Exploring Large Language Models for Trajectory Prediction: A Technical Perspective

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)
332 Downloads (Pure)

Abstract

Large Language Models (LLMs) have been recently proposed for trajectory prediction in autonomous driving, where they potentially can provide explainable reasoning capability about driving situations. Most studies use versions of the OpenAI GPT, while there are open-source alternatives which have not been evaluated in this context. In this report1, we study their trajectory prediction performance as well as their ability to reason about the situation. Our results indicate that open-source alternatives are feasible for trajectory prediction. However, their ability to describe situations and reason about potential consequences of actions appears limited, and warrants future research.

Original languageEnglish
Title of host publicationHRI 2024 Companion - Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction
PublisherIEEE
Pages774-778
Number of pages5
ISBN (Electronic)979-8-4007-0323-2
DOIs
Publication statusPublished - 11 Mar 2024
MoE publication typeA4 Conference publication
EventACM/IEEE International Conference on Human-Robot Interaction - Boulder, United States
Duration: 11 Mar 202415 Mar 2024

Publication series

NameACM/IEEE International Conference on Human-Robot Interaction
ISSN (Electronic)2167-2148

Conference

ConferenceACM/IEEE International Conference on Human-Robot Interaction
Abbreviated titleHRI
Country/TerritoryUnited States
CityBoulder
Period11/03/202415/03/2024

Keywords

  • Autonomous Driving
  • Large Language Models
  • Trajectory Prediction

Fingerprint

Dive into the research topics of 'Exploring Large Language Models for Trajectory Prediction: A Technical Perspective'. Together they form a unique fingerprint.

Cite this