Reproduce “Distributed Predictive Flocking for a Swarm of Miniature Vibration-Driven Robots in a Confined Arena” 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
Prajol Shrestha, Siddhant Mohapatra, Filip Novkoski, Julian Oelhaf, Nicolas Vandewalle, Ana-Sunčana Smith, Andreas Maier
The authors present a decentralized controller for simulated miniature-robot swarms: each robot plans motion using nearby robots’ predicted paths to coordinate flocking, task-following, and safety. A forward-handle variant makes turning affect the safety-rate condition. In 100-robot free-space phototaxis runs, it recorded 36,505 ± 493 contact episodes versus 49,251 ± 614 for a matched variant, but did not eliminate contacts.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.