Researchers develop simulator for improving self-driving vehicle safety

March 28, 2019

The new photo-realistic system provides a more authentic simulation than current systems

Chinese and American researchers have developed a data-driven simulator that could improve autonomous vehicle safety before conducting road testing.

In a study published this week in the Science Robotics journal, the new research showed that the new photo-realistic system provided a more authentic simulation than current systems.

Scientists from Baidu Research in China, the University of Hong Kong, and University of Maryland in the U.S. invented the Augmented Autonomous Driving Simulation (AADS) system designed to make self-driving technology easier to evaluate in the lab and ensure more reliable safety before road testing.

In the current simulator technology, the perception module of the self-driving car receives input from computer-generated imagery and mathematically modeled movement patterns for pedestrians, bicycles, and other cars.

The new system combines photos, videos, and lidar point clouds with real-world trajectory data for pedestrians, bicycles, and other vehicles. Those trajectories can be used to predict the driving behavior and future positions of other vehicles or pedestrians on the road for safer navigation.


Source: Xinhua