Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 2 of 2

Full-Text Articles in Engineering

Vision-Based Autonomous Tracking Of A Non-Cooperative Mobile Robot By A Low-Cost Quadrotor Vehicle, Cheikhna Ahmed Tidiane Sy Nov 2019

Vision-Based Autonomous Tracking Of A Non-Cooperative Mobile Robot By A Low-Cost Quadrotor Vehicle, Cheikhna Ahmed Tidiane Sy

Electrical and Computer Engineering ETDs

The goal of this thesis is the detection and tracking of a ground vehicle, in particular a car-like robot, by a quadrotor. The first challenge to address in any pursuit or tracking scenario is the detection and unique identification of the target. From this first challenge, comes the need to precisely localize the target in a coordinate system that is common to the tracking and tracked vehicles. In most real-life scenarios, the tracked vehicle does not directly communicate information such as its position to the tracking one. From this fact, arises a non-cooperative constraint problem. The autonomous tracking aspect of …


Viewpoint Optimization For Autonomous Strawberry Harvesting With Deep Reinforcement Learning, Jonathon J. Sather Jun 2019

Viewpoint Optimization For Autonomous Strawberry Harvesting With Deep Reinforcement Learning, Jonathon J. Sather

Master's Theses

Autonomous harvesting may provide a viable solution to mounting labor pressures in the United States' strawberry industry. However, due to bottlenecks in machine perception and economic viability, a profitable and commercially adopted strawberry harvesting system remains elusive. In this research, we explore the feasibility of using deep reinforcement learning to overcome these bottlenecks and develop a practical algorithm to address the sub-objective of viewpoint optimization, or the development of a control policy to direct a camera to favorable vantage points for autonomous harvesting. We evaluate the algorithm's performance in a custom, open-source simulated environment and observe affirmative results. Our trained …