ManeuverFlow: Maneuver Hypothesis Generation with Future Evidence for Trajectory Evaluation and Refinement in End-to-End Autonomous Driving

Key points

• End-to-end planning in complex scenes must model diverse driving intentions and select the most appropriate trajectory using scene context and future risks.1
• However, multi-query regression may collapse to one mode, while anchor-based and generative planners share a scaling bottleneck: small candidate sets limit maneuver coverage or discovery of high-quality trajectories, whereas large sets increase generation and scoring costs.1
• The model selects relevant maneuver modes, draws corresponding noise from the Gaussian mixture prior, and maps it to intention-specific trajectories through a maneuver-routed mixture-of-experts MeanFlow field.1
• With a lightweight TransFuser-style ResNet-34 backbone, ManeuverFlow achieves 90.6 PDMS and 90.1 EPDMS on NAVSIM v1/v2 navtest, respectively.1

Sources (1)

• [1]ManeuverFlow: Maneuver Hypothesis Generation with Future Evidence for Trajectory Evaluation and Refinement in End-to-End Autonomous Driving
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 11:20 AM

  We propose ManeuverFlow to generate trajectories for distinct intentions in one step and evaluate and refine them using current and future evidence.

  End-to-end planning in complex scenes must model diverse driving intentions and select the most appropriate trajectory using scene context and future risks.

Extractive summary: sentences quoted from the sources.