Reproduce “Towards a Theory for the Design of Rules in Multi-Agent Systems: the case of Homogeneous Fleets” 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
Matteo Penlington, Lorenzo Fiaschi, Raj Kiriti Velicheti, Andrea Censi, Emilio Frazzoli
The authors select rules for autonomous vehicles by treating available controllers as black boxes and comparing the safety-compliant performance-and-cost guarantees each rule permits. RuleBnB searches candidates and identifies (5 m, 60 km/h) as a maximal rule in an incomplete-catalogue campus-curve simulation. There, profiles shrink as carriageway width grows at 40 and 60 km/h; this finding is limited to the tested controllers and rules.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.