2D Shape Estimation of a Pneumatic‐Driven Soft Finger with a Large Bending Angle Based on Learning from Two Sensing Modalities
Jianxiong Hao, Zhiqiang Zhang, Shuxin Wang, Chaoyang Shi
Abstract
Shape Estimation Methods In article number 2200324, Chaoyang Shi and co-workers propose a shape estimation method that utilizes two sensing modalities (a customized fiber Bragg grating sensor and a commercial air-pressure sensor) for a pneumatically driven soft finger with a large bending angle range based on an artificial neural network model. This method is demonstrated to have high accuracy, strong robustness, and excellent transferability. The potential contact force detection ability of this method is also preliminary verified.
Topics & Concepts
Robustness (evolution)TransferabilityArtificial neural networkComputer scienceModalitiesBendingAcousticsArtificial intelligencePneumatic artificial musclesComputer visionStructural engineeringEngineeringMachine learningActuatorArtificial musclePhysicsBiochemistrySociologyLogitGeneChemistrySocial scienceGear and Bearing Dynamics AnalysisRobot Manipulation and LearningElevator Systems and Control