Coordinated Searching and Target Identification Using Teams of Autonomous Agents

Many modern autonomous systems actually require significant human involvement. Often, the amount of human support and infrastructure required for these autonomous systems exceeds that of their manned counterparts. This work involves increasing both the tactical and strategic decision making capabilities of various autonomous systems. The application considered is the problem of searching for targets using a team of heterogeneous agents. The system maintains a grid-based world model which contains information about the probability of a target being located in any given cell of the map. Agents formulate control decisions for a fixed number of time steps using a modular algorithm that allows for capabilities and characteristics of individual agents to be encoded in several parameters. The resulting search patterns executed by the agents guarantee an exhaustive search of the map in the sense that all cells will be searched sufficiently to ensure that the probability of a target being located in any given cell is driven to zero. This system was simulated using high fidelity simulations with heterogeneous agents in complex and dynamic environments. After performing successfully in simulation, these algorithms were then verified and validated on a distributed human-in-the-loop simulator. This system allows a human operator to handle low level tasks such as state stabilization and signal tracking while preserving the contributions of the autonomous algorithm. Finally, flight test results are presented showing the benefits of augmenting a human system with these types of autonomous algorithms.