Interactive learning of visually symmetric objects

Authors:
Wai Ho Li;Lindsay Kleeman
Affiliations:
Intelligent Robotics Research Centre, Department of Electrical and Computer Systems Engineering, Monash University, Clayton, Victoria, Australia;Intelligent Robotics Research Centre, Department of Electrical and Computer Systems Engineering, Monash University, Clayton, Victoria, Australia
Venue:
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Year:
2009

Citing 4
Cited 2

Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Evaluation of Features Detectors and Descriptors Based on 3D Objects

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Semi-autonomous Learning of Objects

CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Interactive segmentation for manipulation in unstructured environments

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation

Segmentation and modeling of visually symmetric objects by robot actions

International Journal of Robotics Research
Manipulator and object tracking for in-hand 3D object modeling

International Journal of Robotics Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a robotic system that learns visual models of symmetric objects autonomously. Our robot learns by physically interacting with an object using its end effector. This departs from eye-in-hand systems that move the camera while keeping the scene static. Our robot leverages a simple nudge action to obtain the motion segmentation of an object in stereo. The robot uses the segmentation results to pick up the object. The robot collects training images by rotating the grasped object in front of a camera. Robotic experiments show that this interactive object learning approach can deal with topheavy and fragile objects. Trials confirm that the robot-learned object models allow robust object recognition.