Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic Environment

TL;DR

This paper introduces DADRL, a lightweight reinforcement learning framework with attention mechanisms for autonomous vehicle decision-making in dynamic urban environments, achieving high performance without complex transformer architectures.

Contribution

The paper presents a novel attention-based reinforcement learning approach that efficiently encodes spatiotemporal interactions for autonomous driving, reducing computational complexity.

Findings

DADRL outperforms recent state-of-the-art methods on SMARTS urban scenarios.

The spatiotemporal attention encoder significantly improves decision-making accuracy.

The context encoder enhances understanding of map and route information.

Abstract

Autonomous Vehicle (AV) decision making in urban environments is inherently challenging due to the dynamic interactions with surrounding vehicles. For safe planning, AV must understand the weightage of various spatiotemporal interactions in a scene. Contemporary works use colossal transformer architectures to encode interactions mainly for trajectory prediction, resulting in increased computational complexity. To address this issue without compromising spatiotemporal understanding and performance, we propose the simple Deep Attention Driven Reinforcement Learning (DADRL) framework, which dynamically assigns and incorporates the significance of surrounding vehicles into the ego's RL driven decision making process. We introduce an AV centric spatiotemporal attention encoding (STAE) mechanism for learning the dynamic interactions with different surrounding vehicles. To understand map and route context, we employ a context encoder to extract features from context maps. The spatiotemporal representations combined with contextual encoding provide a comprehensive state representation. The resulting model is trained using the Soft Actor Critic (SAC) algorithm. We evaluate the proposed framework on the SMARTS urban benchmarking scenarios without traffic signals to demonstrate that DADRL outperforms recent state of the art methods. Furthermore, an ablation study underscores the importance of the context-encoder and spatio temporal attention encoder in achieving superior performance.