DAP: A Discrete-token Autoregressive Planner for Autonomous Driving
Gaining sustainable performance improvement with scaling data and model budget remains a pivotal yet unresolved challenge in autonomous driving. While autoregressive models exhibited promising data-scaling efficiency in planning tasks, predicting ego trajectories alone suffers sparse supervision and weakly constrains how scene evolution should shape ego motion. Therefore, we introduce DAP, a discrete-token autoregressive planner that jointly forecasts BEV semantics and ego trajectories, thereby enforcing comprehensive representation learning and allowing predicted dynamics to directly condition ego motion. In addition, we incorporate a reinforcement-learning-based fine-tuning, which preserves supervised behavior cloning priors while injecting reward-guided improvements. Despite a compact 160M parameter budget, DAP achieves state-of-the-art performance on open-loop metrics and delivers competitive closed-loop results on the NAVSIM benchmark. Overall, the fully discrete-token autoregressive formulation operating on both rasterized BEV and ego actions provides a compact yet scalable planning paradigm for autonomous driving.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningAutonomous DrivingSimilar Papers 제목 키워드 기반
Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion
Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged as promising candidates for end-to-end autonomous driving. However, these models typically face challenges in inference latency, action precisio…
Autonomous DrivingCorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
Autonomous driving requires safe planning, but most learning-based planners lack explicit self-correction ability: once an unsafe action is proposed, there is no mechanism to correct it. Thus, we propose CorrectionPlanne…
Reinforcement LearningAutonomous DrivingTractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
Significant progress has been made in training multimodal trajectory forecasting models for autonomous driving. However, effectively integrating these models with downstream planners and model-based control approaches is…
Autonomous DrivingTrajectory ForecastingTrajectory PredictionDoe-1: Closed-Loop Autonomous Driving with Large World Model
End-to-end autonomous driving has received increasing attention due to its potential to learn from large amounts of data. However, most existing methods are still open-loop and suffer from weak scalability, lack of high-…
Autonomous DrivingDecision MakingMotion PlanningQuestion Answering+2Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving
Scaling end-to-end autonomous driving to complex, open-world environments requires perceptual models that generalize to anomalous scenarios and planners that produce kinematically valid trajectories. Existing paradigms f…
Collision AvoidanceAutonomous Driving