Vision-Integrated LLMs for Autonomous Driving Assistance : Human Performance Comparison and Trust Evaluation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910820399579136 |
|---|---|
| author | Kim, Namhee Park, Woojin |
| author_facet | Kim, Namhee Park, Woojin |
| contents | Traditional autonomous driving systems often struggle with reasoning in complex, unexpected scenarios due to limited comprehension of spatial relationships. In response, this study introduces a Large Language Model (LLM)-based Autonomous Driving (AD) assistance system that integrates a vision adapter and an LLM reasoning module to enhance visual understanding and decision-making. The vision adapter, combining YOLOv4 and Vision Transformer (ViT), extracts comprehensive visual features, while GPT-4 enables human-like spatial reasoning and response generation. Experimental evaluations with 45 experienced drivers revealed that the system closely mirrors human performance in describing situations and moderately aligns with human decisions in generating appropriate responses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06843 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vision-Integrated LLMs for Autonomous Driving Assistance : Human Performance Comparison and Trust Evaluation Kim, Namhee Park, Woojin Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Traditional autonomous driving systems often struggle with reasoning in complex, unexpected scenarios due to limited comprehension of spatial relationships. In response, this study introduces a Large Language Model (LLM)-based Autonomous Driving (AD) assistance system that integrates a vision adapter and an LLM reasoning module to enhance visual understanding and decision-making. The vision adapter, combining YOLOv4 and Vision Transformer (ViT), extracts comprehensive visual features, while GPT-4 enables human-like spatial reasoning and response generation. Experimental evaluations with 45 experienced drivers revealed that the system closely mirrors human performance in describing situations and moderately aligns with human decisions in generating appropriate responses. |
| title | Vision-Integrated LLMs for Autonomous Driving Assistance : Human Performance Comparison and Trust Evaluation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2502.06843 |