Automation in agriculture, driven by labor shortages and steep production costs, is integral to the future cultivation of specialty crops such as strawberries. To efficiently harvest a strawberry field, a tri-layered algorithm is developed to address the assignment problem that arises when cooperative robots seek a new row to harvest. The proposed algorithm incentivizes robots to cooperate to maximize yield in minimal time, analogous to human harvesters, making it relatively simple to understand and implement. A primary local auction phase is implemented with a centralized fallback algorithm. The local auction is of constant time complexity and aims to reduce communication time among robots, allowing the algorithm to scale to the large farm and fleet sizes required for commercial production. The decentralized process enables real-time decision making and improves robustness. A Monte-Carlo simulation of the proposed algorithm is developed, and the results are compared to a centralized benchmark process with the algorithm displaying superior scalability
| Identifer | oai:union.ndltd.org:ucf.edu/oai:stars.library.ucf.edu:etd2020-2334 |
| Date | 01 January 2021 |
| Creators | Mapes, Madeline |
| Publisher | STARS |
| Source Sets | University of Central Florida |
| Language | English |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Electronic Theses and Dissertations, 2020- |
Page generated in 0.0983 seconds