Assessing pedestrian responses to autonomous and personal mobility robots in crowded public spaces
Science Advances · 2026-08-07 · 12 (32)
DOI: 10.1126/sciadv.aef2576 ↗At a glance
Journal article in Science Advances, published on 2026-08-07. Written by Dominik Wojcikiewicz and 2 co-authors. Institution: Spinal Cord Injury Artificial Intelligence Lab (SCAI), D-HEST, ETH Zürich, Zürich, Switzerland. Major MEDLINE topics: Pedestrians, Crowding, Robotics. 35 references. The full text is freely available in PubMed Central. Funded by: Innosuisse - Schweizerische Agentur für Innovationsförderung, Moonshot Research and Development Program, European ROBotics and AI Network.
Topics: Mobilisation
Abstract (original language)
Robots increasingly share spaces with people, supporting delivery services and mobility for the aging populations, yet their ability to share space comfortably lacks understanding and benchmarks for designers and policy-makers. We compared human-robot (HRI) and human-human (HHI) interactions across four real-world crowd datasets spanning Europe, North America, and Asia, using a unified pipeline to detect interactions, stratify by crowd density, and model pedestrian behavior. Local motion patterns (speed, acceleration, and jerk) remained closely matched between HRI and HHI across all densities. In contrast, proxemics diverged, with effects that grew approximately linearly with robot speed and weakened under higher crowding: In the dataset with the faster navigating robot, pedestrians maintained about 0.23 meters more clearance around the robot than around other pedestrians under less crowded conditions and about 0.05 meters more under more crowded conditions, while in the dataset with the predominantly stationary robot, the corresponding differences were small and inconsistent across crowding levels. The main conclusions were robust to parameter variations and remained stable across a broad range of motion-processing and interaction-labeling settings. Our findings provide density- and speed-aware benchmarks for proxemics in social robot navigation and empirically grounded targets for design, evaluation, and modeling across robotics and urban mobility.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- Spinal Cord Injury Artificial Intelligence Lab (SCAI), D-HEST, ETH Zürich, Zürich, Switzerland.
- Digital Health Care and Rehabilitation, Swiss Paraplegic Research (SPF), Nottwil, Switzerland.
- LASA, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland.
ORCID profiles: Dominik Wojcikiewicz, Aude Billard, Diego Paez-Granados
Funding
- Innosuisse - Schweizerische Agentur für Innovationsförderung
- Moonshot Research and Development Program
- European ROBotics and AI Network
Cite
APA
Wojcikiewicz, D., Billard, A., & Paez-Granados, D. (2026). Assessing pedestrian responses to autonomous and personal mobility robots in crowded public spaces. Science Advances, 12(32). https://doi.org/10.1126/sciadv.aef2576
Vancouver
Wojcikiewicz D, Billard A, Paez-Granados D. Assessing pedestrian responses to autonomous and personal mobility robots in crowded public spaces. Science Advances. 2026;12(32). doi:10.1126/sciadv.aef2576
BibTeX
@article{Wojcikiewicz2026,
author = {Wojcikiewicz, Dominik and Billard, Aude and Paez-Granados, Diego},
title = {Assessing pedestrian responses to autonomous and personal mobility robots in crowded public spaces},
journal = {Science Advances},
year = {2026},
volume = {12},
number = {32},
doi = {10.1126/sciadv.aef2576}
}
EUVIMED