Augmenting Machine Learning with Simulated Data for Robust Undersea Sensing with Synthetic Aperture Sonar
Abstract
Machine learning (ML), specifically deep learning, works well when abundant amounts of labeled data are available for training. However, in many environments, like undersea remote sensing, obtaining abundant amounts of labeled data is financially and logisticallyexpensive. To overcome this hurdle, this work proposes the use of synthetic data to bridge the lack of data gap to improve machine learning performance for undersea remote sensing tasks where little labeled data is often available. Specifically, we work with simulated data provided by the University of Bath to understand the tradeoffs in ML performance versus simulation fidelity, understand the shortcomings of the simulator and determine the #missing physics# of its model, and understand the advantages of training with purely simulated data in a domain-transfer / multi-task learning framework since labels are present and abundant for several aspects of the simulated scene including object orientation, seafloor environment, distance from sensor, and bathymetry; all scene parameterswhich may be used in during the machine learning training process. Finally, we will investigate the use of reinforcement learning in conjunction with the simulator to teach the learner the ability to manipulate the simulator as to reproduce an input real sonar image of interest thus inverting the real sonar image into the simulator parameter space. Success of our proposed efforts will help the Navy understand how to best leverage simulated data in improving current machine learning systems where labeled training data is sparse, and identify gaps in physical acoustic models which may be resolved in future work in order to generate more fidelitous data for physical simulation, personnel training, and machine learning purposes.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Nov 08, 2024
- Source ID
- N000142412444
Entities
People
- Isaac D. Gerg
Organizations
- Kitware
- Office of Naval Research
- United States Navy