Visual task outcome verification using deep learning
Ozgür Erkent, Dadhichi Shukla, Justus Piater
Abstract
Manipulation tasks requiring high precision are difficult for reasons such as imprecise calibration and perceptual inaccuracies. We present a method for visual task outcome verification that provides an assessment of the task status as well as information for the robot to improve this status. The final status of the task is assessed as success, failure or in progress. We propose a deep learning strategy to learn the task with a small number of training episodes and without requiring the robot. A probabilistic, appearance-based pose estimation method is used to learn the demonstrated task. For real-data efficiency, synthetic training images are created around the trajectory of the demonstrated task. We show that our method can estimate the task status with high accuracy in several instances of different tasks, and demonstrate the accuracy of a high-precision task on a real robot.
BibTeX
@inproceedings{iros2017_visualtaskoutcom,
title = {Visual task outcome verification using deep learning},
author = {Ozgür Erkent and Dadhichi Shukla and Justus Piater},
booktitle = {IROS 2017},
year = {2017}
}