IEEE Robotics and Automation Letters · 2021 · 12 citations · 28 references
EngineeringComputer ScienceRobotics EngineeringHuman-robot InteractionMachine LearningRoboticsCollaborative ManipulationDeep LearningForce SensingGrasp DetectionIn-hand ManipulationMultimodal InteractionCollaborative GraspingData AugmentationGrasp Representation LearningIntention RecognitionMulti-object RecognitionMuscles Of The ForearmRobust Object Recognition
Applicable human-robot collaboration requires intuitive recognition of human intention during shared work. A grasped object such as a tool held by the human provides vital information about the upcoming task. In this letter, we explore the use of a wearable device to non-visually recognize objects within the human hand in various possible grasps. The device is based on Force-Myography (FMG) where simple and affordable force sensors measure perturbations of forearm muscles. We propose a novel Deep Neural-Network architecture termed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Flip-U-Net</i> inspired by the familiar U-Net architecture used for image segmentation. The Flip-U-Net is trained over data collected from several human participants and with multiple objects of each class. Data is collected while manipulating the objects between different grasps and arm postures. The data is also pre-processed with data augmentation and used to train a Variational Autoencoder for dimensionality reduction mapping. While prior work did not provide a transferable FMG-based model, we show that the proposed network can classify objects grasped by multiple new users without additional training efforts. Experiment with 12 test participants show classification accuracy of approximately 95% over multiple grasps and objects. Correlations between accuracy and various anthropometric measures are also presented. Furthermore, we show that the model can be fine-tuned to a particular user based on an anthropometric measure.
28
Auto-Encoding Variational Bayes
Diederik P. Kingma, Max Welling · UvA-DARE (University of Amsterdam) · 2013 · 15.6K citations · Full text
A survey on Image Data Augmentation for Deep Learning
Connor Shorten, Taghi M. Khoshgoftaar · Journal Of Big Data · 2019 · 12.4K citations · Full text
The GRASP Taxonomy of Human Grasp Types
Thomas Feix, Javier Romero, Heinz‐Bodo Schmiedmayer et al. · IEEE Transactions on Human-Machine Systems · 2015 · 994 citations
Progress and prospects of the human–robot collaboration
Arash Ajoudani, Andrea Maria Zanchettin, Serena Ivaldi et al. · Autonomous Robots · 2017 · 777 citations · Full text