Wall-climbing Robot for Non-Destructive Evaluation (NDE)

First, CCNY Robotics Lab proposed a new generation of wall climbing robot, called Rise-Rover, to perform impact-echo (IE) acoustic inspection using a machine learning approach to do signal analysis. The wall climbing robot system structure is illustrated below:


This is an image

We propose a machine learning approach to learn the patterns of the waveforms and spectra (especially the latter) that provide information about the existence and locations of flaws (cracks, voids, delamination, etc.) in concrete plates:

This is an image

The field data collection was conducted at a bridge located at Flushing 149st between Barton Ave and 41st Ave, New York City, and the detection result of a sample is:

This is an image

The work of this research has been summarized and published in:

  • B. Li, K. Ushiroda, L. Yang, Q. Song, J. Xiao. Wall-climbing robot for non-destructive evaluation using impact-echo and metric learning SVM. International Journal of Intelligent Robotics and Applications. 2017