{"title":"Multi-sensory fusion of wearable sensors for automatic grasping and releasing with soft-hand exoskeleton","authors":"Guan Erjiage, John Nassour, Gordon Cheng","doi":"10.1109/RoboSoft55895.2023.10122031","DOIUrl":null,"url":null,"abstract":"This paper presents a fully integrated soft-hand exoskeleton enabling automated grasping and releasing functions thanks to the multi-sensory fusion. We use enfolded soft textile actuators to assist the hand, IMU sensors for the arm and hand orientations, and customized soft sensors for tactile feedback from the fingers. We propose a state machine controller that uses the information from tactile sensors and the IMUs to switch between different states to trigger grasping and releasing. The control strategy requires no additional user input; it is designed for meal-eating scenarios. Ten healthy participants instructed not to move their hands tested the system performing 190 trials on five tasks: pouring, drinking, eating a fruit, using a fork, and using a spoon. Objects are randomly placed in four different locations in front of the participant. 97.4% of the trials were successfully accomplished. Furthermore, 78.1% grasps and 83.8% releases are triggered by the first attempt. Compared with no assistant condition of a healthy hand, the system reduced 32.2% of muscle activities and required 2.57 more times to finish the task.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RoboSoft55895.2023.10122031","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper presents a fully integrated soft-hand exoskeleton enabling automated grasping and releasing functions thanks to the multi-sensory fusion. We use enfolded soft textile actuators to assist the hand, IMU sensors for the arm and hand orientations, and customized soft sensors for tactile feedback from the fingers. We propose a state machine controller that uses the information from tactile sensors and the IMUs to switch between different states to trigger grasping and releasing. The control strategy requires no additional user input; it is designed for meal-eating scenarios. Ten healthy participants instructed not to move their hands tested the system performing 190 trials on five tasks: pouring, drinking, eating a fruit, using a fork, and using a spoon. Objects are randomly placed in four different locations in front of the participant. 97.4% of the trials were successfully accomplished. Furthermore, 78.1% grasps and 83.8% releases are triggered by the first attempt. Compared with no assistant condition of a healthy hand, the system reduced 32.2% of muscle activities and required 2.57 more times to finish the task.