Hari Vishnu

Luyuan Peng, Hari Vishnu, Mandar Chitre et al.

High-precision localization is pivotal in underwater reinspection missions. Traditional localization methods like inertial navigation systems, Doppler velocity loggers, and acoustic positioning face significant challenges and are not cost-effective for some applications. Visual localization is a cost-effective alternative in such cases, leveraging the cameras already equipped on inspection vehicles to estimate poses from images of the surrounding scene. Amongst these, machine learning-based pose estimation from images shows promise in underwater environments, performing efficient relocalization using models trained based on previously mapped scenes. We explore the efficacy of learning-based pose estimators in both clear and turbid water inspection missions, assessing the impact of image formats, model architectures and training data diversity. We innovate by employing novel view synthesis models to generate augmented training data, significantly enhancing pose estimation in unexplored regions. Moreover, we enhance localization accuracy by integrating pose estimator outputs with sensor data via an extended Kalman filter, demonstrating improved trajectory smoothness and accuracy.

Luyuan Peng, Mandar Chitre, Hari Vishnu et al.

Real-time visual feedback is essential for tetherless control of remotely operated vehicles, particularly during inspection and manipulation tasks. Though acoustic communication is the preferred choice for medium-range communication underwater, its limited bandwidth renders it impractical to transmit images or videos in real-time. To address this, we propose a model-based image compression technique that leverages prior mission information. Our approach employs trained machine-learning based novel view synthesis models, and uses gradient descent optimization to refine latent representations to help generate compressible differences between camera images and rendered images. We evaluate the proposed compression technique using a dataset from an artificial ocean basin, demonstrating superior compression ratios and image quality over existing techniques. Moreover, our method exhibits robustness to introduction of new objects within the scene, highlighting its potential for advancing tetherless remotely operated vehicle operations.

Luyuan Peng, Hari Vishnu, Mandar Chitre et al.

We investigate the performance of image-based pose regressor models in underwater environments for relocalization. Leveraging PoseNet and PoseLSTM, we regress a 6-degree-of-freedom pose from single RGB images with high accuracy. Additionally, we explore data augmentation with stereo camera images to improve model accuracy. Experimental results demonstrate that the models achieve high accuracy in both simulated and clear waters, promising effective real-world underwater navigation and inspection applications.

Dariush Kari, Hari Vishnu, Andrew C. Singer

Adapting pre-trained deep learning models to new and unknown environments remains a major challenge in underwater acoustic localization. We show that although the performance of pre-trained models suffers from mismatch between the training and test data, they generally exhibit a higher uncertainty in environments where there is more mismatch. Additionally, in the presence of environmental mismatch, spurious peaks can appear in the output of classification-based localization approaches, which inspires us to define and use a method to quantify the "implied uncertainty" based on the number of model output peaks. Leveraging this notion of implied uncertainty, we partition the test samples into sets with more certain and less certain samples, and implement a method to adapt the model to new environments by using the certain samples to improve the labeling for uncertain samples, which helps to adapt the model. Thus, using this efficient method for model uncertainty quantification, we showcase an innovative approach to adapt a pre-trained model to unseen underwater environments at test time. This eliminates the need for labeled data from the target environment or the original training data. This adaptation is enhanced by integrating an independent estimate based on the received signal energy. We validate the approach extensively using real experimental data, as well as synthetic data consisting of model-generated signals with real ocean noise. The results demonstrate significant improvements in model prediction accuracy, underscoring the potential of the method to enhance underwater acoustic localization in diverse, noisy, and unknown environments.