用自适应控制提升机器人手部动作追踪精度
ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control
- 将物体追踪设为约束，动态分配控制权以平衡动作保真度
- 在模拟与真实机器人上均显著提升轨迹成功率与姿态精度
- 支持长时序、高接触任务，适合复杂灵巧操作场景
人类示范为机器人操作提供了强先验，但因运动学差异难以直接迁移至真实机器人。在灵巧操作中，即使在模拟器内追踪长时序、高接触序列仍具挑战：参考追踪策略需保持物体在目标轨迹上，同时保留示范的关节运动与接触时机。现有方法常依赖手工设计奖励函数，需逐序列调参，且在交互预算有限时失效。我们提出ConTrack，一种可扩展的强化学习框架。ConTrack将物体追踪视为约束，将剩余控制权分配给运动保真度，通过双变量更新实现任务-风格的在线自适应权衡。此外，还引入自适应中段重置库，复用策略可达的模拟状态，稳定长时序学习。仿真与真实机器人实验表明，ConTrack在成功率与物体位姿精度上显著优于现有方法，同时保持关节与接触保真度。
原文摘要 · Abstract (English)
Human demonstrations provide strong priors for robot manipulation, yet it is non-trivial to transfer them to execute on real robots due to the kinematic gap. In dexterous manipulation, it remains challenging to track long-horizon, contact-rich sequences even in simulators: a reference-tracking policy must keep objects on their target trajectories while preserving demonstrated joint motion and contact timing. Existing approaches often rely on hand-crafted reward tuning that require per-sequence tuning and break under limited interaction budgets. We introduce ConTrack, a reinforcement learning (RL) framework that scales with tracking data. ConTrack treats object tracking as a constraint and allocates remaining control authority to motion fidelity, which allows it to adapt task--style trade-offs online using a dual-variable update. In addition, ConTrack also stabilizes long-horizon learning with an adaptive mid-trajectory reset library that reuses policy-reachable simulator states. Our qualitative and quantitative results in simulation tracking and real robot demonstrate that ConTrack improves success and object pose accuracy significantly over prior arts while preserving joint and contact fidelity. Website: https://www.lyt0112.com/projects/ConTrack.
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。