Event
A navigation framework combining flow matching and model predictive control is proposed
1 reports · 1 sources
Philipp Holzmann et al. propose a safe navigation framework for mobile robots that combines flow-matching-based path planning with model predictive path-following control: the flow matching model captures multimodal path distributions, the predictive controller uses the latest local sensor information to satisfy state and input constraints online and avoid obstacles, and event-triggered replanning feeds control solutions back into subsequent path generation to handle previously unseen obstacles. The method has so far been validated only in simulation, with results showing it performs robustly in cluttered environments.
Report timeline
- Robot Safe Navigation Framework Combining Flow Matching and Model Predictive Control
This framework combines flow-matching-based path planning with model predictive path-following control for mobile robot navigation. The flow matching model captures multimodal path distributions, while the predictive controller satisfies state and input constraints online and avoids obstacles, and event-triggered replanning feeds control solutions back into subsequent path generation. Simulation results show that the framework performs robustly in cluttered environments.
arXiv cs.RO ·