将人体动作自然适配到人形机器人，生成物理合理运动轨迹。
SPARK: Skeleton-Parameter Aligned Retargeting on Humanoid Robots with Kinodynamic Trajectory Optimization
- 通过骨骼结构对齐而非手动调整目标点，提升动作迁移精度。
- 分三阶段优化：运动学、逆动力学到完整动力学，逐步提升轨迹质量。
- 适用于多款人形机器人，适合做学习型控制的高质量参考轨迹。
人类动作蕴含丰富先验知识，可用于训练通用型人形机器人控制策略，但原始示范常因与机器人运动学和动力学不匹配而难以直接使用。本文提出两阶段流程，从任务空间的人体数据生成自然且动态可行的运动参考。第一阶段将人体动作转换为基于统一机器人描述格式（URDF）的骨骼表示，并校准至目标人形机器人的尺寸。通过对齐底层骨骼结构而非启发式修改任务空间目标，显著降低逆运动学误差与调参成本。第二阶段通过渐进式动力学轨迹优化（TO）精炼重定向轨迹，分三个阶段求解：运动学TO、逆动力学及全动力学TO，每阶段均从前一阶段解热启动。最终输出动态一致的状态轨迹与关节力矩曲线，为基于学习的控制器提供高质量参考。骨架校准与动力学轨迹优化相结合，使自然、物理一致的动作参考可在多种人形平台间生成。
原文摘要 · Abstract (English)
Human motion provides rich priors for training general-purpose humanoid control policies, but raw demonstrations are often incompatible with a robot's kinematics and dynamics, limiting their direct use. We present a two-stage pipeline for generating natural and dynamically feasible motion references from task-space human data. First, we convert human motion into a unified robot description format (URDF)-based skeleton representation and calibrate it to the target humanoid's dimensions. By aligning the underlying skeleton structure rather than heuristically modifying task-space targets, this step significantly reduces inverse kinematics error and tuning effort. Second, we refine the retargeted trajectories through progressive kinodynamic trajectory optimization (TO), solved in three stages: kinematic TO, inverse dynamics, and full kinodynamic TO, each warm-started from the previous solution. The final result yields dynamically consistent state trajectories and joint torque profiles, providing high-quality references for learning-based controllers. Together, skeleton calibration and kinodynamic TO enable the generation of natural, physically consistent motion references across diverse humanoid platforms.
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。