SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation

2025-05-30

AI Summary

In autonomous driving closed-loop trajectory planning, rule-based methods suffer from poor generalization, while learning-based approaches lack real-time performance and interpretability—especially degrading sharply in long-tail scenarios. To address these challenges, this paper proposes a scene-adaptive hybrid planning framework. Our method integrates lightweight rule-based components with deep learning planners via a novel dual-timescale decision neuron; introduces a scene-aware hybrid architecture coupled with a diffusion-guided proposal number modulation mechanism; and incorporates a trajectory fusion module to ensure both robustness and low latency (<50 ms). Evaluated on the interPlan benchmark, our framework achieves state-of-the-art performance, with significantly improved generalization in long-tail scenarios and no appreciable increase in computational overhead.

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

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Reliable planning is crucial for achieving autonomous driving. Rule-based planners are efficient but lack generalization, while learning-based planners excel in generalization yet have limitations in real-time performance and interpretability. In long-tail scenarios, these challenges make planning particularly difficult. To leverage the strengths of both rule-based and learning-based planners, we proposed the Scenario-Aware Hybrid Planner (SAH-Drive) for closed-loop vehicle trajectory planning. Inspired by human driving behavior, SAH-Drive combines a lightweight rule-based planner and a comprehensive learning-based planner, utilizing a dual-timescale decision neuron to determine the final trajectory. To enhance the computational efficiency and robustness of the hybrid planner, we also employed a diffusion proposal number regulator and a trajectory fusion module. The experimental results show that the proposed method significantly improves the generalization capability of the planning system, achieving state-of-the-art performance in interPlan, while maintaining computational efficiency without incurring substantial additional runtime.

Problem

• Combining rule-based and learning-based planners for autonomous driving
• Improving generalization and real-time performance in trajectory planning
• Addressing long-tail scenario challenges in closed-loop vehicle planning

Innovation

• Combines rule-based and learning-based planners
• Uses dual-timescale decision neuron
• Includes diffusion regulator and fusion module