Strategic Level Projects
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.
Hierarchical Integrated Communication and Control
The objective of the work in this project is to design integrated control and communication algorithms that guarantee that a set of vehicles with differing data capabilities will conform to a specified spatial distribution. Unlike most coordinated control settings, we are not only interested in the question of formation control, but also the question of reliably providing the communication necessary to achieve the coordination. Each vehicle is equipped with physical devices that provide local information from sensing and global information from communication. Sensing devices are assumed to be lower cost in terms of power, computation, and range of operation, while communication devices are comparatively higher cost but with more information density and reconfigurability. While each vehicle is equipped with a communication device, not all vehicles will be allowed to use these devices due to resource limitations, environmental constraints such as bandwidth, and/or failure of the device. Such scenarios are typical of multiple autonomous aircraft in urban settings or multiple autonomous underwater vehicles in shipyards.
Cooperative Planning for Teams of Heterogeneous Autonomous Vehicles
In this research, we investigate the problem of dynamic planning for a team of autonomous vehicles to cooperatively execute a set of assigned tasks. The emphasis is on the system architecture, planning algorithms and uncertainty management.
Path Planning with Realistic Weather Models
This research involves the integration of weather information from actual databases and forecast algorithms with evolutionary path planning techniques for long range autonomous flights. It addresses a 4-dimensional problem of space and time, requiring adaptation to account for unexpected changes in the environment. The objective is the planning of trajectories that balance fuel consumption, icing hazard avoidance and observation requirements, considering performance characteristics of the target vehicle.
Autonomous Airborne Geomagnetic Surveying and Target Identification
This project focuses on using total magnetic intensity measurements to search and identify magnetic anomalies in a predetermined area. The challenge is to use noisy sensor measurements to identify and classify these anomalies. This concept is integrated with a centralized occupancy based map search idea to apply to a team of autonomous agents.