| Summary: | Tactile perception of the human hand plays a critical role in everyday object recognition. The development of multimodal tactile sensors that can sense stimuli with high sensitivity and low cost is important for intelligent perception. In this article, a multimodal tactile sensor attached on a mechanical hand is studied, which consists of a magnetostrictive tactile sensor, a temperature sensor, and a flex sensor. By applying multimodal tactile sensors to a robotic hand to grasp objects, the output voltage of the magnetotactictive tractile tactile sensor can be used for object shape and softness recognition. The bending angle of the knuckles can be obtained by the flex sensor for object contour size recognition, while the temperature distribution of objects can be obtained through temperature sensors. In order to improve the accuracy, a 1-D convolutional neural network-extreme learning machine (CNN-ELM) pattern recognition model based on the combination of 1-D CNN and ELM is presented, with the accuracy of 97.14% for 21 objects. This multimodal tactile sensor has promising applications in the field of tactile intelligence and humanoid robotics.
|
|---|