A Model that Predicts the Material Recognition Performance of Thermal Tactile Sensing

摘要

Tactile sensing can enable a robot to infer properties of its surroundings, such as the material of an object. Heat transfer
\nbased sensing can be used for material recognition due to differences in the thermal properties of materials. While datadriven
\nmethods have shown promise for this recognition problem, many factors can influence performance, including
\nsensor noise, the initial temperatures of the sensor and the object, the thermal effusivities of the materials, and the
\nduration of contact. We present a physics-based mathematical model that predicts material recognition performance
\ngiven these factors. Our model uses semi-infinite solids and a statistical method to calculate an F1 score for the binary
\nmaterial recognition. We evaluated our method using simulated contact with 69 materials and data collected by a
\nreal robot with 12 materials. Our model predicted the material recognition performance of support vector machine
\n(SVM) with 96% accuracy for the simulated data, with 92% accuracy for real-world data with constant initial sensor
\ntemperatures, and with 91% accuracy for real-world data with varied initial sensor temperatures. Using our model, we
\nalso provide insight into the roles of various factors on recognition performance, such as the temperature difference
\nbetween the sensor and the object. Overall, our results suggest that our model could be used to help design better
\nthermal sensors for robots and enable robots to use them more effectively.