Litcius/Paper detail

Stable In-Grasp Manipulation with a Low-Cost Robot Hand by Using 3-Axis Tactile Sensors with a CNN

Satoshi Funabashi, Tomoki Isobe, Shun Ogasa, Tetsuya Ogata, Alexander Schmitz, Tito Pradhono Tomo, Shigeki Sugano

202020 citationsDOI

Abstract

The use of tactile information is one of the most important factors for achieving stable in-grasp manipulation. Especially with low-cost robotic hands that provide low-precision control, robust in-grasp manipulation is challenging. Abundant tactile information could provide the required feed-back to achieve reliable in-grasp manipulation also in such cases. In this research, soft distributed 3-axis skin sensors ("uSkin") and 6-axis F/T (force/torque) sensors were mounted on each fingertip of an Allegro Hand to provide rich tactile information. These sensors yielded 78 measurements for each fingertip (72 measurements from the uSkin and 6 measurements from the 6-axis F/T sensor). However, such high-dimensional tactile information can be difficult to process because of the complex contact states between the grasped object and the fingertips. Therefore, a convolutional neural network (CNN) was employed to process the tactile information. In this paper, we explored the importance of the different sensors for achieving in-grasp manipulation. Successful in-grasp manipulation with untrained daily objects was achieved when both 3-axis uSkin and 6-axis F/T information was provided and when the information was processed using a CNN.

Topics & Concepts

GRASPTactile sensorComputer visionComputer scienceArtificial intelligenceProcess (computing)Convolutional neural networkRobotTorqueRobotic handObject (grammar)PhysicsProgramming languageOperating systemThermodynamicsRobot Manipulation and LearningMuscle activation and electromyography studiesEEG and Brain-Computer Interfaces
Stable In-Grasp Manipulation with a Low-Cost Robot Hand by Using 3-Axis Tactile Sensors with a CNN | Litcius