Modeling curiosity in a mobile robot for long-term autonomous exploration and monitoring
MetadataShow full item record
This paper presents a novel approach to modeling curiosity in a mobile robot, which is useful for monitoring and adaptive data collection tasks, especially in the context of long term autonomous missions where pre- programmed missions are likely to have limited utility. We use a realtime topic modeling technique to build a semantic perception model of the environment, using which, we plan a path through the locations in the world with high se- mantic information content. The life-long learning behavior of the proposed perception model makes it suitable for long-term exploration missions. We val- idate the approach using simulated exploration experiments using aerial and underwater data, and demonstrate an implementation on the Aqua underwa- ter robot in a variety of scenarios. We nd that the proposed exploration paths that are biased towards locations with high topic perplexity, produce better terrain models with high discriminative power. Moreover, we show that the proposed algorithm implemented on Aqua robot is able to do tasks such as coral reef inspection, diver following, and sea oor exploration, without any prior training or preparation.
Author Posting. © The Author(s), 2015. This is the author's version of the work. It is posted here by permission of Springer for personal use, not for redistribution. The definitive version was published in Autonomous Robots 40 (2016): 1267–1278, doi:10.1007/s10514-015-9500-x.
Suggested CitationPreprint: Girdhar, Yogesh, Dudek, Gregory, "Modeling curiosity in a mobile robot for long-term autonomous exploration and monitoring", 2015-09, https://doi.org/10.1007/s10514-015-9500-x, https://hdl.handle.net/1912/8505
Showing items related by title, author, creator and subject.
Efficient control based on a verified model for an autonomous underwater vehicle : a case study of Autonomous Benthic Explorer Anderson, Jamie M. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1992-02)The Autonomous Benthic Explorer (ABE) is an unmanned underwater vehicle being developed for scientific study of the deep ocean sea:floor. ABE will be completely autonomous from the surface which means that the lifetime ...
Eustice, Ryan M.; Pizarro, Oscar; Singh, Hanumant (IEEE, 2008-04)As autonomous underwater vehicles (AUVs) are becoming routinely used in an exploratory context for ocean science, the goal of visually augmented navigation (VAN) is to improve the near-seafloor navigation precision of such ...
Sayles, Frederick L.; Eck, Calvert F. (2009-04-13)The design and testing of a robotic analyzer for autonomous TCO2 measurement from oceanographic moorings is described. The analyzer employs a conductimetric method of TCO2 measurement wherein CO2 from an acidified sample ...