A survey on multimodal large language models for autonomous driving
TLDR
A survey on multimodal large language models for autonomous driving, covering background, tools, datasets, benchmarks, and future challenges.
Reasoning
The paper provides a systematic overview of MLLMs in autonomous driving, including datasets and benchmarks, which is a strength. However, it is a survey without novel experiments or real-world validation, limiting its empirical contribution.
Read-first score
Read-first score 51.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 8.
Field roles
Rank sensitivity
Stability: volatile; rank range: 700.
Keyword Scores
Deep Analysis
Innovations
- Systematic investigation of Multimodal Large Language Models (MLLMs) for autonomous driving
- Overview of existing MLLM tools, datasets, and benchmarks for driving, transportation, and map systems
- Summary of the 1st WACV Workshop on Large Language and Vision Models for Autonomous Driving (LLVM-AD)
- Discussion of key challenges and future directions for applying MLLMs in autonomous driving
Methodology
The paper conducts a systematic literature review, covering the background of Multimodal Large Language Models (MLLMs), the development of multimodal models using LLMs, the history of autonomous driving, existing MLLM tools for driving/transportation/map systems, datasets and benchmarks, and a summary of the first workshop on LLMs in autonomous driving.
Key Results
No experimental results are presented; the paper provides a comprehensive overview and identifies important problems that need to be solved by academia and industry.