One of the obstacles hindering the mass adoption of drones is the inefficiency of existing methods
The main problem is thatroad events of interest, including accidents, are all too rare. Thus, systems can require hundreds of millions (sometimes billions) of kilometers to demonstrate the required safety performance. To date, Waymo has modeled only 15 billion km. Therefore, the work carried out by Dr. Liu and his team at the University of Michigan is aimed at creating a natural and competitive driving environment (NADE),
Liu built a simulated driving environment,using large-scale driving data that was collected by the University of Michigan Transportation Research Institute (UMTRI). In this environment, "background" cars (those that simulate road traffic) are trained to perform certain hostile maneuvers towards the drone. This removes bias and improves efficiency.
NADE is a lifelong learning method thatprovides continuous communication between the drone and many background vehicles. For example, if a researcher wants to test his car in an urban environment, this approach would allow the drone to drive continuously and experience adversarial scenarios, including switching on and hard braking at a higher frequency. The results show that this environment eliminates the inefficiencies of the currently available options by orders of magnitude. It is expected that this approach could accelerate the adoption of autonomous vehicles.
“Driving a kilometer using simulationaugmented reality superimposed on a test track is equal to hundreds or thousands of kilometers on public roads. This will lead to a significant reduction in the overall cost and time of testing drones in a safer, more controlled and repeatable test environment, ”said ACM President and CEO Ruben Sarkar.
See also:
Look at an 8 trillion pixel image of Mars
Scientists have developed a replacement for the theory of relativity. What is the essence of the "theory of everything"?
Scientists have found evidence of interbreeding of modern humans with Neanderthals