Tracking large human-motion datasets has become the dominant route to general, expressive humanoid whole-body control, but scaling across many motions is expensive. Current pipelines use model-free reinforcement learning, either merging per-motion specialists through lossy distillation, or brute-forcing a single policy...
Qia-Yuan Liao, Yi-Yang Shao, Jun-Feng Long et al.· 1 citation
Humanoid robots still struggle to plan contact-rich whole-body manipulation from egocentric RGB and proprioception. Workhorse learns such manipulation from robot-free human demonstrations. A visual planner predicts five-link targets: the poses of the torso, both wrists, and both feet. A reinforcement-learning whole-bod...
Song-Bo Hu, Qia-Yuan Liao, Yu-Feng Chi et al.· 1 citation
Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist robots. However, collecting diverse, high-quality interaction videos, such as clips that clearly show a person's full body and unoccluded interactions with objects, poses a practical...
Zihan Wang, Zhen Wu, Pieter Abbeel et al.· 0 citations
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of robot execution systems without updating model wei...
Yen-Jen Wang, Hao-Zhe Jiang, Shu-Ying Deng et al.· 3 citations
Safe-Stop is proposed, a task-agnostic framework that pairs a learned stop policy with learned stoppability estimators, and yields decisions that are robust without sacrificing reactivity.
Jun-Feng Long, Pieter Abbeel, K. Sreenath et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
