In this paper, we present a methodology that uses an optical tactile sensor for efficient tactile exploration of embedded objects within soft materials. The methodology consists of an exploration phase, where a probabilistic estimate of the location of the embedded objects is built using a Bayesian approach. The exploration phase is then followed by a mapping phase which exploits the probabilistic map to reconstruct the underlying topography of the workspace by sampling in more detail regions where there is expected to be embedded objects. To demonstrate the effectiveness of the method, we tested our approach on an experimental setup that consists of a series of quartz beads located underneath a polyethylene foam that prevents direct observation of the configuration and requires the use of tactile exploration to recover the location of the beads. We show the performance of our methodology using ten different configurations of the beads where the proposed approach is able to approximate the underlying configuration. We benchmark our results against a random sampling policy.

We propose a framework for efficient tactile exploration and mapping for embedded rigid objects within matrices of soft materials using an optical tactile sensor. The method first generates a map that indicates the presence of hard objects below the surface (exploration), followed by a more thorough interaction in the areas of interest for an approximate reconstruction of the underlying topography (mapping).

Performance of the exploration phase showing the average over the ten bead configurations on the bottom and an example of the progression of one configuration on the top.