Communications of the ACM
Chinese, .S. Researchers Develop Simulator for Improving Self-Driving Car Safety Before Road Test
The Augmented Autonomous Driving Simulation system can be used to predict the driving behavior and future positions of other vehicles or pedestrians on the road.
Credit: Li et al
Researchers at China's Baidu Research, the University of Hong Kong, and the University of Maryland, have developed a system that could make self-driving technology easier to evaluate in the lab and ensure more reliable safety before expensive road testing.
The new Augmented Autonomous Driving Simulation (AADS) system combines photos, videos, and LiDAR point clouds with real-world trajectory data for pedestrians, bicycles, and other cars.
Those trajectories can be used to predict the driving behavior and future positions of other vehicles or pedestrians on the road for safer navigation.
The researchers eliminated blind spots in real-world images by isolating the components in a street scene, turning them into individual elements that can be synthesized to create a multitude of photo-realistic driving scenarios.
Said University of Maryland researcher Dinesh Manocha, "We extracted data about real trajectories from all the video we had available, and we modeled driving behaviors using social science methodologies."
From Xinhua
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found