University of Alabama Birmingham
Uav Navigation, Tracking, And Interception Using Deep Reinforcement Learning
Abstract
dc:description.abstractWe propose a self-supervised, model-free deep reinforcement learning architecture with cascade reward for unmanned aerial vehicle navigation and target interception in a 3D environment. The first contribution of the dissertation solves the problem of partial observability when non-linear function approximators are used for learning stochastic policies. The second contribution optimizes the problem of maximizing the total expected rewards. The third contribution trains the agent in a photo-realistic environment with a real physics engine. To achieve these goals, a deep Q-network that combines double and dueling architectures is adopted as a value function approximator, and the prioritized experience replays the sample independent and identically distributed random variables from the experiences with the highest relevance to the interception and obstacle avoidance tasks. A new simulator is developed for training drones to track and intercept a target. We demonstrate that our approach achieves better results in learning policies compared to state-of-the-art deep Q-network algorithms.
Degree
thesis:*- Level thesis:degree_level
- Dissertation
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Darwish, Ali Alhaj
- Contributors dc:contributor
-
- Arie Nakhmani
- Amy Amara
- Earl Wells
- Karthikeyan Lingasubramanian
- Leon Jololian
Subjects
dc:subject × 2Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.library.uab.edu/etd-collection/997