Skip to Main Content
In recent years, autonomous robots have been increasingly deployed in unknown environments. In order to cope with the unknown, the capability to train autonomously the perception model of an environment is highly desirable. By developing proper sensing technology, this task can be significantly facilitated. In this paper, we explore the problem of artificial tactile perception, aimed at surface identification. To this end, we introduce a simple tactile probe based upon triple axis accelerometers. This tactile probe was tested on a large collection (28) of flat surfaces, using a controlled test bed. In a first set of experiments, we demonstrated the discrimination capabilities of the probe, by achieving a surface recognition rate of 96.7% with 1 second of data, using a Support Vector Machine classifier. We also demonstrate that similar results can be achieved without the need for ground truth or the actual number of surfaces using Dirichlet process mixture models, a Bayesian nonparametric approach. These two experiments indicate that tactile sensing is, thus, a potentially viable solution for autonomous surface identification.