Autonomous systems can provide the Navy with valuable information about operating environments, such as aboard ships and on cluttered dock spaces. Small unmanned aircraft with cameras can provide the still images and video feeds required for Visit, Board, Search and Seizure (VBSS) operations, as well as data about ship coatings that can be used to reduce the cost of Fleet maintenance and improve readiness. Novel devices such as multimode fire scanners and micro-scale chemical sensors provide data in hazardous environments, allowing autonomous systems to participate in damage control and disaster recovery efforts. Effectively collecting this information autonomously requires explicitly defining the links between the mission, sensor platforms, and algorithms used for situational awareness and guidance.
Navy missions are often conducted in a mix of flat, open and cluttered spaces. This requires search techniques that are efficient when possible and robust when necessary, a level of adaptability that is common in nature and thus suggests a biologically inspired approach. Agent-based foraging algorithms may be expressed in terms of different combinations of forager and food source capabilities. These algorithms allow us to estimate the rate of foraging for highly mobile platforms as well as strategies for dealing with highly constrained motion. Engineered systems can apply these algorithms by properly accounting for agent mobility and control interfaces, define information as “food” using evidence grids, and ensure that sufficient communication and data processing are available.
The focus of this effort is to adapt techniques inspired by nature to information gathering in complex Navy environments. We refine the assumptions the algorithms make about the mission environment and platforms they direct in order to take a systems engineering approach to advancing the state of the art of robotic information gathering. The project is divided into four phases. In the first phase we develop an ontology for applying nature-inspired algorithms to autonomous robot platforms and missions for mobile autonomous teams. In the second phase we investigate the use of imaging sensors to search for information in cluttered environments, such as the deck of a ship during an interdiction operation, or a dock area. In the third phase we investigate information search with both imaging and non-imaging sensors such as chemical and aerosol detectors that would be relevant in damage control or disaster response scenarios. In the fourth phase we investigate how to best incorporate human knowledge to increase the probability of mission success and enhance situational awareness for the mission team.
Navy Center for Applied Research in Artificial Intelligence
Information technology Division
Naval Research Laboratory
Washington DC 20375
email: w5514 "at" itd.nrl.navy.mil