arXiv 2602.217232026-02cs.RO

LessMimic：基于统一距离场表示的长时域人形交互

LessMimic: Versatile Humanoid-Object Interaction with Unified Distance Field Representations

Yutang Lin, Jieming Cui, Yixuan Li, Wei Liang, Baoxiong Jia, Yixin Zhu, Siyuan Huang

AI总结：

LessMimic通过统一距离场表示实现人形机器人长时域交互，无需参考动作，利用变分自编码器和对抗交互先验进行训练，实现高成功率和多任务泛化能力。

摘要：

人形机器人能够自主地在物理环境中进行长时间的交互，代表了具身智能的核心目标。现有方法依赖于参考动作或任务特定的奖励，将策略紧密地与特定物体几何形状联系在一起，从而在单一框架内限制了多技能泛化。一种统一的交互表示，能够在不依赖参考的情况下进行推理，实现几何泛化和长时域技能组合，仍然是一个开放性挑战。本文证明距离场（DF）提供了这样的表示：LessMimic将单一的全身策略与DF衍生的几何线索——表面距离、梯度和速度分解——进行条件，从而摆脱了对运动参考的依赖，通过变分自编码器（VAE）对交互潜在变量进行编码，并通过对抗交互先验（AIP）在强化学习（RL）中进行后训练。通过类Daggers式蒸馏，使DF潜在变量与以自身为中心的深度特征对齐，LessMimic进一步无缝地转移到仅依赖视觉的部署中，而无需运动捕捉（MoCap）基础设施。一个单一的LessMimic策略在PickUp和SitStand任务中，从0.4x到1.6x的物体尺寸上实现了80-100%的成功率，其中基线显著下降；在5个任务实例轨迹中达到了62.1%的成功率，并能连续完成40个依次组成的任务。通过将交互基于局部几何而非示范，LessMimic提供了一条可扩展的路径，使人形机器人能够在无结构环境中实现泛化、技能组合和故障恢复。

英文摘要：

Humanoid robots capable of versatile whole-body interaction with everyday objects represent a central goal of embodied intelligence. Existing approaches often rely on motion-reference inputs or task-specific rewards, coupling policies to particular motion scripts, object geometries, and contact timings. This limits geometric generalization and flexible interaction control, where simple commands specify motion intent while object geometry determines how contact should be executed. We introduce LessMimic, a framework for versatile motion-free-at-inference humanoid-object interaction. At inference, a single whole-body policy is steered by root commands and an interaction-type flag instead of motion-reference inputs, and is conditioned on a compact interaction representation built from short histories of distance-field-derived surface distances and local surface directions. This geometry-conditioned interface enables command-steered control while adapting contact behavior to local object geometry. Through visual distillation, LessMimic further enables egocentric-depth-based deployment for MoCap-free sensing. Across object scales from 0.4x to 1.6x, LessMimic maintains robust performance over four interaction tasks, including PickUp, SitStand, Push, and Carry, where motion-conditioned baselines degrade sharply away from the training scale. Beyond single-task evaluation, LessMimic further supports sequential composition of heterogeneous interaction skills, attaining 62.1% success on five-task sequences and retaining 23.5% success at 15 task instances. By grounding interaction control in local geometry rather than motion references, LessMimic provides a path toward geometry-generalizable, command-steerable humanoid-object control with heterogeneous skill composition.

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。

AI总结：

摘要：

英文摘要：

相关论文