Problem
Research questions and friction points this paper is trying to address.
end-to-end autonomous driving
future state modeling
trajectory generation
scene evolution
FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving
🤖 AI Summary
为解决自动驾驶中未来轨迹随场景变化的有效性问题，提出FeasibleFlow框架，通过联合传输可行性和轨迹，并引入安全机制来生成更安全的行驶路径。
📝 Abstract
End-to-end autonomous driving maps current observations directly to future trajectories, yet those trajectories must remain valid as the scene evolves. Future state modeling aims to address this temporal mismatch, but general representations often contain information unrelated to ego planning and affect trajectory generation only through auxiliary supervision, static conditioning, or proposal evaluation. We propose FeasibleFlow, a one-step end-to-end generative framework that jointly transports a configuration-space feasibility field and multimodal ego trajectories. Our Asymmetric Joint MeanFlow uses the pathwise Jacobian-vector product in the MeanFlow identity to incorporate field evolution into trajectory transport. Because safety feedback is sparser than progress feedback, we further introduce the Anchor-relative ranker (ARR) and Pareto-ReinFlow to balance safety and progress in candidate selection and generation, respectively. Experiments on the NAVSIM benchmark demonstrate the strong performance of FeasibleFlow and validate both the joint transport of feasibility and trajectories and the proposed safety-first mechanisms.
Innovation
Methods, ideas, or system contributions that make the work stand out.
FeasibleFlow
Asymmetric Joint MeanFlow
Anchor-relative ranker (ARR)
Pareto-ReinFlow
🔎 Similar Papers
No similar papers found.
