Autonomous Sonar Imaging

Autonomous underwater vehicles (AUVs) are commonly employed to perform imaging of underwater objects and environments for many Naval applications, ranging from target classification to mapping and inspection tasks. Because the image characteristics depend not only on the target class but also on the environmental conditions and imaging sensor modalities, it can be particularly challenging for an AUV to decide how to improve upon the image quality, based on existing information without human intervention.

Silvia Ferrari, Mechanical and Aerospace Engineering, is developing a new class of autonomous sensor path planning algorithms for imaging AUVs that are able to plan and react to the sonar images collected in real time.

To do this, Ferrari is developing theory and algorithms applicable to a broad class of autonomous imaging problems and sensing objectives. For example, the proposed theoretical framework will provide solutions for minimum-time or minimum-distance problems. The sonar-equipped AUV will maximize detection and classification performance or cover a set of targets or area of interest, while minimizing the energy required based on bathymetry and ocean currents information.

The image processing and planning algorithms developed in the project are being demonstrated on a high-fidelity simulation of AUVs. The AUVs are equipped with synthetic aperture sonar (SAS) developed and implemented by the Naval Surface Warfare Center (NSWC), Panama City, Florida. Ferrari is working closely with NSWC, as well as the Naval Undersea Warfare Center (NUWC), on the integration and interface of the sensor planning theory developed in the project with future Naval target recognition and scheduling algorithms for autonomous undersea sensing applications.

Cornell Researchers

Funding Received

$570 Thousand spanning 3 years

Sponsored by