Show simple item record

dc.contributor.advisorLeslie Pack Kaelbling and Tomás Lozano-Pérez.en_US
dc.contributor.authorKim, Beomjoon.en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2021-01-06T19:35:57Z
dc.date.available2021-01-06T19:35:57Z
dc.date.copyright2020en_US
dc.date.issued2020en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/129257
dc.descriptionThesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, September, 2020en_US
dc.descriptionCataloged from student-submitted PDF of thesis.en_US
dc.descriptionIncludes bibliographical references (pages [113]-124).en_US
dc.description.abstractHow can we enable robots to efficiently reason both at the discrete task-level and the continuous motion-level to achieve high-level goals such as tidying up a room or constructing a building? This is a challenging problem that requires integrated reasoning about the combinatoric aspects of the problem, such as deciding which object to manipulate, and continuous aspects of the problem, such as finding collision-free manipulation motions, to achieve goals. The classical robotics approach is to design a planner that, given an initial state, goal, and transition model, computes a plan. The advantage of this approach is its immense generalization capability. For any given state and goal, a planner will find a solution if there is one. The inherent drawback, however, is that a planner does not typically make use of planning experience, and computes a plan from scratch every time it encounters a new problem. For complex problems, this renders planners extremely inefficient.en_US
dc.description.abstractAlternatively, we can take a pure learning approach where the system learns, from either reinforcement signals or demonstrations, a policy that maps states to actions. The advantage of this approach is that computing the next action to execute becomes much cheaper than pure planning because it is simply making a prediction using a function approximator. The drawback, however, is that it is brittle. If a policy encounters a state that is very different from the ones seen in the training set, then it is likely to make mistakes and might get into a situation from which it does not know how to proceed. Our approach is to take the middle ground between these two extremes. More concretely, this thesis introduces several algorithms that learn to guide a planner from planning experience. We propose state representations, neural network architectures, and data-efficient algorithms for learning to perform both task and motion level reasoning using neural networks.en_US
dc.description.abstractWe then use these neural networks to guide a planner and show that it performs more efficiently than pure planning and pure learning algorithms.en_US
dc.description.statementofresponsibilityby Beomjoon Kim.en_US
dc.format.extent124 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.subjectElectrical Engineering and Computer Science.en_US
dc.titleLearning to guide task and motion planningen_US
dc.typeThesisen_US
dc.description.degreePh. D.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.identifier.oclc1227520382en_US
dc.description.collectionPh.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienceen_US
dspace.imported2021-01-06T19:35:56Zen_US
mit.thesis.degreeDoctoralen_US
mit.thesis.departmentEECSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record