No abstract

No abstract

No abstract

Many complex systems, such as multi-agent modeling and simulation which are crucial in military applications, necessitate concurrent task planning and decision making. These applications include battlefield modeling and simulation for soldier virtual training. In general these systems are implemented on automated systems with distributed architectures on heterogeneous operating systems and hardware platforms. In this paper we present an autonomous multi agent path planning system with agents-in-formation constraints in a distributed computing environment. Here a given agent, an entity with behaviors, exchanges sensory positioning feedback information over the network with other agents that are running on separate networked distributed computing nodes than the one the given agent is running on. Hence the agents do not have complete knowledge of the environment, but only a limited one. That is, in keeping with the agent formation constraint, the agents have knowledge only of the agents' information residing on the distributed memory of the computing node the agents are running on. The agents exchange agents' positioning sensory information of the rest of the agents they are interacting with, over a distributed network. Here agents autonomous trajectory planning is achieved for each agent to reach its destination via an unstructured distributed environment filled with dynamic obstacles and other agents. One focus is on the agents achieving their goals under real time formation constraints. We propose a multi-threaded architecture to achieve light-weight concurrency and multi-agent cooperative concurrency, as they allow separation between address space and thread control. Additionally, a threads-based architecture benefits from nonblocking system calls. Finally, experimental results are presented to show the potential of the proposed method for multi-agent distributed path planning.