Reproducing human somatosensory networks in robots is crucial for agile operation, ensuring appropriate grasping force for objects of different softness and texture. Although artificial tactile perception has made progress in object recognition, accurately quantifying tactile perception to identify softness and texture remains challenging.

To solve this problem, a team led by Wu Huaping from Zhejiang University of Technology and Jiang Hanqing from Xihu University recently reported a method of using dual-mode tactile sensors to capture multidimensional static and dynamic stimuli, allowing for simultaneous quantification of softness and texture features. This method can achieve collaborative measurement of elastic coefficient and friction coefficient, providing a universal strategy for obtaining the adaptive clamping force necessary for scar free and anti slip interaction with fine objects. By equipping the sensor, the robotic arm has an accuracy rate of 98.44% in identifying pig mucosal features and stably grasps mature white strawberries that are difficult to distinguish visually, achieving reliable tissue palpation and intelligent picking. The proposed design concepts and comprehensive guidelines will provide insights for the development of tactile sensors and bring prospects to robotics technology.

Source: Sensor Expert Network