Self-supervised learning of object slippage: An LSTM model trained on low-cost tactile sensors
Paper i proceeding, 2020

This paper presents a combination of machine learning techniques for slip detection in grasping, based on temporal features collected by low-cost tactile sensors. A slippage is an event that is subsequent to prior micro-slippages that have occurred at hand-object contact. The method is based on the application of a sequential classification technique (a variant of recurrent neural networks known as long short-term memory networks or LSTMs), whereby time-series pressure readings from tactile sensors are classified as either slip or non-slip events. We also propose a novel method for autonomous labelling, removing the need for humans in the labelling process. Lastly, this paper proposes a new design for an adaptable wearable tactile sensing device that integrates non-expensive sensors. Our proposed method achieved high accuracy in the classification of slip and non-slip events, obtaining over 95% in offline classification and 89% in online classification using a Sawyer robot.


Ainur Begalinova

University of Manchester

Ross King

Chalmers, Biologi och bioteknik, Systembiologi

Barry Lennox

University of Manchester

Riza Batista-Navarro

University of Manchester

Proceedings - 4th IEEE International Conference on Robotic Computing, IRC 2020

191-196 9287944

4th IEEE International Conference on Robotic Computing, IRC 2020
Virtual, Taichung, Taiwan,


Robotteknik och automation

Datavetenskap (datalogi)

Datorseende och robotik (autonoma system)



Mer information

Senast uppdaterat