Anthony Levandowski's pronto.ai with claims of a hands-free, zero-disengagement cross-country trip from San Francisco to New York.

https://www.theguardian.com/technology/2018/dec/18/controversial-engineer-i-travelled-over-3000-miles-in-a-self-driving-car

https://medium.com/pronto-ai/pronto-means-ready-e885bc8ec9e9

Anthony Levandowski, the former Google engineer  who was at the center of a trade secrets lawsuit between Uber and Waymo, has taken his newest autonomous vehicle technology company pronto.ai out of stealth mode with a product aimed at the commercial trucking industry. Special introductory pricing of $4,999 per truck includes bolt-on installation of our camera-based system, driver training and more.

Levandowski built an automated car that drove from San Francisco to New York without any human intervention. The 3,099-mile journey started on 26 October on the Golden Gate Bridge, and finished nearly four days later on the George Washington Bridge in Manhattan. The car, a modified Toyota Prius, used only video cameras, computers and basic digital maps to make the cross-country trip.The system does not use laser-ranging lidars like those that Levandowski helped to develop at Waymo, Otto and Uber.

Pronto.AI’s driving technology uses only six video cameras, pointing to the front, side and rear of the vehicle, and each with a much lower resolution than those found in modern smartphones. Images from the cameras are fed to the trunk, where a computer is running two neural networks: artificial intelligence systems that can speedily process large quantities of data.

One network recognizes lane markings, signs, obstacles and other road users, and extracts information about their position and speed. The second takes that information and controls the driving, using digital signals and mechanical actuators for the throttle, brake and steering.

A seventh camera faces inwards, watching the human driver to ensure that they are keeping their eyes on the road. Should the driver look away, nod off, or pull out a cellphone, the system sounds increasingly strident alerts and could ultimately be programmed to stop the vehicle.