LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharan, S P, Pittaluga, Francesco, G, Vijay Kumar B, Chandraker, Manmohan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929195595071488
author Sharan, S P
Pittaluga, Francesco
G, Vijay Kumar B
Chandraker, Manmohan
author_facet Sharan, S P
Pittaluga, Francesco
G, Vijay Kumar B
Chandraker, Manmohan
contents Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer from overfitting and poor long-tail performance. On the other hand, rule-based planners generalize well, but might fail to handle scenarios that require complex driving maneuvers. To address these limitations, we investigate the possibility of leveraging the common-sense reasoning capabilities of Large Language Models (LLMs) such as GPT4 and Llama2 to generate plans for self-driving vehicles. In particular, we develop a novel hybrid planner that leverages a conventional rule-based planner in conjunction with an LLM-based planner. Guided by commonsense reasoning abilities of LLMs, our approach navigates complex scenarios which existing planners struggle with, produces well-reasoned outputs while also remaining grounded through working alongside the rule-based approach. Through extensive evaluation on the nuPlan benchmark, we achieve state-of-the-art performance, outperforming all existing pure learning- and rule-based methods across most metrics. Our code will be available at https://llmassist.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2401_00125
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning
Sharan, S P
Pittaluga, Francesco
G, Vijay Kumar B
Chandraker, Manmohan
Artificial Intelligence
Computer Vision and Pattern Recognition
Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer from overfitting and poor long-tail performance. On the other hand, rule-based planners generalize well, but might fail to handle scenarios that require complex driving maneuvers. To address these limitations, we investigate the possibility of leveraging the common-sense reasoning capabilities of Large Language Models (LLMs) such as GPT4 and Llama2 to generate plans for self-driving vehicles. In particular, we develop a novel hybrid planner that leverages a conventional rule-based planner in conjunction with an LLM-based planner. Guided by commonsense reasoning abilities of LLMs, our approach navigates complex scenarios which existing planners struggle with, produces well-reasoned outputs while also remaining grounded through working alongside the rule-based approach. Through extensive evaluation on the nuPlan benchmark, we achieve state-of-the-art performance, outperforming all existing pure learning- and rule-based methods across most metrics. Our code will be available at https://llmassist.github.io.
title LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning
topic Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.00125