A Training Framework of Robotic Operation and Image Analysis for Decision-making in Bridge Inspection and Preservation

Inspection and preservation of existing transportation infrastructure to extend their service life is an effective way of mitigating the pressure of steadily growing transportation demands on the aging infrastructure. Their current practice, though, represents one of the most costly operations in state departments of transportation. The INSPIRE University Transportation Center will develop a remotely-controlled robotic platform that helps with these labor-intensive tasks and allows engineers to focus on decision-making processes. An important mission of INSPIRE is to leverage users’ capability of implementing, and interacting with, the robotic platform. Therefore, a long-term plan has been made to create a framework of training engineers and policy makers as well as new workforce on robotic operation and image analysis for the inspection and maintenance of transportation infrastructure. The proposed project, as a component of the plan, involves the prototyping of such a framework based on camera-based bridge inspection and robot-based maintenance. A training framework will be developed through an integration of the following components: (1) a set of training modules to use robotic systems for bridge inspection and maintenance; (2) data processing and pattern recognition algorithms in a semi-supervised way with engineers’ injection; (3) summary and visualization of processed inspection data, recognized patterns, and other research findings; and (4) a set of learning modules, which can be arranged as a customizable training plan for individuals, to help users analyze and use the vision-based materials in their decision making for bridge inspection and preservation. The overall goal of the project is to create a framework of training engineers and policy makers on robotic operation and image analysis for the inspection and preservation of transportation infrastructure. Specifically, the project aims to (1) provide the method for collecting camera-based bridge inspection data and the algorithms for data processing and pattern recognitions; and (2) create tools for assisting and training users on visually analyzing the processed image data and recognized patterns for inspection and preservation decision-making. Scope of Work in Year 1. The focus of this project for the first year is to deliver a prototype of the training framework. Following the proposed methods and approaches, five tasks will be performed to achieve the project objective: (1) collect bridge image data using cameras and annotate sample images; (2) process image data and develop pattern recognition algorithms; (3) summarize & visualize processed image data and discovered patterns; (4) develop a training tool for image data analysis and understanding; and (5) test and validate the prototype framework.