LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulation
For robotic manipulation, this work improves the reliability of diffusion policies in asynchronous real-world deployment by reducing jerky motions and collisions.
LAGO Policy addresses inter-chunk discontinuities and collision issues in diffusion-based visuomotor policies by integrating latency-aware guidance and trajectory optimization, achieving smooth and safe manipulation with high task success in real-world experiments.
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/