Reproduce “Multi-Robot Navigation in Social Mini-Games: Definitions, Taxonomy, and Algorithms” 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

Rohan Chandra, Shubham Singh, Wenhao Luo, Katia Sycara

This research defines "Social Mini-Games" (SMGs) as a distinct subclass of multi-robot navigation problems, establishing a comprehensive taxonomy and proposing novel evaluation metrics for a fragmented field. It formalizes SMGs with characteristics like persistent mutual occupancy contention and introduces an open-source simulation environment, SMGLib, to facilitate standardized research and benchmarking.

Key insights

  • Social Mini-Games fundamentally differ from general MRN scenarios due to their sustained mutual occupancy contention, capacity-one resource bottlenecks, and high agency among agents.
  • A structured taxonomy is essential for unifying the fragmented SMG research landscape, allowing for systematic comparison and understanding of diverse solver approaches.
  • Effective SMG solvers must balance critical properties including safety, liveness, welfare maximization, social compliance, and scalability, especially within active coupling sets.

Summary by alphaXiv.

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