A Knowledge-Driven Diffusion Policy for End-to-End Autonomous Driving Based on Expert Routing
This addresses the challenge of producing consistent and generalizable driving behaviors across diverse scenarios for autonomous vehicles, representing a novel method rather than an incremental improvement.
The paper tackled the problem of adaptive, robust, and interpretable decision-making in end-to-end autonomous driving by proposing KDP, a knowledge-driven diffusion policy with expert routing, which achieved higher success rates, reduced collision risk, and smoother control in experiments.
End-to-end autonomous driving remains constrained by the difficulty of producing adaptive, robust, and interpretable decision-making across diverse scenarios. Existing methods often collapse diverse driving behaviors, lack long-horizon consistency, or require task-specific engineering that limits generalization. This paper presents KDP, a knowledge-driven diffusion policy that integrates generative diffusion modeling with a sparse mixture-of-experts routing mechanism. The diffusion component generates temporally coherent action sequences, while the expert routing mechanism activates specialized and reusable experts according to context, enabling modular knowledge composition. Extensive experiments across representative driving scenarios demonstrate that KDP achieves consistently higher success rates, reduced collision risk, and smoother control compared to prevailing paradigms. Ablation studies highlight the effectiveness of sparse expert activation and the Transformer backbone, and activation analyses reveal structured specialization and cross-scenario reuse of experts. These results establish diffusion with expert routing as a scalable and interpretable paradigm for knowledge-driven end-to-end autonomous driving.