Parameterized Decision-making with Multi-modal Perception for Autonomous Driving

TL;DR

This paper introduces AUTO, a deep reinforcement learning framework for autonomous driving that integrates multi-modal perception and parameterized actions to improve decision-making, safety, and efficiency in complex traffic environments.

Contribution

It proposes a novel parameterized decision-making framework with multi-modal perception and a graph-based state representation for autonomous vehicles.

Findings

AUTO outperforms existing methods in safety and efficiency metrics.

The framework effectively distinguishes lane-following and lane-changing behaviors.

Experimental results demonstrate improved adaptability in complex traffic scenarios.

Abstract

Autonomous driving is an emerging technology that has advanced rapidly over the last decade. Modern transportation is expected to benefit greatly from a wise decision-making framework of autonomous vehicles, including the improvement of mobility and the minimization of risks and travel time. However, existing methods either ignore the complexity of environments only fitting straight roads, or ignore the impact on surrounding vehicles during optimization phases, leading to weak environmental adaptability and incomplete optimization objectives. To address these limitations, we propose a parameterized decision-making framework with multi-modal perception based on deep reinforcement learning, called AUTO. We conduct a comprehensive perception to capture the state features of various traffic participants around the autonomous vehicle, based on which we design a graph-based model to learn a state representation of the multi-modal semantic features. To distinguish between lane-following and lane-changing, we decompose an action of the autonomous vehicle into a parameterized action structure that first decides whether to change lanes and then computes an exact action to execute. A hybrid reward function takes into account aspects of safety, traffic efficiency, passenger comfort, and impact to guide the framework to generate optimal actions. In addition, we design a regularization term and a multi-worker paradigm to enhance the training. Extensive experiments offer evidence that AUTO can advance state-of-the-art in terms of both macroscopic and microscopic effectiveness.