让机器人异步执行时更顺滑无碰撞，靠的是智能规划与动作优化结合。
LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulation
- 用未来动作预测引导扩散策略，缓解不同片段间的动作跳变。
- 从示范中学习任务目标，实现避障且指向目标的路径规划。
- 时空联合优化动作序列，降低抖动，提升真实场景执行成功率。
基于扩散模型的视觉运动策略在异步推理部署中常出现片段间不连续，且缺乏显式障碍物感知机制，导致动作僵硬甚至碰撞，影响真实场景下的可靠操作。为此，我们提出 LAGO Policy，一种统一的异步动作生成框架，将轨迹优化与扩散策略相结合，实现平滑安全执行。LAGO Policy 通过延迟感知的无分类器指导，以未来动作作为条件，提升片段间一致性；通过从示范中预测任务相关的交互目标，实现目标导向的避障轨迹规划；最后通过时空轨迹优化，生成低抖动且可行的动作序列。大量真实世界实验表明，LAGO Policy 在复杂操作任务中实现了平滑无碰撞的高成功率执行。项目网站：https://lago-policy.github.io/
原文摘要 · Abstract (English)
Diffusion-based visuomotor policies deployed with asynchronous inference often exhibit inter-chunk discontinuities and lack explicit mechanisms for obstacle-aware execution, leading to jerky motions and collisions that hinder reliable manipulation in real-world scenes. To address these issues, we propose LAGO Policy, a unified asynchronous action-generation framework that integrates trajectory optimization with diffusion policy for smooth and safe execution. LAGO Policy improves inter-chunk consistency via latency-aware classifier-free guidance conditioning on future actions. It further enables goal-directed collision-free trajectory planning by predicting a task-relevant interaction goal from demonstrations. Finally, spatial-temporal trajectory optimization refines the actions to be executed for low-jerk and feasible motion. Extensive real-world experiments demonstrate that LAGO Policy achieves smooth collision-free execution with high task success across challenging manipulation tasks. Project Website: https://lago-policy.github.io/
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。