Adaptive exploration of benthic habitats using Gaussian processes

Currently, the majority of AUV missions follow fixed pre-programmed surveys. In exploration missions, the environment is unknown and pre-programmed surveys risk wasting limited resources on data with little scientific value. This risk can be mitigated by allowing autonomous agents to adapt their behaviour to suit the environment and the scientific goals of the survey. This paper presents a method for performing adaptive surveys which combines elements from the fields of perception, machine learning and planning. During exploration, a Gaussian mixture model is used to classify sensor data. The classes returned by the Gaussian mixture model are modelled spatially using a Gaussian process classifier. This spatial model is used to guide the agent's exploration into informative areas of the environment using value iteration. The advantage of using adaptive surveys and its potential for outperforming pre-programmed surveys is demonstrated in an example application.