Preprint
Aug 2026
NeurRAFT: Robot Motion Planning via Anchor-Level Flow Matching with Clearance-Aware Preference Tuning
This work presents NeurRAFT, a generative planning framework based on anchor-level flow matching and clearance-aware preference tuning that operates on compact anchor waypoints, and directly reshape the pretrained planner's distribution toward safer solutions without augmenting inference.
Si-Bo Tian, Chang Liu, Ming-Hui Zheng et al.
· 0 citations