Multidimensional Time-Series Shapelets Reliably Detect and Classify Contact Events in Force Measurements of Wiping Actions

Abstract

The vision of service robots that autonomously manipulate objects as skillfully and flexibly as humans is still an open challenge. Findings from cognitive psychology suggest that the human brain structures manipulation actions along representations of contact events and their perceptually distinctive sensory signals. In this letter, we investigate how to reliably detect and classify contact events during robotic wiping actions. We present an algorithm that learns the distinct shapes of force measurements during contact events using multidimensional time-series shapelets. We evaluate our approach on a dataset consisting of 460 real-world robot wiping episodes that we collected using a table-mounted robot with a wrist-mounted force/torque sensor. Our approach shows good performance with tenfold cross validation yielding 97.5% precision and 99.3% recall, and can also be used for online contact event detection and classification.