As urban spaces evolve and technology advances, the concept of human-robot interaction becomes not just a science fiction trope but a part of our reality. This transformation is manifesting in various forms, one of them being sidewalk autonomous delivery robots. These compact machines, often designed to deliver packages or food, are increasingly sharing our walkways, leading to an essential question – how can pedestrians and robots safely and efficiently coexist in shared spaces?
To address this question, our recent study took a deep dive into the dynamics between sidewalk delivery robots and pedestrians in urban settings. Our focus was twofold: evaluating pedestrian safety and determining the efficiency of robots in shared spaces.
Digital Twins: Realistic Simulations of Human-Robot Interactions
Our approach began with the development of a 3D digital twin environment model. This innovative model allows us to simulate robot-human and robot-cityscape interactions realistically. We integrated the Pedestrian Aware Model (PAM) to ensure that our simulated robots could navigate their environments both effectively and safely.
Adopting an agent-based modeling approach, we analyzed various scenarios where pedestrians, wheelchair users, and robots share sidewalk spaces. This diverse range of scenarios enabled us to explore the complexities of human-robot interaction comprehensively.
Snapshot York University campus Digital Twin}
Robots and Pedestrians: A Potential for Smooth Coexistence
Our findings challenge the common concern that robots may contribute to sidewalk congestion. The study reveals that robots can be programmed to maintain a buffer zone, allowing for both safety and efficiency in pedestrian spaces. This buffer zone reduces the chances of congestion and collision, suggesting that robots could potentially coexist smoothly with pedestrians.
However, our study also highlights areas for improvement. We observed that robots were responsible for most collisions, while pedestrians primarily violated the minimum distance thresholds, which in turn, increase the risks of interactions. These findings emphasize the necessity for further research and strategies aimed at minimizing these risks.
Last Mile Delivery Robot Simulation Tool: (a) and (b) show diverse mobility agents, including robots, pedestrians, and wheelchair users, seamlessly progressing to their destinations. In (c), agents adhere to the path created by the route analysis API.
Towards a Harmonious Urban Landscape
Our research suggests that with careful design-oriented planning and continued research, robots can safely and comfortably share sidewalks with pedestrians, contributing to a more harmonious and efficient urban landscape. In essence, the advancement of sidewalk autonomous delivery robots doesn’t have to come at the expense of pedestrian comfort or safety.
This work also opens new avenues for urban planners, policymakers, and researchers. The proposed simulation model offers a tool to evaluate the influence of various design interventions and policies on human-robot coexistence in cities, marking a crucial step toward accommodating both humans and robots in urban spaces.
As our cities grow and evolve, so too must our understanding and approach toward the emerging role of robots in these spaces. Harmonious human-robot coexistence is not a distant fantasy, but a realistic prospect that we can and should strive for, one sidewalk at a time.
Keywords: Digital twin, pedestrian behaviour, sidewalk autonomous delivery robots, Human-robot interaction.