Probabilistic Planning for Decentralized Multi-Robot Systems

Christopher Amato, George Dimitri Konidaris, Shayegan Omidshafiei, Ali-akbar Agha-mohammadi, Jonathan P. How, Leslie Pack Kaelbling

Abstract

Multi-robot systems are an exciting application domain for AI research and Dec-POMDPs, specifically. MacDec-POMDP methods can produce high-quality general solutions for realistic heterogeneous multi-robot coordination problems by automatically generating control and communication policies, given a model. In contrast to most existing multi-robot methods that are specialized to a particular problem class, our approach can synthesize policies that exploit any opportunities for coordination that are present in the problem, while balancing uncertainty, sensor information, and information about other agents.
BibTeX
@inproceedings{amato2015probabilistic,
  author = {Christopher Amato and George Dimitri Konidaris and Shayegan Omidshafiei and Ali-akbar Agha-mohammadi and Jonathan P. How and Leslie Pack Kaelbling},
  title = {{Probabilistic Planning for Decentralized Multi-Robot Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2015},
}

Loading related content...

Figure