Waze is an example of a widely-used system that uses crowd-sourced human  reporting to share knowledge about road conditions. In this video, we  present a demo of LiveMap on the streets of Pittsburgh.   LiveMap is a  research system built at Carnegie Mellon University that is conceptually similar to Waze, but avoids the driver distraction that is inherent in human reporting from a single-occupant vehicle.

LiveMap uses edge computing to perform video analytics close to the point of data capture.  Computer vision algorithms running  on an in-vehicle computer (called a "vehicular cloudlet") continuously analyze video  streams from one or more cameras mounted on that vehicle.     Observations from these algorithms are transmitted over a 4G LTE wireless network  to a central collection point (called a "zone  cloudlet"), where the reports from many vehicles are synthesized and disseminated.  

Kevin Christensen, Christoph Mertz, Padmanabhan Pillai, Martial Hebert,  and Mahadev Satyanarayanan. 2019. Towards a Distraction-free Waze. In Proceedings of the 20th International Workshop on Mobile Computing Systems and Applications (HotMobile '19). ACM, New York, NY, USA, 15-20. DOI: https://doi.org/10.1145/3301293.3302369