发表机构
University of Massachusetts Amherst; Massachusetts Institute of Technology（马萨诸塞大学阿默斯特分校; 麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对人形机器人遥操作中空间感知视界受限的问题，提出SPOT系统，通过鱼眼相机、宽视场显示与视角解耦，提升长时间跨度数据收集的效率与准确性。
AI 中文摘要
高质量演示数据正成为训练通用人形机器人的核心瓶颈。尽管近期的人形机器人遥操作系统在将人体运动重定向到机器人运动方面取得了实质性进展，但长时间跨度的移动操作还需要另一种能力：操作员必须随时间保持与任务相关的空间感知，例如物体位置、周围环境以及机器人的姿态。我们将这种感知的范围称为操作员的感知视界。然而，现有方法往往会缩短这一视界：狭窄的视野会遗漏周边事件，安装在机器人上的摄像头在运动过程中会变得不稳定，而耦合的头部视角控制会使环顾四周干扰机器人运动。我们提出了SPOT，一种面向空间感知的VR遥操作系统，通过提供扩展的感知视界来收集长时间跨度的人形机器人演示数据。SPOT结合了安装在机器人上的双目鱼眼摄像头、宽视场立体显示器、视角解耦的自由观看以及视觉稳定化，以提供一种宽广、稳定且可主动检查的机器人中心视角。与传统的第一人称界面不同，SPOT将视觉探索与机器人驱动解耦：第一人称立体观察被渲染在操作员周围的虚拟半球上，因此自然的头部旋转会改变操作员在宽视场视图中的观看位置，而不是控制机器人头部、摄像头或躯干。我们在感知关键的机器人数据收集任务上评估了SPOT，涵盖掉落恢复、周边取物、大工作空间双臂操作、精细对齐和动态交互。SPOT提高了效率、准确性和恢复速度，证明了其在用户友好且可扩展的长时间跨度人形机器人数据收集方面的有效性。
英文摘要
High-quality demonstration data is becoming a central bottleneck for training general-purpose humanoid robots. While recent humanoid teleoperation systems have made substantial progress in retargeting human motion to robot motion, long-horizon loco-manipulation requires another capability: operators must maintain task-relevant spatial awareness over time, e.g., object locations, surrounding environments, the robot's pose. We call the extent of this awareness the operator's perceptual horizon. However, existing methods often shorten this: narrow views miss peripheral events, robot-mounted cameras become unstable during locomotion, and coupled head-view control makes looking around interfere with robot motion. We present SPOT, a Spatial Perception-Oriented VR Teleoperation system for collecting long-horizon humanoid demonstration data by providing extended perceptual horizon. SPOT combines a robot-mounted binocular fisheye camera, a wide-field stereoscopic display, viewpoint-decoupled free-looking, and visual stabilization to provide a robot-centric view that is wide, stable, and actively inspectable. Unlike conventional egocentric interfaces, SPOT decouples visual exploration from robot actuation: the egocentric stereo observation is rendered on a virtual hemisphere around the operator, so natural head rotations change where the operator looks within the wide-field view rather than commanding the robot head, camera, or torso. We evaluate SPOT on perception-critical humanoid data-collection tasks spanning drop recovery, peripheral retrieval, large-workspace bimanual manipulation, fine alignment, and dynamic interaction. SPOT improves efficiency, accuracy, and recovery speed, demonstrating its effectiveness for user-friendly and scalable long-horizon humanoid data collection.
