Reproduce “A Scalable Framework For Real-Time Multi-Robot, Multi-Human Collision Avoidance” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Andrea Bajcsy, Sylvia L. Herbert, David Fridovich-Keil, Jaime F. Fisac, Sampada Deglurkar, Anca D. Dragan, Claire J. Tomlin

SCAFFOLD combines robot tracking bounds, uncertainty-aware human forecasts, and fixed-priority planning to coordinate robots around people. It expands paths by tracking error, adapts forecasts to unexpected behavior, and checks robots sequentially. Tests used two quadcopters and two people; simulation involved five robots and ten people, with planning taking 0.23 ± 0.16 seconds per robot, demonstrating feasibility at that scale.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.