实时操控人形机器人，避免关节极限与碰撞陷阱。
MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation with Parallel Differential Inverse Kinematics
- 并行差分逆运动学求解器，多路径并行优化
- 在真实世界任务中实现毫秒级响应，零碰撞
- 适合人形机器人远程操控与实时仿生动作迁移
实时人形机器人遥操作需要高效且安全的逆运动学（IK）求解器，以应对运动冗余和自碰撞约束。尽管差分逆运动学可实现高效在线重定向，但其局部线性化更新受吸引域限制，常困于关节极限、奇点或活跃碰撞边界，导致行为不安全或停滞。本文提出一种基于GPU并行的连续型差分逆运动学方法，在保持实时性能的同时，提升逃离此类约束局部极小值的能力，增强安全性与稳定性。多个带约束的逆运动学二次规划问题并行求解，结合自碰撞避让控制屏障函数（CBF），并通过基于李雅普诺夫的进展准则选择能最小化最终全局任务空间误差的更新。该方法与视觉骨骼姿态估计流程集成，实现了在真实世界任务中对THEMIS人形机器人上肢的鲁棒、实时遥操作。
原文摘要 · Abstract (English)
Real-time humanoid teleoperation requires inverse kinematics (IK) solvers that are both responsive and constraint-safe under kinematic redundancy and self-collision constraints. While differential IK enables efficient online retargeting, its locally linearized updates are inherently basin-dependent and often become trapped near joint limits, singularities, or active collision boundaries, leading to unsafe or stagnant behavior. We propose a GPU-parallelized, continuation-based differential IK that improves escape from such constraint-induced local minima while preserving real-time performance, promoting safety and stability. Multiple constrained IK quadratic programs are evaluated in parallel, together with a self-collision avoidance control barrier function (CBF), and a Lyapunov-based progression criterion selects updates that reduce the final global task-space error. The method is paired with a visual skeletal pose estimation pipeline that enables robust, real-time upper-body teleoperation on the THEMIS humanoid robot hardware in real-world tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。