Estimation of Pedestrian Risk Level Using Context Features for Remote Monitoring Alert System of Autonomous Micro-Mobility Vehicles

Abstract

Smart cities utilize IoT and ICT technologies to optimize urban infrastructure, addressing challenges such as rapid urbanization, traffic congestion, and environmental impact. Micro-mobility services, including autonomous delivery robots and electric scooters, have recently emerged as promising solutions to enhance urban mobility and logistics efficiency. However, autonomous micro-mobility vehicles operating on sidewalks require remote monitoring by human operators for immediate intervention during unexpected events. Existing remote monitoring systems, primarily developed for road-based autonomous vehicles, often generate excessive alerts in crowded sidewalk environments, significantly increasing operator workload. This paper proposes a novel remote monitoring alert system that estimates pedestrian risk levels using context features such as pedestrian size, position, and posture from the perspective of micro-mobility vehicles. A numerical risk level is computed, predicting the likelihood of pedestrians obstructing vehicle movement, and alerts are generated accordingly. The proposed approach was evaluated using the JRDB open dataset, a simulator environment, and a real-world demonstration with an autonomous micro-mobility vehicle. The results show that the estimation performance depends on the future horizon and the combination of context features. Our findings highlight the potential of context-based risk assessment systems to support efficient and scalable remote monitoring of autonomous micro-mobility vehicles.