A Practical Application of Market-Based Mechanisms for Allocating Harvesting Tasks

Market-based task allocation mechanisms are designed to distribute a set of tasks fairly amongst a set of agents. Such mechanisms have been shown to be highly effective in simulation and when applied to multi-robot teams. Application of such mechanisms in real-world settings can present a range of practical challenges, such as knowing what is the best point in a complex process to allocate tasks and what information to consider in determining the allocation. The work presented here explores the application of market-based task allocation mechanisms to the problem of managing a heterogeneous human workforce to undertake activities associated with harvesting soft fruit. Soft fruit farms aim to maximise yield (the volume of fruit picked) while minimising labour time (and thus the cost of picking). Our work evaluates experimentally several different strategies for practical application of market-based mechanisms for allocating tasks to workers on soft fruit farms, identifying methods that appear best when simulated using a multi-agent model of farm activity.