A triboelectric-inductive hybrid tactile sensor for highly accurate object recognition

Tactile sensors can enable a robotic manipulator to identify the object in contact. However, due to the dynamics and diversity of target objects, as well as the complexity of real environment, accurate recognition of objects by existing tactile sensors has been very challenging. This paper proposes a hybrid tactile sensor that integrates a triboelectric active sensing unit with an electromagnetic inductance transducer. The triboelectric signal relates strongly to the specific charge condition of the surface material of a target object, while the inductive signal manifests the electromagnetic characteristics at a certain depth inside the object. With the help of machine learning, the triboelectric signals and inductive signals can be used for object identification. We demonstrate a robotic gripper with random operation settings can recognize eight different fruits with an accuracy as high as 98.75%. Furthermore, the hybrid sensor can recognize objects packaged in different ways. The recognition ac-curacy of four different fruits in three different packages can reach 95.93%. This study demonstrates the po-tential of hybrid tactile sensor to improve the artificial intelligence of robots, in particular their ability to distinguish objects in complex settings and sorting them effectively.

Automated summary

This paper proposes a hybrid tactile sensor that integrates the triboelectric active sensing unit with an electromagnetic inductance transducer for object identification. With the help of machine learning, the sensor can accurately recognize different fruits and objects packaged in different ways. This study demonstrates the potential of the hybrid tactile sensor to improve the artificial intelligence of robots in complex settings.