Rulla Al-Haideri

Rulla Al-Haideri, Bilal Farooq, Elisabetta Cherchi

Pedestrian safety at midblock crossings is a critical concern in mixed traffic environments where autonomous vehicles (AVs) and human-driven vehicles (HDVs) share the road. Pedestrians often infer intent from vehicle motion in AV encounters, making them vulnerable to small shifts in conflict margins. This study investigates whether virtual reality (VR) crossing sessions separate into distinct interaction risk profiles and whether AV-only sessions shift profile prevalence compared to HDV-only sessions. Using large-scale immersive VR experiments from Toronto, Canada, and Newcastle, England, we compute surrogate safety measures (SSMs) and apply latent profile analysis (LPA) to identify distinct pedestrian crossing stances, ranging from risk-accepting to highly cautious. Key findings show that Newcastle exhibits a higher prevalence of high-urgency risk profiles in AV-only sessions, indicating that AVs contribute to higher-risk encounters. In contrast, Toronto shows no significant difference between AV-only and HDV-only sessions, suggesting that contextual factors influence the impact of AVs on pedestrian safety.

Rulla Al-Haideri, Bilal Farooq

High frequency pedestrian motion forecasting when interacting with autonomous vehicles (AVs) can be enhanced through the use of behavioural frameworks, such as discrete choice models, that can explicitly account for correlation among similar movement alternatives. We formulate the pedestrian next step choice as a spatial discrete choice defined by a grid of speed adjustment and heading change. Using naturalistic pedestrian-AV encounters from nuScenes and Argoverse 2 (1 sec decision interval), we estimate a multinomial logit baseline and four spatial generalized extreme value (GEV) specifications (SCL, GSCL, SCNL, and GSCNL). We then compare them to a residual neural network logit (ResLogit) model that learns cross alternative effects while retaining an interpretable linear utility component. Across the evaluated data, spatial GEV structures yield only marginal improvements over multinomial logit, whereas ResLogit achieves a substantially better fit and produces behaviourally coherent errors concentrated among neighbouring grid cells. The results suggest that in dense, high frequency spatial choice sets, learning based residual corrections can capture proximity induced correlation more effectively than analyst specified GEV nesting structures, while maintaining interpretability.