State-of-the-art sensors mounted on electric vehicles, both self-driving and human-driven, that can monitor the city by detecting the condition of the road surface. This is what the ENEA Laboratory of Robotics and Artificial Intelligence has developed for the Smart Road project under the Electric System Research program funded by the Ministry of Environment and Energy Security. Two different sensors have been developed to analyze the state of the road surface: the first uses a laser-based LIDAR (Light Detection and Ranging) to measure geometric distances with remarkable accuracy, while the second consists of a camera mounted frontally on the vehicle that analyzes the video stream using Artificial Intelligence techniques. The second sensor uses a deep neural network trained to detect and recognize defects in the camera video Stream. It makes it possible to see objects that cannot be measured by LIDAR such as lattice cracks or all those defects attributable to painted elements on the asphalt (crosswalks or faded roadway lines). Both sensors work in real time and can be used for urban monitoring: geo-referenced road defect information is sent to the smart city manager to map road conditions and plan any repairs. In addition, the self-driving electric vehicle used for the trial is also equipped with an air quality sensor that records particulate matter concentrations and sends data to process high-resolution pollutant maps in real time. The development of systems for analyzing the sound environment is currently underway.
|