Material classification based on thermal properties — A robot and human evaluation

Abstract

The surface properties of an object and the environment in which it is located are important for robot grasping and manipulation. Physical contact with an object using tactile sensors can enable the retrieval of detailed information about the object, i.e. compressibility, surface texture and thermal properties. This paper describes a system that classifies materials based on their thermal properties alone, minimising the amount of manipulation required. Following acquisition of data from a sophisticated tactile sensor, the system uses an Artificial Neural Network (ANN) to classify materials based on representations of their thermal properties. The system was compared with human performance in the task of classifying materials and was found to perform better.