{"ID":22952774,"CreatedAt":"2026-09-17T02:12:05.498442134Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.18930","arxiv_id":"2609.18930","title":"Learning Holistic Whole-Body Loco-Manipulation with a Bipedal Mobile Manipulator","abstract":"Bipedal loco-manipulation enables robots to interact with objects beyond the nominal workspace of their arms by coordinating locomotion and manipulation. Realizing this capability requires a low-level whole-body controller that translates task-level manipulation goals into coordinated arm and leg motions while maintaining balance. We present a unified whole-body controller trained with reinforcement learning that directly maps 6-DoF end-effector targets to coordinated actions for the bipedal base and robotic arm. Given only an end-effector target, the learned controller autonomously coordinates reaching, postural adaptation, and stepping without explicit base-velocity or footstep commands. A reward-gating strategy regulates the trade-offs among end-effector tracking, locomotion, and balance during training, while a temporal context estimator combines windowed Transformer encoding, recurrent GRU memory, and auxiliary dynamics prediction to extract dynamics-relevant information from observation history. Real-robot experiments demonstrate that the same controller supports reaching, postural adaptation, and stepping under commands from VR teleoperation, a learned diffusion policy, and scripted trajectories, providing a common end-effector interface for diverse manipulation tasks.","short_abstract":"Bipedal loco-manipulation enables robots to interact with objects beyond the nominal workspace of their arms by coordinating locomotion and manipulation. Realizing this capability requires a low-level whole-body controller that translates task-level manipulation goals into coordinated arm and leg motions while maintain...","url_abs":"https://arxiv.org/abs/2609.18930","url_pdf":"https://arxiv.org/pdf/2609.18930v1","authors":"[\"Zhongyu Chen\",\"Yuxuan Nai\",\"Qian Chen\",\"Yidong Zhu\",\"Chen Jing\",\"Qihan Wang\",\"Xudong Li\",\"Zhizhan Li\",\"Leixin Chang\",\"Liangjing Yang\",\"Hua Chen\"]","published":"2026-09-16T17:05:32Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Reinforcement Learning\",\"Diffusion Model\",\"Transformer\"]","has_code":false}