GPT-4V Takes the Wheel: Promises and Challenges for Pedestrian Behavior Prediction

TL;DR

This paper evaluates GPT-4V's ability to predict pedestrian behavior in autonomous driving, highlighting its strengths in understanding complex scenarios and its limitations compared to specialized models.

Contribution

First to assess Vision Language Models like GPT-4V for pedestrian behavior prediction in autonomous driving contexts.

Findings

GPT-4V achieves 57% accuracy in zero-shot pedestrian behavior prediction.

GPT-4V effectively interprets complex traffic scenarios and pedestrian groups.

Challenges include detecting small pedestrians and assessing relative motion.

Abstract

Predicting pedestrian behavior is the key to ensure safety and reliability of autonomous vehicles. While deep learning methods have been promising by learning from annotated video frame sequences, they often fail to fully grasp the dynamic interactions between pedestrians and traffic, crucial for accurate predictions. These models also lack nuanced common sense reasoning. Moreover, the manual annotation of datasets for these models is expensive and challenging to adapt to new situations. The advent of Vision Language Models (VLMs) introduces promising alternatives to these issues, thanks to their advanced visual and causal reasoning skills. To our knowledge, this research is the first to conduct both quantitative and qualitative evaluations of VLMs in the context of pedestrian behavior prediction for autonomous driving. We evaluate GPT-4V(ision) on publicly available pedestrian datasets: JAAD and WiDEVIEW. Our quantitative analysis focuses on GPT-4V's ability to predict pedestrian behavior in current and future frames. The model achieves a 57% accuracy in a zero-shot manner, which, while impressive, is still behind the state-of-the-art domain-specific models (70%) in predicting pedestrian crossing actions. Qualitatively, GPT-4V shows an impressive ability to process and interpret complex traffic scenarios, differentiate between various pedestrian behaviors, and detect and analyze groups. However, it faces challenges, such as difficulty in detecting smaller pedestrians and assessing the relative motion between pedestrians and the ego vehicle.