The Massachusetts Institute of Technology has announced the development of a new system that will allow self-driving cars to better see the corners around them. The system can sense small changes in the shadows of the ground to determine if a moving object is coming from a corner. This shadowCam system uses computer vision technology to detect and classify changes in ground shadows. ShadowCam uses a sequence of video frames from the camera to target specific areas, such as floors around corners. Changes in frame-by-frame lighting may indicate that something is moving toward or away from the camera.
The Massachusetts Institute of Technology says self-driving cars could one day use the system to quickly avoid collisions with vehicles or pedestrians around the corner of buildings or parked in parking lots. The Massachusetts Institute of Technology says future robots will also be able to use the system to navigate inside buildings. When approaching vehicles are detected and parked, the system is superior to traditional lidar, the researchers said. Lidar can only detect visible objects, and MIT’s system is more than half a second faster than lidar.
Half a second doesn’t seem to improve much, but it only takes a fraction of a second to avoid hitting pedestrians or another car. The additional warning provided by the MIT system can allow self-driving cars to adjust their route or slow down. So far, the new system has only been tested indoors.