Answers are grounded in this paper and cite their sources.
This dataset contains the raw outputs of a discrete event simulation study of hospital robot dispatch, together with the frozen experiment designs, calibration logs, and summary analyses. It accompanies the article "When Hospital Robots Ask Staff for Help: Forecasting Human Support in Robot Dispatch" (submitted to the International Journal of Social Robotics). The simulation replays 33,079 recorded transport requests from the University Medical Center Freiburg (https://doi.org/10.5281/zenodo.19085901) and compares human transport with robot dispatch rules for missions that need staff to load, receive, or clean. The main experiment covers 18 conditions (three staff arrangements, three levels of staff unavailability, and two reporting delays) with 20 paired seeds each. Further phases add random admission controls at matched robot coverage, a staff time front, an optimizer volume control, a threshold rule compared at equal coverage, exploratory operating scenarios, a warm-up check, a class mix with 20% instead of 40% urgent specimens, and an availability gate that admits a robot only when idle workers can serve it. The run files also contain staff-side measures: support calls, call-to-arrival time, robot waiting time, displaced other duties, and overtime. The record holds 24,661 run files (one JSON file per run) in thirteen archives, plus SHA256 checksums; README.md describes each archive and the fields of the run files. The simulation code is available at https://github.com/siwekk/hospital-robot-staff-support, and together with it the data reproduce every table and figure of the article. Task classes, deadlines, service times, and staffing are model assumptions, so the results do not estimate clinical benefit or staffing needs at Freiburg.
No takes yet. Share an insight, caveat, or question.
Siwek et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: