Today’s robots tend to use one of three imaging techniques: cameras, LIDAR, or radar. Cameras see virtually the same views we do, meaning they’re susceptible to smoke, fog, light reflections, and other visual obstacles. LIDAR pulses laser signals to map out the robot’s surroundings, but that light scatters in smoke and reflects off of windows or glass walls. And while traditional radar can “see” through solid objects, the images it provides are extremely low-resolution, meaning it still falls short. Radio waves readily travel through smoke and glass, making them impervious to conditions that wouldn’t be safe for human eyes and to the shiny surfaces that make up many retail and office buildings.
In an effort to help robots see in tricky situations, researchers at the University of Pennsylvania are reaching for a fourth option: radio. Radio waves readily travel through smoke and glass, making them impervious to conditions that wouldn’t be safe for human eyes and to the shiny surfaces that make up many retail and office buildings. PanoRadar, the researchers’ experimental system, tests the viability of using this technology in place of more conventional techniques.
In an effort to help robots see in tricky situations, researchers at the University of Pennsylvania are reaching for a fourth option: radio. Radio waves readily travel through smoke and glass, making them impervious to conditions that wouldn’t be safe for human eyes and to the shiny surfaces that make up many retail and office buildings. PanoRadar, the researchers’ experimental system, tests the viability of using this technology in place of more conventional techniques.
Based on how long it takes for all these radio waves to bounce back—AKA how close or far away an object is—PanoRadar builds a heat map. Then, to create an image useful to humans, PanoRadar feeds that heat map into a machine learning algorithm, which constructs a 3D image of the system’s surroundings. The result is a high-resolution, panoramic view of an environment that would otherwise be difficult for human eyes, LIDAR, or radar to parse.
For the complete article CLICK HERE.
Note – If you have a lidar related news story that you would like us to promote, please forward to editor@lidarnews.com and if you would like to join the Younger Geospatial Professional movement click here
