Google Driverless Car
Google driverless car is powered by artificial intelligence that utilizes the input from the video cameras inside the car, a sensor on the vehicle’s top, and some radar and position sensors attached to different positions of the car. A Velodyne 64-beam laser allows the vehicle to generate a detailed 3D map of its environment. The car then takes these generated maps and combines them with high-resolution maps of the world, producing different types of data models that allow it to drive itself. Legislation has been passed in four U.S. states and Washington, D.C. allowing driverless cars. In August 2012, the team announced that they have completed over 300,000 autonomous-driving miles (500,000 km) accident-free. The latest prototype cannot handle heavy rain and snow-covered roads. Google’s self-driving car team will continue to test the vehicle on a private track in California, where it works its way around traffic lights and mock construction zones. Google has said it’s interested in launching a pilot program for the cars in the coming years.
As of August 28, 2014 the latest prototype cannot “handle heavy rain and snow-covered roads“. Functionally it can go at sluggish speeds when crossing an unmarked 4-way stop due to the algorithms of the computer taking extra precaution. There are also other limitations on discerning objects such as trash and debris that can unnecessarily veer the vehicle. Additionally Chris Urmson of Google has said that the lidar technology cannot spot potholes or humans, such as a police officer, signaling the car to stop.
The vehicles are unable to recognize temporary traffic signals. They have not proven themselves in snow or rain. They are also unable to navigate through parking lots. Vehicles are unable to differentiate between pedestrian and policeman or between crumpled up paper and a rock. Google projects having these issues fixed by 2024.