On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving

TL;DR

This paper evaluates GPT-4V(ision), a visual-language model, for autonomous driving, demonstrating its strengths in scene understanding and reasoning, while identifying key challenges for real-world deployment.

Contribution

It provides an exhaustive assessment of GPT-4V(ision) in autonomous driving scenarios, highlighting its capabilities and limitations in complex driving environments.

Findings

Superior scene understanding and causal reasoning compared to existing systems

Effective handling of out-of-distribution scenarios and recognizing intentions

Challenges in direction discernment, traffic light recognition, and spatial reasoning

Abstract

The pursuit of autonomous driving technology hinges on the sophisticated integration of perception, decision-making, and control systems. Traditional approaches, both data-driven and rule-based, have been hindered by their inability to grasp the nuance of complex driving environments and the intentions of other road users. This has been a significant bottleneck, particularly in the development of common sense reasoning and nuanced scene understanding necessary for safe and reliable autonomous driving. The advent of Visual Language Models (VLM) represents a novel frontier in realizing fully autonomous vehicle driving. This report provides an exhaustive evaluation of the latest state-of-the-art VLM, GPT-4V(ision), and its application in autonomous driving scenarios. We explore the model's abilities to understand and reason about driving scenes, make decisions, and ultimately act in the capacity of a driver. Our comprehensive tests span from basic scene recognition to complex causal reasoning and real-time decision-making under varying conditions. Our findings reveal that GPT-4V demonstrates superior performance in scene understanding and causal reasoning compared to existing autonomous systems. It showcases the potential to handle out-of-distribution scenarios, recognize intentions, and make informed decisions in real driving contexts. However, challenges remain, particularly in direction discernment, traffic light recognition, vision grounding, and spatial reasoning tasks. These limitations underscore the need for further research and development. Project is now available on GitHub for interested parties to access and utilize: \url{https://github.com/PJLab-ADG/GPT4V-AD-Exploration}