Abstract
Tactile sensing is an instrumental modality of robotic manipulation, as it provides information that is not accessible via remote sensors such as cameras or lidars. Touch is particularly crucial in unstructured environments, where the robot's internal representation of manipulated objects is uncertain. In this study we present the sensorization of an existing artificial hand, with the aim to achieve fine control of robotic limbs and perception of object's physical properties. Tactile feedback is conveyed by means of a soft sensor integrated at the fingertip of a robotic hand. The sensor consists of an optical fiber, housing Fiber Bragg Gratings (FBGs) transducers, embedded into a soft polymeric material integrated on a rigid hand. Through several tasks involving grasps of different objects in various conditions, the ability of the system to acquire information is assessed. Results show that a classifier based on the sensor outputs of the robotic hand is capable of accurately detecting both size and rigidity of the operated objects (99.36 and 100% accuracy, respectively). Furthermore, the outputs provide evidence of the ability to grab fragile objects without breakage or slippage e and to perform dynamic manipulative tasks, that involve the adaptation of fingers position based on the grasped objects' condition.
Highlights
The sense of touch is a key sensory modality of prehensile manipulation
Since the trials of the Material Task were performed using the static controller, selecting a constant velocity for fingers movements, such condition allowed for estimation of the hardness of the different materials via the temporal variation of the Bragg wavelength (100% accuracy using the proposed classifier)
The results presented some peaks related to the phase of inversion of the motion of the stage, as highlighted from the NRMSE values, which were based on the entire raw dataset and the interquartile range
Summary
The sense of touch is a key sensory modality of prehensile manipulation. Humans can perceive object properties such as size, hardness, temperature, contour, etc. Information arises from the multiple receptors available within the human skin, especially across hand and fingers (Johansson and Vallbo, 1979; Johansson et al, 1982). The hand partially occludes the object from sight. Tactile sensing enables measurements to be obtained in areas that are inaccessible through vision. Prior behavioral studies have demonstrated the tactile reliance of human manipulation, for both simple grasping and dexterous manipulation (Johansson and Flanagan, 2009). The successful automation of complex human-like manipulative tasks depends
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call