Adaptive Decision Making at the Intersection for Autonomous Vehicles Based on Skill Discovery

TL;DR

This paper introduces a hierarchical reinforcement learning framework that combines motion primitives to enable autonomous vehicles to adaptively make decisions at intersections, reusing knowledge across scenarios for improved safety and efficiency.

Contribution

It presents a novel HRL-based approach integrating motion primitives for adaptive decision making, addressing knowledge reuse in uncertain intersection environments.

Findings

Proposed method outperforms baseline methods in CARLA simulations.

Hierarchical framework effectively decomposes complex intersection tasks.

Method demonstrates robust knowledge reuse across different scenarios.

Abstract

In urban environments, the complex and uncertain intersection scenarios are challenging for autonomous driving. To ensure safety, it is crucial to develop an adaptive decision making system that can handle the interaction with other vehicles. Manually designed model-based methods are reliable in common scenarios. But in uncertain environments, they are not reliable, so learning-based methods are proposed, especially reinforcement learning (RL) methods. However, current RL methods need retraining when the scenarios change. In other words, current RL methods cannot reuse accumulated knowledge. They forget learned knowledge when new scenarios are given. To solve this problem, we propose a hierarchical framework that can autonomously accumulate and reuse knowledge. The proposed method combines the idea of motion primitives (MPs) with hierarchical reinforcement learning (HRL). It decomposes complex problems into multiple basic subtasks to reduce the difficulty. The proposed method and other baseline methods are tested in a challenging intersection scenario based on the CARLA simulator. The intersection scenario contains three different subtasks that can reflect the complexity and uncertainty of real traffic flow. After offline learning and testing, the proposed method is proved to have the best performance among all methods.