Charles River Analytics was awarded a ~$400K follow-on contract from the National Oceanic and Atmospheric Administration (NOAA) to continue development of SOUSAPHONE, a software package that enables uncrewed aircraft system (UAS) swarms to safely conduct semi-autonomous wildlife survey operations.
UASs have an important and ever-growing role in support of government, military, commercial, and scientific missions. To minimize the risk to human scientific observers when accessing dangerous or hard-to-reach environments, it’s safer to dispatch UASs. UAS swarms operating as part of a SOUSAPHONE-enabled team use autonomous navigation and robust, state-of-the-art image processing algorithms for marine mammal detection and classification. SOUSAPHONE is specifically designed to detect pinnipeds, the group of animals that includes walruses and seals.
SOUSAPHONE applies artificial intelligence and machine learning (AI/ML) in computer vision to enable safe, semi-autonomous, beyond visual line of sight (BVLOS) operations in challenging environments, such as the Alaskan Arctic.
“With SOUSAPHONE, we’ve applied the autonomous robotic capabilities from our defense AI portfolio to support environmental research,” said Daniel Stouch, Director of Space and Airborne Systems in Charles River’s Sensing, Perception, and Applied Robotics Division, and Principal Investigator for the SOUSAPHONE effort. “We’re excited to continue enhancing our swarm autonomy capabilities to advance environmental awareness and conservation.”
The SOUSAPHONE framework will improve wildlife accessibility and surveying accuracy, reduce risk to humans, and develop autonomy advancements that support wildlife conservation.
This work was funded by NOAA, U.S. Department Commerce under award NA21OAR0210109. The statements, findings, conclusions, and recommendations are those of the author(s) and do not necessarily reflect the views of NOAA or the U.S. Department of Commerce.