves beyond-tabletop household tasks, enabling squatting, cross-height manipulation, and coordinated whole-body motion with markedly improved robustness and generalization. Results show that TrajBooster allows existing wheeled-humanoid data to efficiently strengthen bipedal humanoid VLA performance, reducing reliance on costly same-embodiment data while enhancing action space understanding and zero-shot skill transfer capabilities. For more details, For more details, please refer to our \href{https://jiachengliu3.github.io/TrajBooster/}.

📄 PDF Abstract BibTeX arXiv:2509.11839

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HumanoidExo: Scalable Whole-Body Humanoid Manipulation via Wearable Exoskeleton

2025-10-03 · Rui Zhong, Yizhe Sun, Junjie Wen, Jinming Li 외 arxiv

A significant bottleneck in humanoid policy learning is the acquisition of large-scale, diverse datasets, as collecting reliable real-world data remains both difficult and cost-prohibitive. To address this limitation, we…

WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination

2026-09-15 · Zhuo Li, Yiming Yao, Jim Tan, Mengjie Jing 외 arxiv

World Action Models (WAMs) offer a promising approach to general-purpose robot manipulation by jointly modeling visual dynamics and actions. However, most WAM studies focus on tabletop or arm-centric manipulation, while …

Robot Manipulation

HumanoidUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation

2026-06-25 · Hongwu Wang, Chenhao Yu, Youhao Hu, Jiachen Zhang 외 arxiv

High-quality demonstration data are essential for humanoid robot skill learning, especially for whole-body behaviors that require coordinated perception, locomotion, and manipulation. Existing data-collection methods lar…

Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations

2026-02-06 · Ruiqian Nai, Boyuan Zheng, Junming Zhao, Haodong Zhu 외 arxiv

Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics and complex reward engineering. Consequently, d…

Reinforcement Learning

TWIST: Teleoperated Whole-Body Imitation System

2025-05-05 · Yanjie Ze, Zixuan Chen, João Pedro Araújo, Zi-ang Cao 외

Teleoperating humanoid robots in a whole-body manner marks a fundamental step toward developing general-purpose robotic intelligence, with human motion providing an ideal interface for controlling all degrees of freedom.…