HOTICE：杂乱环境中的全身人形物体运输
HOTICE: Whole-Body Humanoid Object Transportation in Cluttered Environments
- University of Southern California（南加州大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
HOTICE提出全身人形学习框架，通过解耦势场和双智能体强化学习，结合专家到通才蒸馏，实现杂乱环境中物体的鲁棒运输与避碰。
中文摘要 AI 辅助
物体运输是人形机器人在真实、以人为中心的环境中运行的一项基本能力，然而当杂乱环境限制了机器人和其所携带负载周围自由空间时，现有方法难以应对。我们提出了HOTICE，一个用于在杂乱环境中运输物体的全身人形学习框架。首先，我们引入了人形-物体解耦势场，该势场联合编码了机器人和所携带物体的避碰引导，使两者能够协调、感知障碍物地运动。其次，为了解决全身腿部-操作控制固有的巨大动作空间问题，我们设计了一种双智能体强化学习架构，该架构解耦了上半身和下半身的控制，同时通过共享状态观测和奖励保持全身协调。为了训练一个能泛化到各种杂乱场景的策略，我们进一步采用了从专家到通才的蒸馏策略，将特权教师策略蒸馏到一个可部署的学生策略中。我们在MuJoCo仿真和真实Unitree G1人形机器人上评估了HOTICE，展示了在杂乱场景中对不同形状物体进行有效且鲁棒的物体运输。我们的结果表明，HOTICE可靠地协调全身运动和物体感知避碰，有效泛化到未见过的杂乱环境，并在仿真到现实部署中实现了强劲性能。
英文摘要
Object transportation is a fundamental capability for humanoid robots operating in real-world, human-centric environments, yet existing methods struggle when clutter constrains free space around both the robot and its carried payload. We present HOTICE, a whole-body humanoid learning framework for transporting objects through such cluttered environments. First, we introduce Humanoid-Object Decoupled Potential Fields, which jointly encode collision-avoidance guidance for the robot and the carried object, enabling coordinated, obstacle-aware motion for both. Second, to address the large action space inherent to whole-body loco-manipulation, we design a dual-agent reinforcement learning architecture that decouples upper- and lower-body control while preserving whole-body coordination via shared state observations and rewards. To train a policy that generalizes across diverse cluttered scenes, we further employ a specialist-to-generalist distillation strategy, in which privileged teacher policies are distilled into a single deployable student policy. We evaluate HOTICE in MuJoCo simulation and on a real Unitree G1 humanoid, demonstrating effective and robust object transportation across cluttered scenarios for objects of varying shapes. Our results show that HOTICE reliably coordinates whole-body motion and object-aware collision avoidance, generalizing effectively to previously unseen cluttered environments while achieving strong performance in sim2real deployment.
