Show simple item record

dc.contributor.advisorYogesh Girdhar and Jonathan P. How.en_US
dc.contributor.authorJamieson, Stewart Christopher.en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Aeronautics and Astronautics.en_US
dc.date.accessioned2020-09-03T17:45:21Z
dc.date.available2020-09-03T17:45:21Z
dc.date.copyright2020en_US
dc.date.issued2020en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/127067
dc.descriptionThesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, May, 2020en_US
dc.descriptionCataloged from the official PDF of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 93-104).en_US
dc.description.abstractContemporary scientific exploration most often takes place in highly remote and dangerous environments, such as in the deep sea and on other planets. These environments are very hostile to humans, which makes robotic exploration the first and often the only option. However, they also impose restrictive limits on how much communication is possible, creating challenges in implementing remote command and control. We propose an approach to enable more efficient autonomous robot-based scientific exploration of remote environments despite these limits on human-robot communication. We find this requires the robot to have a spatial observation model that can predict where to find various phenomena, a reward model which can measure how relevant these phenomena are to the scientific mission objectives, and an adaptive path planner which can use this information to plan high scientific value paths. We identified and addressed two main gaps: the lack of a general-purpose means for spatial observation modelling, and the challenge in learning a reward model based on images online given the limited bandwidth constraints. Our first key contribution is enabling general-purpose spatial observation modelling through spatio-temporal topic models, which are well suited for unsupervised scientific exploration of novel environments. Our next key contribution is an active learning criterion which enables learning an image-based reward model during an exploration mission by communicating with the science team efficiently. We show that using these together can result in a robotic explorer collecting up to 230% more scientifically relevant observations in a single mission than when using lawnmower trajectories.en_US
dc.description.statementofresponsibilityby Stewart Christopher Jamieson.en_US
dc.format.extent104 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectAeronautics and Astronautics.en_US
dc.titleEnabling human-robot cooperation in scientific exploration of bandwidth-limited environmentsen_US
dc.typeThesisen_US
dc.description.degreeS.M.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Aeronautics and Astronauticsen_US
dc.identifier.oclc1191819112en_US
dc.description.collectionS.M. Massachusetts Institute of Technology, Department of Aeronautics and Astronauticsen_US
dspace.imported2020-09-03T17:45:20Zen_US
mit.thesis.degreeMasteren_US
mit.thesis.departmentAeroen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record