Autonomous Adaptive Underwater Exploration using Online Topic Modeling

Exploration of underwater environments, such as coral reefs and ship wrecks, is a difficult and potentially dangerous tasks for humans, which naturally makes the use of an autonomous robotic system very appealing. This paper presents such an autonomous system, and shows its use in a series of experiments to collect image data in an underwater marine environment. We presents novel contributions on three fronts. First, we present an online topic-modeling based technique to describe what is being observed using a low dimensional semantic descriptor. This descriptor attempts to be invariant to observations of different corals belonging to the same species, or observations of similar types rocks observed from different viewpoints. Second, we use the topic descriptor to compute the surprise score of the current observation. This is done by maintaining an online summary of observations thus far, and then computing the surprise score as the distance of the current observation to the summary, in the topic space. Finally, we present a novel control strategy for an underwater robot thats allows for intelligent traversal; hovering over surprising observations, and swimming quickly over previously seen corals and rocks. Exploration, in the context of robotics, has been studied before. Work has been done on autonomous mapping of challenging environments [19], [12], frontier expansion [22], minimizing uncertainty [21], and utility based exploration[8]. Our focus is instead on traversing an environment similar to how a tourist might do so in a new city; stopping and recording any surprising sights, while moving fast when