ROBO-SPECT - ROBotic System with Intelligent Vision and Control for Tunnel Structural INSPECTion and Evaluation
Overview
Background & policy context:
A large number of underground transportation tunnels have been in operation for more than half a century and are in dire need for inspection, assessment and maintenance. Things are bad to the point that there have been a number of failures resulting in collapses in tunnels in recent years which highlighted the need for better ways to inspect and assess the tunnel stability of in-service tunnels.
ROBO-SPECT adapts and integrates recent research results in robotics, computer vision and non-destructive sensing in an innovative, integrated, robotic system that automatically scans the intrados for potential defects on the surface and detects and measures radial deformation in the cross-section, distance between parallel cracks, cracks and open joints that impact tunnel stability, with mm accuracies. This permits in one pass, both the inspection and structural assessment of tunnels.
Objectives:
The main goal of the project is to develop an autonomous robotic inspection and assessment system for tunnels that will include: (a) a computer vision system that will detect structural defects and colour changes at the concrete lining intrados, (b) a sensor system that will measure the depth of cracks and the depth of opening of joints of interest with an accuracy of 1 mm and the width of these cracks and openings with an accuracy of 0.1 mm and (c) laser equipment able to measure radial deformation with an accuracy of 1 mm, while it will be integrated with software that based on the above measurements will assess the structural condition of the inspected tunnel.
The ROBO-SPECT system will be tested at a research infrastructure of tunnels in Switzerland and at actual tunnels in UK and Greece.
Methodology:
ROBO-SPECT proposes specialised work to adapt, extent and validate recent exploitable research results that will provide the required functionalities and intelligence to an automatic, multi component and multi-degree of freedom robotic system that will credibly, efficiently and inexpensively perform both inspection and assessment of the tunnel in a single pass.
The work includes the following steps:
- Definition of user requirements and system architecture.
- Development of robotic navigation and intelligent positioning controllers.
- Development of the computer vision system for real time defect detection.
- Development of ultrasonic sensors for the measurement of width and depth of cracks and openings.
- Structural assessment based on measurements at the intrados.
- Integration of the whole system.
- Field evaluation and benchmarking of the integrated system at a research infrastructure of tunnels in Switzerland and at actual tunnels in UK and Greece.
Share this page