Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model
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 predictin...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/64 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548980145618944 |
|---|---|
| author | Yi Chen Chengzhe Li Qirui Yuan Jinyu Li Yuze Fan Xiaojun Ge Yun Li Fei Gao Rui Zhao |
| author_facet | Yi Chen Chengzhe Li Qirui Yuan Jinyu Li Yuze Fan Xiaojun Ge Yun Li Fei Gao Rui Zhao |
| author_sort | Yi Chen |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-2f1bc9c4733c47bea8f45243db3d86bb |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-2f1bc9c4733c47bea8f45243db3d86bb2025-01-10T13:20:45ZengMDPI AGSensors1424-82202024-12-012516410.3390/s25010064Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language ModelYi Chen0Chengzhe Li1Qirui Yuan2Jinyu Li3Yuze Fan4Xiaojun Ge5Yun Li6Fei Gao7Rui Zhao8College of Automotive Engineering, Jilin University, Changchun 130025, ChinaCollege of Automotive Engineering, Jilin University, Changchun 130025, ChinaCollege of Automotive Engineering, Jilin University, Changchun 130025, ChinaCollege of Automotive Engineering, Jilin University, Changchun 130025, ChinaCollege of Automotive Engineering, Jilin University, Changchun 130025, ChinaCollege of Automotive Engineering, Jilin University, Changchun 130025, ChinaGraduate School of Information and Science Technology, The University of Tokyo, Tokyo 113-8654, JapanCollege of Automotive Engineering, Jilin University, Changchun 130025, ChinaCollege of Automotive Engineering, Jilin University, Changchun 130025, ChinaThe 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.https://www.mdpi.com/1424-8220/25/1/64intelligent cockpitlarge language modelintent predictionhuman–machine interaction |
| spellingShingle | Yi Chen Chengzhe Li Qirui Yuan Jinyu Li Yuze Fan Xiaojun Ge Yun Li Fei Gao Rui Zhao Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model Sensors intelligent cockpit large language model intent prediction human–machine interaction |
| title | Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model |
| title_full | Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model |
| title_fullStr | Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model |
| title_full_unstemmed | Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model |
| title_short | Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model |
| title_sort | cockpit llama driver intent prediction in intelligent cockpit via large language model |
| topic | intelligent cockpit large language model intent prediction human–machine interaction |
| url | https://www.mdpi.com/1424-8220/25/1/64 |
| work_keys_str_mv | AT yichen cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT chengzheli cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT qiruiyuan cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT jinyuli cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT yuzefan cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT xiaojunge cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT yunli cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT feigao cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel AT ruizhao cockpitllamadriverintentpredictioninintelligentcockpitvialargelanguagemodel |