aiqbench analysis
The paper applies flow-matching generative models to real-time trajectory planning for a robot facing an adversarial pursuer. Instead of regenerating full trajectories, it edits the remaining plan with FlowEdit and falls back to a control barrier function safety filter near danger, reporting lower compute time at a comparable success rate. For ML readers, the main question is whether generative trajectory models can be made fast and safe enough for closed-loop control; the evidence so far is limited to 2D simulations with static obstacles.
TrajEdit: Real-Time Flow-Matching Trajectory Adaptation via FlowEdit and CBF Safety Filter
arXiv:2610.24256v1 Announce Type: new Abstract: Safe, real-time motion planning is especially difficult when a dynamic obstacle actively pursues the ego agent, requiring rapid adaptation as the environment changes. We present TrajEdit, a hierarchical trajectory planner for pursuit-evasion that combines flow matching, trajectory editing, and safety filtering. Rather than regenerating trajectories from scratch at every step, TrajEdit follows the current plan under nominal conditions and adapts its remaining portion through FlowEdit as the pursuer approaches, and falls back to a control barrier function safety filter if the adversarial agent is within a safety threshold. Our use of FlowEdit for trajectory editing reduces computation time while maintaining a comparable success rate. We evaluate TrajEdit in 2D pursuit-evasion with static obstacles and an adversarial pursuer, demonstrating high success rates with low capture and collision rates, while achieving computational time savings over full replanning baselines.
Abstract:Safe, real-time motion planning is especially difficult when a dynamic obstacle actively pursues the ego agent, requiring rapid adaptation as the environment changes. We present TrajEdit, a hierarchical trajectory planner for pursuit-evasion that combines flow matching, trajectory editing, and safety filtering. Rather than regenerating trajectories from scratch at every step, TrajEdit follows the current plan under nominal conditions and adapts its remaining portion through FlowEdit as the pursuer approaches, and falls back to a control barrier function safety filter if the adversarial agent is within a safety threshold. Our use of FlowEdit for trajectory editing reduces computation time while maintaining a comparable success rate. We evaluate TrajEdit in 2D pursuit-evasion with static obstacles and an adversarial pursuer, demonstrating high success rates with low capture and collision rates, while achieving computational time savings over full replanning baselines.
Robotics (cs.RO)
arXiv:2610.24256 [cs.RO]
(or arXiv:2610.24256v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.24256 Focus to learn more arXiv-issued DOI via DataCite
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.
Full text under the publisher's open licence · 227 words