Online Proactive Multi-Task Assignment with Resource Availability Anticipation

TL;DR

This paper introduces a proactive, receding-horizon approach for online multi-task assignment that anticipates resource availability without assuming future request locations, improving efficiency and task allocation.

Contribution

It presents a novel proactive multi-task assignment method using a genetic algorithm that does not rely on future request location assumptions, enhancing online optimization performance.

Findings

Outperforms reactive methods in cost and task allocation

Reduces resource idle time in benchmark tests

Effective in synthetic and real-world scenarios

Abstract

With the emergence of services and online applications as taxi dispatching, crowdsourcing, package or food delivery, industrials and researchers are paying attention to the online multi-task assignment optimization field to quickly and efficiently met demands. In this context, this paper is interested in the multi-task assignment problem where multiple requests (e.g. tasks) arrive over time and must be dynamically matched to (mobile) agents. This optimization problem is known to be NP-hard. In order to treat this problem with a proactive mindset, we propose to use a receding-horizon approach to determine which resources (e.g. taxis, mobile agents, drones, robots) would be available within this (possibly dynamic) receding-horizon to meet the current set of requests (i.e. tasks) as good as possible. Contrarily to several works in this domain, we have chosen to make no assumption concerning future locations of requests. To achieve fast optimized online solutions in terms of costs and amount of allocated tasks, we have designed a genetic algorithm based on a fitness function integrating the traveled distance and the age of the requests. We compared our proactive multi-task assignment with resource availability anticipation approach with a classical reactive approach. The results obtained in two benchmark problems, one synthetic and another based on real data, show that our resource availability anticipation method can achieve better results in terms of costs (e.g. traveled distance) and amount of allocated tasks than reactive approaches while decreasing resources idle time.