DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Licheng, Fu, Daocheng, Li, Xin, Cai, Xinyu, Ma, Tao, Cai, Pinlong, Dou, Min, Shi, Botian, He, Liang, Qiao, Yu
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911781749784576
author Wen, Licheng
Fu, Daocheng
Li, Xin
Cai, Xinyu
Ma, Tao
Cai, Pinlong
Dou, Min
Shi, Botian
He, Liang
Qiao, Yu
author_facet Wen, Licheng
Fu, Daocheng
Li, Xin
Cai, Xinyu
Ma, Tao
Cai, Pinlong
Dou, Min
Shi, Botian
He, Liang
Qiao, Yu
contents Recent advancements in autonomous driving have relied on data-driven approaches, which are widely adopted but face challenges including dataset bias, overfitting, and uninterpretability. Drawing inspiration from the knowledge-driven nature of human driving, we explore the question of how to instill similar capabilities into autonomous driving systems and summarize a paradigm that integrates an interactive environment, a driver agent, as well as a memory component to address this question. Leveraging large language models (LLMs) with emergent abilities, we propose the DiLu framework, which combines a Reasoning and a Reflection module to enable the system to perform decision-making based on common-sense knowledge and evolve continuously. Extensive experiments prove DiLu's capability to accumulate experience and demonstrate a significant advantage in generalization ability over reinforcement learning-based methods. Moreover, DiLu is able to directly acquire experiences from real-world datasets which highlights its potential to be deployed on practical autonomous driving systems. To the best of our knowledge, we are the first to leverage knowledge-driven capability in decision-making for autonomous vehicles. Through the proposed DiLu framework, LLM is strengthened to apply knowledge and to reason causally in the autonomous driving domain. Project page: https://pjlab-adg.github.io/DiLu/
format Preprint
id arxiv_https___arxiv_org_abs_2309_16292
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
Wen, Licheng
Fu, Daocheng
Li, Xin
Cai, Xinyu
Ma, Tao
Cai, Pinlong
Dou, Min
Shi, Botian
He, Liang
Qiao, Yu
Robotics
Computation and Language
Recent advancements in autonomous driving have relied on data-driven approaches, which are widely adopted but face challenges including dataset bias, overfitting, and uninterpretability. Drawing inspiration from the knowledge-driven nature of human driving, we explore the question of how to instill similar capabilities into autonomous driving systems and summarize a paradigm that integrates an interactive environment, a driver agent, as well as a memory component to address this question. Leveraging large language models (LLMs) with emergent abilities, we propose the DiLu framework, which combines a Reasoning and a Reflection module to enable the system to perform decision-making based on common-sense knowledge and evolve continuously. Extensive experiments prove DiLu's capability to accumulate experience and demonstrate a significant advantage in generalization ability over reinforcement learning-based methods. Moreover, DiLu is able to directly acquire experiences from real-world datasets which highlights its potential to be deployed on practical autonomous driving systems. To the best of our knowledge, we are the first to leverage knowledge-driven capability in decision-making for autonomous vehicles. Through the proposed DiLu framework, LLM is strengthened to apply knowledge and to reason causally in the autonomous driving domain. Project page: https://pjlab-adg.github.io/DiLu/
title DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
topic Robotics
Computation and Language
url https://arxiv.org/abs/2309.16292