PILOT：一种用于非结构化场景中人形机器人类人协作的感知式低层控制器
PILOT: A Perceptive Integrated Low-level Controller for Loco-manipulation over Unstructured Scenes
AI总结：
PILOT通过统一的强化学习框架，实现了感知式人形机器人移动与操作的稳定控制，提升了在复杂非结构化环境中的任务执行能力。
摘要：
人形机器人在人类中心环境中具有广泛的应用潜力，需要能够无缝整合精确移动与灵活操作的控制器。然而，大多数现有的全身控制器缺乏对周围环境的外周感知能力，无法在复杂、非结构化的场景中稳定执行任务。为了解决这一挑战，我们提出了PILOT，一种统一的单阶段强化学习（RL）框架，专门用于感知式移动与操作。该框架在单一策略中协同感知移动和扩展的全身控制。为了增强地形感知并确保精确的脚部放置，我们设计了一种跨模态上下文编码器，将基于预测的本体感觉特征与基于注意的感知表示进行融合。此外，我们引入了专家混合（MoE）策略架构，以协调多种运动技能，促进在不同运动模式下的更好专业化。在模拟和物理Unitree G1人形机器人上的大量实验验证了我们框架的有效性。PILOT在稳定性、命令跟踪精度和地形穿越能力方面均优于现有基线。这些结果突显了其作为非结构化场景中人形机器人移动与操作稳健基础低层控制器的潜力。
英文摘要：
Humanoid robots hold great potential for diverse interactions and daily service tasks within human-centered environments, necessitating controllers that seamlessly integrate precise locomotion with dexterous manipulation. However, most existing whole-body controllers lack exteroceptive awareness of the surrounding environment, rendering them insufficient for stable task execution in complex, unstructured scenarios.To address this challenge, we propose PILOT, a unified single-stage reinforcement learning (RL) framework tailored for perceptive loco-manipulation, which synergizes perceptive locomotion and expansive whole-body control within a single policy. To enhance terrain awareness and ensure precise foot placement, we design a cross-modal context encoder that fuses prediction-based proprioceptive features with attention-based perceptive representations. Furthermore, we introduce a Mixture-of-Experts (MoE) policy architecture to coordinate diverse motor skills, facilitating better specialization across distinct motion patterns. Extensive experiments in both simulation and on the physical Unitree G1 humanoid robot validate the efficacy of our framework. PILOT demonstrates superior stability, command tracking precision, and terrain traversability compared to existing baselines. These results highlight its potential to serve as a robust, foundational low-level controller for loco-manipulation in unstructured scenes.
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。
