A Decision-Making GPT Model Augmented with Entropy Regularization for Autonomous Vehicles

TL;DR

This paper introduces a GPT-based decision-making model for autonomous vehicles that uses entropy regularization to improve safety and exploration in complex environments, outperforming existing methods.

Contribution

The study presents a novel GPT-driven decision-making framework for AVs that integrates entropy regularization within a CMDP approach, enhancing safety and policy articulation.

Findings

Outperforms baseline methods in safety and efficacy

Enhances exploration through entropy regularization

Effective in complex autonomous driving scenarios

Abstract

In the domain of autonomous vehicles (AVs), decision-making is a critical factor that significantly influences the efficacy of autonomous navigation. As the field progresses, the enhancement of decision-making capabilities in complex environments has become a central area of research within data-driven methodologies. Despite notable advances, existing learning-based decision-making strategies in autonomous vehicles continue to reveal opportunities for further refinement, particularly in the articulation of policies and the assurance of safety. In this study, the decision-making challenges associated with autonomous vehicles are conceptualized through the framework of the Constrained Markov Decision Process (CMDP) and approached as a sequence modeling problem. Utilizing the Generative Pre-trained Transformer (GPT), we introduce a novel decision-making model tailored for AVs, which incorporates entropy regularization techniques to bolster exploration and enhance safety performance. Comprehensive experiments conducted across various scenarios affirm that our approach surpasses several established baseline methods, particularly in terms of safety and overall efficacy.