EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model

Yi Chen, Chengzhe Li, Qirui Yuan, Jinyu Li iD, Yuze Fan iD, Xiaojun Ge iD, Yun Li iD, Fei Gao iD, Rui Zhao iD

Sensors · 25.12.2024 · 25 (1) · 64

DOI: 10.3390/s25010064 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.12.2024. Verfasst von Yi Chen und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Automotive Engineering, Jilin University, Changchun 130025, China. Hauptthemen laut MEDLINE: Automobile Driving, Intention. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Development Project of Jilin Province, National Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The cockpit is evolving from passive, reactive interaction toward proactive, cognitive interaction, making precise predictions of driver intent a key factor in enhancing proactive interaction experiences. This paper introduces Cockpit-Llama, a novel language model specifically designed for predicting driver behavior intent. Cockpit-Llama predicts driver intent based on the relationship between current driver actions, historical interactions, and the states of the driver and cockpit environment, thereby supporting further proactive interaction decisions. To improve the accuracy and rationality of Cockpit-Llama’s predictions, we construct a new multi-attribute cockpit dataset that includes extensive historical interactions and multi-attribute states, such as driver emotional states, driving activity scenarios, vehicle motion states, body states and external environment, to support the fine-tuning of Cockpit-Llama. During fine-tuning, we adopt the Low-Rank Adaptation (LoRA) method to efficiently optimize the parameters of the Llama3-8b-Instruct model, significantly reducing training costs. Extensive experiments on the multi-attribute cockpit dataset demonstrate that Cockpit-Llama’s prediction performance surpasses other advanced methods, achieving BLEU-4, ROUGE-1, ROUGE-2, and ROUGE-L scores of 71.32, 80.01, 76.89, and 81.42, respectively, with relative improvements of 92.34%, 183.61%, 95.54%, and 201.27% compared to ChatGPT-4. This significantly enhances the reasoning and interpretative capabilities of intelligent cockpits.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Automobile DrivingIntentionHumansAlgorithmsLarge Language Models

Stichwörter der Autor:innen

human–machine interactionintelligent cockpitintent predictionlarge language model

Autor:innen und Institutionen

  • College of Automotive Engineering, Jilin University, Changchun 130025, China.
  • Graduate School of Information and Science Technology, The University of Tokyo, Tokyo 113-8654, Japan.
  • National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun 130025, China.

ORCID-Profile: Jinyu Li, Yuze Fan, Xiaojun Ge, Yun Li, Fei Gao, Rui Zhao

Förderung

  • Science and Technology Development Project of Jilin Province
  • National Science Foundation of China

Zitieren

APA

Chen, Y., Li, C., Yuan, Q., Li, J., Fan, Y., Ge, X., Li, Y., Gao, F., & Zhao, R. (2024). Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model. Sensors, 25(1), 64. https://doi.org/10.3390/s25010064

Vancouver

Chen Y, Li C, Yuan Q, Li J, Fan Y, Ge X, et al. Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model. Sensors. 2024;25(1):64. doi:10.3390/s25010064

BibTeX
@article{Chen2024,
  author = {Chen, Yi and Li, Chengzhe and Yuan, Qirui and Li, Jinyu and Fan, Yuze and Ge, Xiaojun and Li, Yun and Gao, Fei and Zhao, Rui},
  title = {Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model},
  journal = {Sensors},
  year = {2024},
  volume = {25},
  number = {1},
  pages = {64},
  doi = {10.3390/s25010064}
}
Kostenlos starten →