AI RESEARCH

ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation

arXiv CS.CV

ArXi:2604.01129v1 Announce Type: new We present ReinDriveGen, a framework that enables full controllability over dynamic driving scenes, allowing users to freely edit actor trajectories to simulate safety-critical corner cases such as front-vehicle collisions, drifting cars, vehicles spinning out of control, pedestrians jaywalking, and cyclists cutting across lanes. Our approach constructs a dynamic 3D point cloud scene from multi-frame LiDAR data,