Towards Learning to Detect and Predict Contact Events on Vision-based Tactile Sensors
arXiv:1910.03973
Abstract
In essence, successful grasp boils down to correct responses to multiple contact events between fingertips and objects. In most scenarios, tactile sensing is adequate to distinguish contact events. Due to the nature of high dimensionality of tactile information, classifying spatiotemporal tactile signals using conventional model-based methods is difficult. In this work, we propose to predict and classify tactile signal using deep learning methods, seeking to enhance the adaptability of the robotic grasp system to external event changes that may lead to grasping failure. We develop a deep learning framework and collect 6650 tactile image sequences with a vision-based tactile sensor, and the neural network is integrated into a contact-event-based robotic grasping system. In grasping experiments, we achieved 52% increase in terms of object lifting success rate with contact detection, significantly higher robustness under unexpected loads with slip prediction compared with open-loop grasps, demonstrating that integration of the proposed framework into robotic grasping system substantially improves picking success rate and capability to withstand external disturbances.
arXiv comment10 pages, 7 figures, Accepted to conference on Robot Learning (CoRL 2019)
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
- The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
- FingerVision Tactile Sensor Design and Slip Detection Using Convolutional LSTM Network
- Dense Tactile Force Distribution Estimation using GelSlim and inverse FEM
- Slip Detection: Analysis and Calibration of Univariate Tactile Signals
- Maintaining Grasps within Slipping Bound by Monitoring Incipient Slip