Reinforcement Learning with Gaussian Processes for Unmanned Aerial Vehicle Navigation

dc.contributor.authorGondhalekar, Nahush Rameshen
dc.contributor.committeechairTokekar, Pratapen
dc.contributor.committeememberZeng, Haiboen
dc.contributor.committeememberAbbott, A. Lynnen
dc.contributor.departmentElectrical and Computer Engineeringen
dc.description.abstractWe study the problem of Reinforcement Learning (RL) for Unmanned Aerial Vehicle (UAV) navigation with the smallest number of real world samples possible. This work is motivated by applications of learning autonomous navigation for aerial robots in structural inspec- tion. A naive RL implementation suffers from curse of dimensionality in large continuous state spaces. Gaussian Processes (GPs) exploit the spatial correlation to approximate state- action transition dynamics or value function in large state spaces. By incorporating GPs in naive Q-learning we achieve better performance in smaller number of samples. The evalua- tion is performed using simulations with an aerial robot. We also present a Multi-Fidelity Reinforcement Learning (MFRL) algorithm that leverages Gaussian Processes to learn the optimal policy in a real world environment leveraging samples gathered from a lower fidelity simulator. In MFRL, an agent uses multiple simulators of the real environment to perform actions. With multiple levels of fidelity in a simulator chain, the number of samples used in successively higher simulators can be reduced.en
dc.description.degreeMaster of Scienceen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.subjectReinforcement Learningen
dc.subjectGaussian Processesen
dc.subjectUnmanned Aerial Vehicle Navigationen
dc.titleReinforcement Learning with Gaussian Processes for Unmanned Aerial Vehicle Navigationen
dc.typeThesisen Engineeringen Polytechnic Institute and State Universityen of Scienceen
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
42.29 MB
Adobe Portable Document Format