AI-enabled software tests autonomous navigation for future Navy USVsNews
February 28, 2023
WOBURN, Mass. Artificial intelligence/machine learning (AI/ML) engineering company Scientific Systems Company, Inc. (SSCI) paired up with MIT Sea Grant to demonstrate AI for unmanned surface vehicles (USV) using the Navy's Unmanned Maritime Autonomy Architecture (UMAA).
According to the SSCI account, the joint SSCI/MIT software combined computer vision, waypoint navigation, obstacle avoidance, vehicle control, and mission management into a fully integrated and orchestrated autonomy stack, which the team demonstrated on the Charles River (Massachusetts) in October 2022 using MIT's fully autonomous Boston Whaler boat.
MIT Sea Grant is a U.S. government-assisted program within the university's department of mechanical engineering that focuses on innovative technologies and ocean engineering.
During the demonstration, the autonomous Boston Whaler safely navigated the busy Charles River while sterring around another vessel using COLREG maneuvers [International Regulations for Preventing Collisions at Sea] to avoid a collision. The SSCI account notes that MIT provided open-source maneuver operations software through MOOS-IvP (Mission Oriented Operating Suite -- Interval Programming), performing local waypoint navigation, COLREGs and vehicle control. For its part, SSCI provided the mission-management software, which performed high-level reasoning, route planning, and executive oversight similar to human operator functions, plus software that enabled the autonomous Boston Whaler to sense its surroundings with fused onboard sensors, including an electro-optical camera, lidar, and radar.
These new capabilities, say SSCI officials, is important for the Navy's UMAA, an initiative described as aiming "to promote the development of common, modular, and scalable software for Unmanned Maritime Vehicles (UMVs)" and reduce costs for acquisition programs and accelerate the fielding of autonomous systems.