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

TL;DR

SAH-Drive is a hybrid planning system for autonomous vehicles that combines rule-based and learning-based methods, inspired by human driving, to improve generalization, efficiency, and robustness in complex scenarios.

Contribution

This paper introduces SAH-Drive, a novel scenario-aware hybrid planner that integrates rule-based and learning-based components with a dual-timescale decision mechanism.

Findings

Achieves state-of-the-art performance in interPlan benchmarks.

Significantly improves generalization in diverse driving scenarios.

Maintains computational efficiency comparable to existing methods.

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.