作者@ARTICLE {10.3389 / frobt.2022.864745 ={哈曼,海伦和Sklar,伊丽莎白一世。},标题=多智能体任务分配收获管理}{,杂志={机器人和人工智能前沿},体积= {9}= {2022},URL = {https://www.f雷竞技rebatrontiersin.org/articles/10.3389/frobt.2022.864745}, DOI = {10.3389 / frobt.2022.864745}, ISSN ={2296 - 9144},多智能体任务分配方法抽象={寻求公平之间分配一组任务的一组代理。在实际设置,例如软水果农场,人类劳动者进行收集任务。收集员工通常是由农场经理(s)分配工人的字段将迎来收获的季节和团队领导者管理工人在田里。创建这些任务是一个动态的、复杂的问题,随着技能的劳动力和收益率(成熟的水果采摘量)变量和不完全可预测的。这里介绍的工作多智能体任务分配方法假定,可以帮助农场经理和团队领导管理收获劳动力有效且高效地。有三个关键的多代理方法适应这个问题时所面临的挑战:(i)员工时间应该最小化(因此成本);(2)任务必须分布相当保持员工积极性;和(iii)的方法必须能够处理增量数据随着赛季的进行(不完整)。适应变化的轮循(RR)提出了分配工人的问题领域,应用和以市场为基础的任务分配机制的挑战将任务分配给工人在字段。 To evaluate the approach introduced here, experiments are performed based on data that was supplied by a large commercial soft fruit farm for the past two harvesting seasons. The results demonstrate that our approach produces appropriate worker-to-field allocations. Moreover, simulated experiments demonstrate that there is a “sweet spot” with respect to the ratio between two types of in-field workers.} }