Reproduce “Cognitive Multi-Agent Search and Rescue: Language-Grounded Hierarchical Reinforcement Learning for Collaborative Robotics” 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
Sepideh Ravanbakhsh, Hamidreza Moradi
LG-HRL translates operator language into shared mission cues and uses them to guide team-level strategies and lower-level robot policies. In a simulated disaster environment, four robots use a shared workspace to coordinate priorities and hazards. Across five scenarios, LG-HRL rescued 88–92% of victims, versus 65–70% for HRL without language and 55–62% for flat RL; these are simulation results, not field performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.