Interpretable Underwater Diver Gesture Recognition
This work addresses a domain-specific problem for underwater robotics and human-robot interaction, with incremental improvements in accuracy and interpretability.
The paper tackles underwater gesture recognition for diver-AUV interaction, achieving 98.01% accuracy on a specific dataset, and improves interpretability using XAI techniques.
In recent years, usage and applications of Autonomous Underwater Vehicles has grown rapidly. Interaction of divers with the AUVs remains an integral part of the usage of AUVs for various applications and makes building robust and efficient underwater gesture recognition systems extremely important. In this paper, we propose an Underwater Gesture Recognition system trained on the Cognitive Autonomous Diving Buddy Underwater gesture dataset using deep learning that achieves 98.01\% accuracy on the dataset, which to the best of our knowledge is the best performance achieved on this dataset at the time of writing this paper. We also improve the Gesture Recognition System Interpretability by using XAI techniques to visualize the model's predictions.