A General Classifier of Whisker Data using Stationary Naive Bayes: Application to BIOTACT Robots Nathan F. Lepora 1 ,Charles Fox 1 , Mat Evans 1 , Ben Mitchinson 1 , Asma Motiwala 1 , J. Charlie Sullivan 2 , Martin J. Pearson 2 , Jason Welsby 2 , Tony Pipe 2 , Kevin Gurney 1 , and Tony J. Prescott 1 1 Adaptive Behaviour Research Group, Department of Psychology, University of Sheffield, UK. {n.lepora,c.fox,mat.evans,b.mitchinson,a.motiwala, k.gurney,t.j.prescott}@sheffield.ac.uk 2 Bristol Robotics Laboratory, Bristol Business Park, Bristol, UK. {charlie.sullivan,martin.pearson,jason.welsby,tony.pipe}@brl.ac.uk Abstract. A general problem in robotics is how to best utilize sensors to classify the robot’s environment. The BIOTACT project (BIOmimetic Technology for vibrissal Active Touch) is a collaboration between biolo- gists and engineers that has led to many distinctive robots with artificial whisker sensing capabilities. One problem is to construct classifiers that can recognize a wide range of whisker sensations rather than constructing different classifiers for specific features. In this article, we demonstrate that a stationary naive Bayes classifier can perform such a general classi- fication by applying it to various robot experiments. This classifier could be a key component of a robot able to learn autonomously about novel environments, where classifier properties are not known in advance. Keywords: BIOTACT, Active touch, Whiskers, Bayes’ rule, Classifier 1 Introduction Robotics has much to learn from the ways that animals are constructed, control their bodies and utilize their sensory capabilities [1]. All of the robots described in this article result from a long-term collaboration between biologists and engineers that aims to further understanding of biological vibrissal (whisker) systems and determine the potential applications to engineered systems such as autonomous robots [2]. Research into these systems was undertaken as part of a European Framework 7 project termed BIOTACT (BIOmimetic Technology for vibrissal Active Touch) [3]. The vibrissal sensing technology used in these robots was inspired by many aspects of biological whiskers [4], including their morphology, control and sensory information processing. This article focuses on how to process the sensory information from artificial vibrissal sensors to categorize and recognize the robot’s nearby environment.