This repository serves as a curated collection of research papers focusing on Vision-Language Models (VLMs) applied to Autonomous Driving (AD) and Intelligent Transportation Systems (ITS). It aims to provide a comprehensive overview of the field for researchers and practitioners, tracking the latest advancements and offering a structured catalog of relevant work.

How It Works

The repository organizes papers by application area within AD/ITS, including Perception and Understanding, Navigation and Planning, Decision-Making and Control, End-to-End Autonomous Driving, Data Generation, and ITS applications. Each entry typically includes the paper's title, year, specific task addressed, and a link to its code or related resources, facilitating easy access to the underlying research.

Quick Start & Requirements

This repository is a curated list of papers and does not have a direct installation or execution process. Users can browse the listed papers and access their associated code repositories or datasets via the provided links.

Highlighted Details

• Comprehensive coverage of VLMs in AD/ITS, categorized by task.
• Includes links to code repositories for many listed papers.
• Features a dedicated section for relevant datasets in AD and ITS.
• Regularly updated to reflect the latest research in the field.

Maintenance & Community

The repository is maintained by TUM-AIR and is continuously updated. The primary output is a survey paper, "Vision Language Models in Autonomous Driving: A Survey and Outlook," which is available on ArXiv and has been accepted by IEEE Transactions on Intelligent Vehicles. Citation details are provided.

Licensing & Compatibility

This repository is released under the Apache 2.0 license. This license is permissive and generally allows for commercial use and integration into closed-source projects.

Limitations & Caveats

The repository is a curated list and does not provide direct implementations or tools. Users must follow the links to individual research projects for code and execution details. The "latest update" is noted as May 17, 2024, indicating potential lag for very recent publications.