A Social Multi-Agent Cooperation System Based on Planning and Distributed Task Allocation

Abstract

Planning and distributed task allocation are considered challenging problems. To address them, autonomous agents called planning agents situated in a multi-agent system should cooperate to achieve planning and complete distributed tasks. We propose a solution for distributed task allocation where agents dynamically allocate the tasks while they are building the plans. We model and verify some properties using computation tree logic (CTL) with the model checker its-ctl. Lastly, simulations are performed to verify the effectiveness of our proposed solution. The result proves that it is very efficient as it requires little message exchange and computational time. A benchmark production system is used as a running example to explain our contribution.

Task Allocation on Layered Multiagent Systems: When Evolutionary Many-Objective Optimization Meets Deep Q-Learning

“…13. The optimal makespan comparison between two kinds of methods deep learning within different cooperation environment and various agent types for various targets [6], [25]; 2) solving the uncertain task allocation problem in a dynamic environment by using some novel optimization methods [2], [10], [35]- [38], [53]; and 3) the task allocation problem on MASs subject to engineering-oriented complexities [40], [46], [59], [62]- [64].…”

“…T HE past two decades have witnessed a great deal of research attention devoted to multi-agent systems (MASs) [7], [8], [13], [16], [19], [31], [55], [57]. Task allocation in MASs aims at finding appropriate agents who can independently or cooperatively conduct specific tasks [2], [25]. In the existing literature, task allocation has been classified into various categories according to three different perspectives: 1) from the tasks' viewpoint, task allocations can be divided into single-task and multi-task assignments; 2) in terms of the agents (more generally robots), there are single-robot and multi-robot allocations; and 3) by means of assignment style, task allocations can be grouped into instantaneous and timeextended ones.…”

Multi-Robot based Control System

“…a set of sensors to get data about the external environment in which the flexible robot is existing) and the effectors (i.e. a set of actuators to realize the flexible robot's tasks) [35]. Fig.…”