Strategies for autonomous robots to inspect pavement distresses

The distress survey is an important task for pavement maintenance and rehabilitation (M&R) activities. As distress surveys require tremendous human resources, many investigators have begun to develop automatic inspection methods with the aim of increasing the efficiency and accuracy of inspections. After assessment of distress surveys on pavements using an autonomous robot (P3-AT), this research aims at developing motion strategies for executing distress surveys using robots under project-level practices. Three motion strategies were specifically developed: (1) Strategy I: random survey (R); (2) Strategy II: random survey with map recording (R + M); (3) Strategy III: random survey with map recording and vision guidance (R + M + V). To validate these three strategies, we developed a test field in a virtual environment. The test field included five distress types, including an alligator crack, a small patching, a pothole, a rectangular manhole and a circular manhole. We also developed a virtual robot to navigate the test field autonomously. The three survey strategies were then implemented by the virtual robot and their performances were compared with the current traffic-directional survey strategy.

Research Highlights
► This research aimed to develop strategies for robotics pavement survey.
► Three strategies, (1) random survey (R strategy), (2) random survey with map recording (R+M strategy) and (3) random survey with map recording and vision guidance (R+M+V strategy), have been developed.
► After testing the strategies in a realistic virtual environment, we found strategies can identify more pavement distresses than traditional survey method does.
► The performance of the strategies rank from the best is R+M+V, R+M and R strategy.