analiza aiqbench
LAGO Policy addresses critical stability issues in diffusion-based robotic control by integrating latency-aware guidance with trajectory optimization to ensure smooth, collision-free manipulation. This research advances the practical deployment of asynchronous inference models in real-world scenarios where inter-chunk discontinuities previously hindered reliable execution. By predicting task-relevant goals and refining actions for low-jerk motion, it bridges a significant gap between theoretical AI policies and robust physical interaction.
LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulation
arXiv:2606.17982v1 Announce Type: new Abstract: 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/
Abstract: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: this https URL
Robotics (cs.RO)
arXiv:2606.17982 [cs.RO]
(or arXiv:2606.17982v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.17982 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 216 cuvinte
Subiecte conexe
Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion
arXiv · 21 iul. 2026
Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies
arXiv · 29 sept. 2026
Chronos Policy: Learning Robot Policies on Physical Time
arXiv · 12 oct. 2026
Implementing and Evaluating a Basic Per-Action Monitor for Safer Evals
METR · 27 sept. 2026