Empowering Autonomous Driving with Large Language Models: A Safety Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yixuan, Jiao, Ruochen, Zhan, Sinong Simon, Lang, Chengtian, Huang, Chao, Wang, Zhaoran, Yang, Zhuoran, Zhu, Qi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909145888718848
author Wang, Yixuan
Jiao, Ruochen
Zhan, Sinong Simon
Lang, Chengtian
Huang, Chao
Wang, Zhaoran
Yang, Zhuoran
Zhu, Qi
author_facet Wang, Yixuan
Jiao, Ruochen
Zhan, Sinong Simon
Lang, Chengtian
Huang, Chao
Wang, Zhaoran
Yang, Zhuoran
Zhu, Qi
contents Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly in out-of-distribution and uncertain data. To this end, this paper explores the integration of Large Language Models (LLMs) into AD systems, leveraging their robust common-sense knowledge and reasoning abilities. The proposed methodologies employ LLMs as intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning, for enhancing driving performance and safety. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine. Demonstrating superior performance and safety metrics compared to state-of-the-art approaches, our approach shows the promising potential for using LLMs for autonomous vehicles.
format Preprint
id arxiv_https___arxiv_org_abs_2312_00812
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Empowering Autonomous Driving with Large Language Models: A Safety Perspective
Wang, Yixuan
Jiao, Ruochen
Zhan, Sinong Simon
Lang, Chengtian
Huang, Chao
Wang, Zhaoran
Yang, Zhuoran
Zhu, Qi
Artificial Intelligence
Machine Learning
Systems and Control
Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly in out-of-distribution and uncertain data. To this end, this paper explores the integration of Large Language Models (LLMs) into AD systems, leveraging their robust common-sense knowledge and reasoning abilities. The proposed methodologies employ LLMs as intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning, for enhancing driving performance and safety. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine. Demonstrating superior performance and safety metrics compared to state-of-the-art approaches, our approach shows the promising potential for using LLMs for autonomous vehicles.
title Empowering Autonomous Driving with Large Language Models: A Safety Perspective
topic Artificial Intelligence
Machine Learning
Systems and Control
url https://arxiv.org/abs/2312.00812