Grasp stability assessment through unsupervised feature learning of tactile images

/in , , /by
Grasp stability assessment through unsupervised feature learning of tactile images

Cockbum, Deen and Roberge, Jean Philippe and Le, Thuy Hong Loan and Maslyczyk, Alexis and Duchaine, Vincent

Proceedings – IEEE International Conference on Robotics and Automation 2017

Abstract : Grasping tasks have always been challenging for robots, despite recent innovations in vision-based algorithms and object-specific training. If robots are to match human abilities and learn to pick up never-before-seen objects, they must combine vision with tactile sensing. This paper present a novel way to improve robotic grasping: by using tactile sensors and an unsupervised feature-learning approach, a robot can find the common denominators behind successful and failed grasps, and use this knowledge to predict whether a grasp attempt will succeed or fail. This method is promising as it uses only high-level features from two tactile sensors to evaluate grasp quality, and works for the training set as well as for new objects. In total, using a total of 54 different objects, our system recognized grasp failure 83.70% of time.

You might also like
Audio-visual fusion for emotion recognition in the valence-arousal space using joint cross-attention
A low-cost parallel K-means VQ algorithm using cluster computing
Query-by-example word spotting using multiscale features and classification in the space of representation differences
Experimental Study of Subcritical Dividing Flow in an Equal-Width, Four-Branch Junction
Video encoder and motion estimation apparatus therefor with rate-constrained search ordering of candidate blocks
A Autenticação de Manuscritos Aplicada à Análise Forense de Documentos
Off-line signature verification using directional PDF and neural networks
Pedestrian Detection Based on Deep Learning