让机器人动作既自然又可执行，直接生成符合物理规律的全身运动轨迹。
Shooting for Contact: Contact-Implicit Multiple Shooting for Dynamic Motion Retargeting
- 用可微仿真器嵌入非线性规划，自动处理接触与碰撞问题。
- 在单位兔G1上实现零样本仿真到现实的动态跳跃转身和爬行。
- 适合需要高动态、强接触交互的机器人动作生成任务。
现有运动重定向方法常侧重运动学相似性，忽视全身动力学、接触一致性与执行器限制，导致强化学习策略难以复现，尤其在富含接触的行为中。本文提出一种接触隐式、基于直接模拟的多打靶（DSMS）框架，将运动学可行的参考轨迹转化为动力学可行的全身运动轨迹。通过在非线性规划中嵌入可微仿真器，DSMS 内部处理接触、摩擦、冲击、自碰撞与关节限位，同时满足跟踪、执行与任务约束，无需预设接触序列或显式接触约束。相比现有方法，DSMS 加速了运动模仿强化学习训练，生成策略成功率高、跟踪误差低。我们进一步在 Unitree G1 上验证了零样本仿真到现实的迁移效果，实现了命令控制下的接触丰富爬行及高度动态的 180 度跳转动作。
原文摘要 · Abstract (English)
Motion retargeting approaches often prioritize kinematic similarity over whole-body dynamics, contact consistency, and actuation limits, yielding references that are difficult for reinforcement learning (RL) policies to reproduce, particularly for contact-rich behaviors. We present a contact-implicit, direct simulation-based multiple shooting (DSMS) framework that transforms kinematically feasible references into dynamically feasible whole-body trajectories. By embedding a differentiable simulator within a nonlinear program, DSMS resolves contact, friction, impacts, self-collision, and joint limits internally while enforcing tracking, actuation, and task constraints without prescribing a contact schedule or introducing explicit contact constraints. Compared with existing retargeting methods, DSMS accelerates motion-imitation RL training and yields policies with high success rates and low tracking error. We further demonstrate zero-shot sim-to-real transfer on the Unitree G1 through command-conditioned contact-rich crawling and a highly dynamic 180-degree jump-turn.
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。