Mechanical features based object recognition

TL;DR

This paper introduces a real-time object recognition framework for robots that uses multiple mechanical properties derived from haptic signals, achieving high accuracy and outperforming traditional statistical methods.

Contribution

It proposes a novel approach combining multiple mechanical properties and dual Kalman filtering for robust, real-time object recognition in robotics.

Findings

Achieved 98.18% recognition accuracy with 20 objects.

Using all four mechanical properties improves recognition over statistical parameters.

Mechanical properties are identified in real-time and enhance robustness.

Abstract

Current robotic haptic object recognition relies on statistical measures derived from movement dependent interaction signals such as force, vibration or position. Mechanical properties that can be identified from these signals are intrinsic object properties that may yield a more robust object representation. Therefore, this paper proposes an object recognition framework using multiple representative mechanical properties: the coefficient of restitution, stiffness, viscosity and friction coefficient. These mechanical properties are identified in real-time using a dual Kalman filter, then used to classify objects. The proposed framework was tested with a robot identifying 20 objects through haptic exploration. The results demonstrate the technique's effectiveness and efficiency, and that all four mechanical properties are required for best recognition yielding a rate of 98.18 $\pm$ 0.424 %. Clustering with Gaussian mixture models further shows that using these mechanical properties results in superior recognition as compared to using statistical parameters of the interaction signals.