We study the problem of distributed multi-robot coverage over an unknown,non-uniform sensory field . We propose an adaptive coverage algorithm called DeterministicSequencing of Learning and Coverage (DSLC) that schedules learning and coverageepochs such that its emphasis gradually shifts from exploration to exploitation . Using a novel definition of coverage regret, we analyze DSLC to provide an upper bound on expectedcumulative coverage regret . Finally, we illustrate the empirical performance of the algorithm through simulations of the coverage task over an unknowndistribution of wildfires to illustrate the algorithm’s performance . We use DSLC as an example of simulated coverage performance .

Author(s) : Lai Wei, Andrew McDonald, Vaibhav Srivastava

Links : PDF - Abstract

Code :

https://github.com/nhynes/abc


Coursera

Keywords : coverage - performance - algorithm - dslc - regret -

Leave a Reply

Your email address will not be published. Required fields are marked *