AI vs. Humans: Comparing road user intention recognition performance

• Empirical comparison of human and AI performance on a critical driving task : This paper compares video-based road user intention recognition (RUIR) performance between human participants and a state-of-the-art AI model under the same controlled conditions. • Insight into human video-based RUIR performance: Through an experiment involving 161 participants, the study reveals no significant performance differences across demographic groups, while highlighting specific maneuver types where AI and humans diverge in intention recognition performance. • Novel road user intention recognition dataset extension: By extending existing road user action recognition datasets with intention labels derived from the action annotations, we address a gap in publicly available RUIR datasets and enable benchmarking of human and AI performance. Anticipating the behavior of other road users is critical for safe driving. To anticipate the behavior of other road users in a timely manner, it is essential to recognize their intentions. Although artificial intelligence (AI)-based intention recognition systems for traffic scenarios have advanced significantly, their performance relative to human road user intention recognition (RUIR) remains largely unexplored. To address this gap, we conducted an experiment comparing the RUIR performance of human participants and a state-of-the-art end-to-end video recognition AI model on a set of 25 video scenarios. The selected scenarios offered a balanced representation of various road user types and a range of intention maneuvers. Among human participants (N=161), we found no statistically significant differences in RUIR performance with respect to age, self-perceived driving skill, annual driven kilometers, or years of driving experience. However, the average human participant exhibited slightly lower RUIR performance than the AI models.