Safe and Stylized Trajectory Planning for Autonomous Driving via Diffusion Model

2026-02-04

AI Summary

This work addresses the challenge of generating safe and preference-aware driving trajectories in complex real-world scenarios by proposing SDD Planner, the first diffusion-based framework for real-time trajectory planning. The method integrates a style-aware encoder and a dynamic weight modulation mechanism, leveraging distance-sensitive attention and multi-source heterogeneous environmental information to jointly optimize safety constraints and personalized driving styles during the denoising process. Experimental results demonstrate that SDD Planner improves the SM-PDMS metric by 3.9% on StyleDrive and achieves state-of-the-art scores of 91.76 and 80.32 on NuPlan Test14 and Test14-hard, respectively. Furthermore, closed-loop real-vehicle tests confirm its practical deployability in real-world autonomous driving systems.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Achieving safe and stylized trajectory planning in complex real-world scenarios remains a critical challenge for autonomous driving systems. This paper proposes the SDD Planner, a diffusion-based framework designed to effectively reconcile safety constraints with driving styles in real time. The framework integrates two core modules: a Multi-Source Style-Aware Encoder, which employs distance-sensitive attention to fuse dynamic agent data and environmental contexts for heterogeneous safety-style perception; and a Style-Guided Dynamic Trajectory Generator, which adaptively modulates priority weights within the diffusion denoising process to generate user-preferred yet safe trajectories. Extensive experiments demonstrate that SDD Planner achieves state-of-the-art performance. On the StyleDrive benchmark, it improves the SM-PDMS metric by 3.9% over WoTE, the strongest baseline. Furthermore, on the NuPlan Test14 and Test14-hard benchmarks, SDD Planner ranks first with overall scores of 91.76 and 80.32, respectively, outperforming leading methods such as PLUTO. Real-vehicle closed-loop tests further confirm that SDD Planner maintains high safety standards while aligning with preset driving styles, validating its practical applicability for real-world deployment.

Problem

• trajectory planning
• autonomous driving
• safety
• driving style
• diffusion model

Innovation

• Diffusion Model
• Trajectory Planning
• Driving Style
• Safety Constraints
• Style-Guided Generation