Adaptive Give-Up Decisions for a Team of Robots Foraging with Task Partitioning

This work considers a team of robots foraging in a dynamic environment. The arena is divided into source and nest regions. Robots must transport objects from a source to a nest having two ways to complete this task: partitioning and non-partitioning. When partitioning, a robot carries the object until an area for transference while another robot may pick it up later to carry it to a nest. The non-partitioning option uses an alternative path that allows robots traveling back and forth between the regions. Robot decisions are based on experienced time to complete the transportation. Robots look for the faster option. We proposed two decision-making models: M-SGU (model for Static give up function) and M-AGU (model for adaptive give up function). M-AGU allows adaptation while robots forage and delivered the most promising results. We changed the delay to transfer an object to reproduce dynamic conditions that could be faced in real environments. Due to these changeable conditions, robots have to consider whether to abandon or struggle to complete the current task. The proposed decision-making strategies use a new adaptive give up function to make robots decide considering costs on both options and mixing old and new information. Simulation results show that robots reach faster adaptations leading to more objects successfully transported when using the proposed M-AGU strategy, which is also scalable to larger teams.