Multi-Agent Task Allocation Techniques for Harvest Team Formation

Harman, Helen and Sklar, Elizabeth (2022) Multi-Agent Task Allocation Techniques for Harvest Team Formation. In: Advances in Practical Applications of Agents, Multi-Agent Systems, and Complex Systems Simulation. The PAAMS Collection, 13th-15th July 2022, Italy.

Full content URL:

Multi-Agent Task Allocation Techniques for Harvest Team Formation
Author's accepted manuscript

Request a copy
[img] PDF
harman_sklar_paams22_manuscript.pdf - Whole Document
Restricted to Repository staff only until 12 October 2023.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive


With increasing demands for soft fruit and shortages of seasonal workers, farms are seeking innovative solutions for efficiently managing their workforce. The harvesting workforce is typically organised by farm managers who assign workers to the fields that are ready to be harvested. They aim to minimise staff time (and costs) and distribute work fairly, whilst still picking all ripe fruit within the fields that need to be harvested. This paper posits that this problem can be addressed using multi-criteria, multi-agent task allocation techniques. The work presented compares the application of Genetic Algorithms (GAs) vs auction-based approaches to the challenge of assigning workers with various skill sets to fields with various estimated yields. These approaches are evaluated alongside a previously suggested method and the teams that were manually created by a farm manager during the 2021 harvesting season. Results indicate that the GA approach produces more efficient team allocations than the alternatives assessed.

Keywords:Multi-agent system, Applied AI, Harvest management
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
Divisions:College of Science > Lincoln Institute for Agri-Food Technology
Related URLs:
ID Code:50057
Deposited On:18 Jul 2022 14:55

Repository Staff Only: item control page