Drive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized Driving
TL;DR
M-Diffusion Planner is proposed with a dual-decoupling design: separating intent understanding from trajectory planning, and general planning capability learning from strategy alignment, to mitigate degradation of pretrained planning capabilities.
Abstract
Personalized autonomous driving requires understanding the driving needs implicit in user requests. This is challenging when driving demonstrations lack style annotations and behavioral adaptation risks degrading planning quality. We propose M-Diffusion Planner with a dual-decoupling design: separating intent understanding from trajectory planning, and general planning capability learning from strategy alignment. A large language model infers driving needs and selects a strategy, which is executed by the corresponding head of a shared diffusion planner. Following imitation pretraining, strategy-specific rewards specialize individual heads without style annotations. We innovatively adapt Group Relative Policy Optimization using surrogate policy-ratio estimation and constrained head-specific updates to mitigate degradation of pretrained planning capabilities. Open-loop and closed-loop evaluations on nuPlan demonstrate distinct strategy-aligned behaviors and competitive planning performance. Further experiments assess intent-to-strategy mapping and collision risk, and analyze the effects of reward design and optimization on strategy alignment and planning quality.
