Expanding Constrained Kinodynamic Path Planning Solutions through Recurrent Neural Networks
dc.contributor.advisor | Xu, Huan | en_US |
dc.contributor.author | Shaffer, Joshua Allen | en_US |
dc.contributor.department | Aerospace Engineering | en_US |
dc.contributor.publisher | Digital Repository at the University of Maryland | en_US |
dc.contributor.publisher | University of Maryland (College Park, Md.) | en_US |
dc.date.accessioned | 2019-06-20T05:38:52Z | |
dc.date.available | 2019-06-20T05:38:52Z | |
dc.date.issued | 2019 | en_US |
dc.description.abstract | Path planning for autonomous systems with the inclusion of environment and kinematic/dynamic constraints encompasses a broad range of methodologies, often providing trade-offs between computation speed and variety/types of constraints satisfied. Therefore, an approach that can incorporate full kinematics/dynamics and environment constraints alongside greater computation speeds is of great interest. This thesis explores a methodology for using a slower-speed, robust kinematic/dynamic path planner for generating state path solutions, from which a recurrent neural network is trained upon. This path planning recurrent neural network is then used to generate state paths that a path-tracking controller can follow, trending the desired optimal solution. Improvements are made to the use of a kinodynamic rapidly-exploring random tree and a whole-path reinforcement training scheme for use in the methodology. Applications to 3 scenarios, including obstacle avoidance with 2D dynamics, 10-agent synchronized rendezvous with 2D dynamics, and a fully actuated double pendulum, illustrate the desired performance of the methodology while also pointing out the need for stronger training and amounts of training data. Last, a bounded set propagation algorithm is improved to provide the initial steps for formally verifying state paths produced by the path planning recurrent neural network. | en_US |
dc.identifier | https://doi.org/10.13016/dgob-oe6g | |
dc.identifier.uri | http://hdl.handle.net/1903/22019 | |
dc.language.iso | en | en_US |
dc.subject.pqcontrolled | Engineering | en_US |
dc.subject.pqcontrolled | Robotics | en_US |
dc.subject.pqcontrolled | Aerospace engineering | en_US |
dc.subject.pquncontrolled | Machine learning | en_US |
dc.subject.pquncontrolled | Motion/trajectory planning | en_US |
dc.subject.pquncontrolled | Neural networks | en_US |
dc.subject.pquncontrolled | Optimization | en_US |
dc.subject.pquncontrolled | Path planning | en_US |
dc.subject.pquncontrolled | Reinforcement learning | en_US |
dc.title | Expanding Constrained Kinodynamic Path Planning Solutions through Recurrent Neural Networks | en_US |
dc.type | Thesis | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Shaffer_umd_0117N_19941.pdf
- Size:
- 1.79 MB
- Format:
- Adobe Portable Document Format