Multi-modal Obstacle Avoidance in USVs via Anomaly Detection and Cascaded Datasets

We introduce a novel strategy for obstacle avoidance in aquatic settings, using anomaly detection for quick deployment of autonomous water vehicles in limited geographic areas. The unmanned surface vehicle (USV) is initially manually navigated to collect training data. The learning phase involves three steps: learning imaging modality specifics, learning the obstacle-free environment using collected data, and setting obstacle detector sensitivity with images containing water obstacles. This approach, which we call cascaded datasets, works with different image modalities and environments without extensive marine-specific data. Results are demonstrated with LWIR and RGB images from river missions.