AI RESEARCH
Learning Direct Control Policies with Flow Matching for Autonomous Driving
arXiv CS.CV
•
ArXi:2605.14832v1 Announce Type: cross We present a flow-matching planner for autonomous driving that directly outputs actionable control trajectories defined by acceleration and curvature profiles. The model is conditioned on a bird's-eye-view (BEV) raster of the surrounding scene and generates control sequences in a small number of Ordinary Differential Equations (ODE) integration steps, enabling low-latency inference suitable for real-time closed-loop re-planning.