Close Range Inspection Using Novelty Detection Results

Authors:
Muhammad Fahmi Miskon;Andrew R. Russell
Affiliations:
Intelligent Robotic Research Center (IRRC), Monash University, Australia;Intelligent Robotic Research Center (IRRC), Monash University, Australia
Venue:
ICIRA '09 Proceedings of the 2nd International Conference on Intelligent Robotics and Applications
Year:
2009

Citing 5
Cited 0

Coverage for robotics – A survey of recent results

Annals of Mathematics and Artificial Intelligence
Embedded Robotics

Embedded Robotics
Performance Comparison of Bug Navigation Algorithms

Journal of Intelligent and Robotic Systems
Mapping normal sensor measurement using regions

ICIT '09 Proceedings of the 2009 IEEE International Conference on Industrial Technology
A novel electromagnetic signature sensor for mobile robots

RA '07 Proceedings of the 13th IASTED International Conference on Robotics and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a close range inspection strategy which requires minimum information from mobile novelty detection results. We propose the use of the estimated position of the detected anomaly to assist path planning for close range inspection. This strategy allows the robot to have more inspection coverage of the surrounding perimeter of the object which in turn will increase the performance of detection using sensors with limited work range. A down sampled laser range finder measurements are used to show that the strategy is robust and work with any range sensors including one that is noisy, inaccurate and has low angular resolution. Experimental results show that the close range inspection brings the robot near the perimeter of the anomalous object and also achieved total close range inspection coverage.