碰撞感知的人形机器人全身控制在不完美跟踪目标下的研究
Collision-Aware Humanoid Whole-Body Control under Imperfect Tracking Targets
浏览论文内容
中文总结 AI 辅助
针对全身控制器忽视场景几何导致碰撞的问题，提出RECAL交叉注意力层，融合环境点云实现碰撞感知跟踪，在仿真和真实Digit V3机器人上验证了碰撞避免与跟踪性能的兼顾。
中文摘要 AI 辅助
人形机器人通常通过全身控制器（WBCs）执行运动命令，这些控制器在跟踪目标的同时保持平衡和稳定性。然而，大多数全身控制器对场景几何结构视而不见，这可能导致由于感知、规划或遥操作错误而产生几何上不安全的、不完美的目标运动，从而引发碰撞。我们提出了RECAL，一种机器人-环境交叉注意力层，它包裹一个盲全身控制器，利用外部场景几何结构在目标跟踪和碰撞避免之间进行权衡。RECAL支持浮动基座和末端执行器命令的碰撞感知跟踪，包括对持有物体的碰撞避免。它将机器人、持有物体和环境表示为点云，利用机器人/物体点与环境之间的交叉注意力来生成几何感知的控制特征。在仿真中，与替代的几何感知全身控制架构相比，RECAL在冻结手臂和自适应手臂运动、物体搬运和站立操作场景中，在保持目标跟踪性能的同时改善了碰撞避免。我们还在真实的Digit V3人形机器人上展示了该控制器。
英文摘要
Humanoid robots often execute motion commands through whole-body controllers (WBCs) that track targets while maintaining balance and stability. However, most WBCs are blind to scene geometry, which can lead to collisions from imperfect target motions that are geometrically unsafe due to perception, planning, or teleoperation errors. We propose RECAL, a Robot--Environment Cross-Attention Layer that wraps a blind WBC to trade off target tracking against collision avoidance using external scene geometry. RECAL supports collision-aware tracking of floating-base and end-effector commands, including collision avoidance for held objects. It represents the robot, held objects, and environment as point clouds, using cross-attention between robot/object points and the environment to produce geometry-aware control features. In simulation, RECAL improves collision avoidance while preserving target-tracking performance across frozen-arm and adaptive-arm locomotion, object-carrying, and standing-manipulation scenarios relative to alternative geometry-aware WBC architectures. We further demonstrate the controller on a real Digit V3 humanoid robot.
发表机构
- Oregon State University（俄勒冈州立大学）
机构由 AI 辅助整理，请以论文原文为准。
