Nature-Inspired Multi-Agent Coordination in Task Assignment Problems

The main problem when using multi-agent systems (MAS) for task assignment problems in real-world environments is the limited scalability of traditional MAS approaches such as centralized planning. Therefore, we look at a scalable, generic methodology inspired by nature for multi-agent coordination in large, embodied MAS, operating in noisy, real-time environments. More specifically, we look at real-world task assignment problems and use the testbed of robots performing resource distribution in large storage facilities. As a first step toward a generic methodology for embodied, distributed MAS, we analyse the behavior and the scalability of an embodied MAS which is driven by simulated potential fields. Resources in a storage facility emit a certain simulated potential while robots emit an opposite potential. Applying principles inspired by physics to local behavior, idle robots move toward resources but away from other robots. Whenever a resource appears, a central agent system registers this appearance and creates a plan for a robot to pick up the resource and deliver it to some destination area. We show that this system is highly scalable with respect to both the environment and the number of robots, while maintaining functionality, adaptivity and robustness. Furthermore, the integration of planning prevents local optima and increases fairness. In future work, the central agent system will be replaced by a distributed system, such as a sensor network, to further increase scalability, adaptivity and robustness of the system.