Safe and Stylized Trajectory Planning for Autonomous Driving via Diffusion Model

Achieving safe and stylized trajectory planning in complex real-world scenarios remains a critical challenge for autonomous driving systems. This paper proposes the Stylish Diffusion Drive (SDD) Planner, a diffusion-based framework that explicitly reconciles safety constraints with personalized driving styles in real time. 1) A Multi-Source Style-Aware Encoder that uses distance-sensitive attention to fuse dynamic agents and scene context, enabling joint perception of safety and driving style. 2) A Style-Guided Dynamic Trajectory Generator that applies adaptive safety–style guidance during the diffusion denoising process and integrates a feasibility-oriented post-processing stage to produce user-preferred and physically executable trajectories. Extensive experiments demonstrate the effectiveness of SDD Planner. On the StyleDrive benchmark, it improves the SMPDMS metric by 3.91 points over the strongest baseline. On the NuPlan Test14 and Test14-hard benchmarks, SDD Planner ranks first with overall scores of 91.76 and 80.32, respectively, outperforming strong planning baselines such as PLUTO. Additional robustness and ablation studies further confirm the effectiveness of the proposed hyper-parameter design, learnable distance-sensitive attention, and cost-based trajectory selection. We further conduct a deployment-oriented study using a distilled variant on an NVIDIA Orin platform. With DDIM fast sampling and mixed-precision execution, the planner achieves an end-to-end latency of approximately 93 ms. This result indicates its practical executability under onboard runtime constraints.