Corrosion Detection using Robotic Vehicles in Challenging Environments

摘要

Navigation algorithms are presented that can be used to guide autonomous vehicles along a right of way to inspect poles or towers for corrosion, or to inspect enclosed spaces such as power substations. These algorithms use the combined methods of sensor feature extraction, PID control, dynamic window obstacle avoidance (DWA), and genetic algorithm (GA) solutions to the traveling-salesman problem (TSP). It is shown through simulation that these algorithms can be used to navigate a wheeled or tracked vehicle in a realistic environment. Results are shown using these algorithms on several types of vehicles in representative environments.