arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.30044cs.ROcs.AI
收藏

SP-HLM:用于人形机器人移动操作的稀疏姿态驱动运动生成与全身控制

SP-HLM: Sparse-Pose-Driven Motion Generation and Whole-Body Control for Humanoid Loco-Manipulation

Shanghai Jiao Tong University(上海交通大学);Moore Threads(摩尔线程);The University of Hong Kong(香港大学)

Zhaohui Yang, Quanbao Lin, Chengqi Shi, Zhenglang Weng, Jicheng Lin, Boyu Chen, Tengjie Zhu, Guanzhu Ren, Jiahao Xu, Yang Feng, Xiaokang Yang, Yao Mu

AI总结:

该研究提出SP-HLM框架,通过稀疏姿态驱动接口结合多模型实现人形机器人移动操作的运动生成与全身控制,实验验证其在相关指标上优于现有方法。

摘要:

人形机器人移动操作需要在高层任务策略与全身控制之间建立有效接口。现有接口通常依赖单一动作表示来同时承载任务意图与全身协调,这可能会给高层策略带来负担,或导致某一方面的规范不足。我们提出SP-HLM,一个基于稀疏姿态驱动接口的框架。该接口将5个对任务至关重要的身体姿态与学习到的潜在运动先验相结合,以互补形式表示空间意图与全身协调。SP-VLA是一个视觉-语言-动作模型,首先通过异步动作块推理,从多模态观测和语言指令中预测与任务相关的稀疏姿态和手指关节位置。给定这些稀疏目标后,SP-MGM是一个经两阶段蒸馏训练的运动生成模型,可实时重构协调的全身运动。一个预训练的运动编码器将该运动映射为紧凑的潜在表示。随后,SP-GMT是一个通用运动跟踪器,将显式稀疏目标与该隐式运动先验相整合,用于全身控制。在仿真环境和真实人形机器人上开展的实验表明,与现有方法相比,该方法在运动跟踪、全身协调及移动操作成功率方面均有所提升。更多结果和视频可在我们的项目页面获取。

英文摘要:

Humanoid loco-manipulation requires an effective interface between high-level task policies and whole-body control. Existing interfaces typically rely on a single action representation for both task intent and whole-body coordination. This may burden the high-level policy or leave one aspect underspecified. We present SP-HLM, a framework built on a sparse-pose-driven interface. The interface combines five task-critical body poses with a learned latent motion prior to represent spatial intent and whole-body coordination in complementary forms. SP-VLA, a vision-language-action model, first predicts task-relevant sparse poses and finger joint positions from multimodal observations and language instructions using asynchronous action-chunk inference. Given these sparse targets, SP-MGM, a motion generation model trained through two-stage distillation, reconstructs coordinated full-body motion in real time. A pretrained motion encoder maps this motion to a compact latent representation. SP-GMT, a general motion tracker, then integrates the explicit sparse targets with this implicit motion prior for whole-body control. Experiments in simulation and on a real humanoid robot demonstrate improved motion tracking, whole-body coordination, and loco-manipulation success over existing approaches. Additional results and videos are available on our \href{https://sp-hlm.github.io/}{\textcolor{blue}{project page}}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑