A Neuro-Symbolic Framework Combining Inductive and Deductive Reasoning for Autonomous Driving Planning

원문 초록

Existing end-to-end autonomous driving models rely heavily on purely data-driven inductive reasoning. This "black-box" nature limits interpretability and makes safety-critical planning challenging in complex, long-tail scenarios. To overcome this bottleneck, we propose a novel neuro-symbolic trajectory planning (NS-Plan) framework, which integrates rigorous deductive reasoning into end-to-end neural networks. Specifically, our framework utilizes a Large Language Model (LLM) to dynamically extract scene rules and employs an Answer Set Programming (ASP) solver for deterministic logical arbitration, generating logically consistent and traceable discrete driving decisions. To bridge the gap between discrete symbols and continuous trajectories, we introduce a decision-conditioned decoding mechanism that transforms high-level logical decisions into learnable embedding vectors, simultaneously constraining the planning query and the physical initial velocity of a differentiable Kinematic Bicycle Model (KBM). By combining KBM-generated baseline trajectories with neural residual corrections, our approach uses the KBM to guide trajectory generation while keeping the decision-making process traceable. On the nuScenes benchmark, our method (NS-Plan) comprehensively outperforms state-of-the-art baselines, reducing the average $L_2$ error by 18.3% (to 0.49 m), the collision rate by 22.2% (to 0.07%), and improving the trajectory prediction consistency (TPC) by 13% (to 0.47 m) compared to MomAD. More importantly, in the complex Turning-nuScenes subset, our method reduces the collision rate by 78.1% (to 0.07%) over the baseline.