LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Can, Ma, Yunsheng, Park, Sung-Yeon, Yang, Zichong, Zhou, Yupeng, Liu, Peiran, Lu, Juanwu, Peng, Juntong, Zhang, Jiaru, Zhang, Ruqi, Li, Lingxi, Chen, Yaobin, Panchal, Jitesh H., Abdelraouf, Amr, Gupta, Rohit, Han, Kyungtae, Wang, Ziran
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914423292035072
author Cui, Can
Ma, Yunsheng
Park, Sung-Yeon
Yang, Zichong
Zhou, Yupeng
Liu, Peiran
Lu, Juanwu
Peng, Juntong
Zhang, Jiaru
Zhang, Ruqi
Li, Lingxi
Chen, Yaobin
Panchal, Jitesh H.
Abdelraouf, Amr
Gupta, Rohit
Han, Kyungtae
Wang, Ziran
author_facet Cui, Can
Ma, Yunsheng
Park, Sung-Yeon
Yang, Zichong
Zhou, Yupeng
Liu, Peiran
Lu, Juanwu
Peng, Juntong
Zhang, Jiaru
Zhang, Ruqi
Li, Lingxi
Chen, Yaobin
Panchal, Jitesh H.
Abdelraouf, Amr
Gupta, Rohit
Han, Kyungtae
Wang, Ziran
contents With the broader adoption and highly successful development of Large Language Models (LLMs), there has been growing interest and demand for applying LLMs to autonomous driving technology. Driven by their natural language understanding and reasoning capabilities, LLMs have the potential to enhance various aspects of autonomous driving systems, from perception and scene understanding to interactive decision-making. This paper first introduces the novel concept of designing Large Language Models for Autonomous Driving (LLM4AD), followed by a review of existing LLM4AD studies. Then, a comprehensive benchmark is proposed for evaluating the instruction-following and reasoning abilities of LLM4AD systems, which includes LaMPilot-Bench, CARLA Leaderboard 1.0 Benchmark in simulation and NuPlanQA for multi-view visual question answering. Furthermore, extensive real-world experiments are conducted on autonomous vehicle platforms, examining both on-cloud and on-edge LLM deployment for personalized decision-making and motion control. Next, the future trends of integrating language diffusion models into autonomous driving are explored, exemplified by the proposed ViLaD (Vision-Language Diffusion) framework. Finally, the main challenges of LLM4AD are discussed, including latency, deployment, security and privacy, safety, trust and transparency, and personalization.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15281
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends
Cui, Can
Ma, Yunsheng
Park, Sung-Yeon
Yang, Zichong
Zhou, Yupeng
Liu, Peiran
Lu, Juanwu
Peng, Juntong
Zhang, Jiaru
Zhang, Ruqi
Li, Lingxi
Chen, Yaobin
Panchal, Jitesh H.
Abdelraouf, Amr
Gupta, Rohit
Han, Kyungtae
Wang, Ziran
Robotics
Artificial Intelligence
Computation and Language
Human-Computer Interaction
With the broader adoption and highly successful development of Large Language Models (LLMs), there has been growing interest and demand for applying LLMs to autonomous driving technology. Driven by their natural language understanding and reasoning capabilities, LLMs have the potential to enhance various aspects of autonomous driving systems, from perception and scene understanding to interactive decision-making. This paper first introduces the novel concept of designing Large Language Models for Autonomous Driving (LLM4AD), followed by a review of existing LLM4AD studies. Then, a comprehensive benchmark is proposed for evaluating the instruction-following and reasoning abilities of LLM4AD systems, which includes LaMPilot-Bench, CARLA Leaderboard 1.0 Benchmark in simulation and NuPlanQA for multi-view visual question answering. Furthermore, extensive real-world experiments are conducted on autonomous vehicle platforms, examining both on-cloud and on-edge LLM deployment for personalized decision-making and motion control. Next, the future trends of integrating language diffusion models into autonomous driving are explored, exemplified by the proposed ViLaD (Vision-Language Diffusion) framework. Finally, the main challenges of LLM4AD are discussed, including latency, deployment, security and privacy, safety, trust and transparency, and personalization.
title LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends
topic Robotics
Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2410.15281