Communications of the ACM
Better Autonomous 'Reasoning' at Tricky Intersections
Massachusetts Institute of Technology and Toyota researchers have developed a model to help autonomous vehicles determine when it is safe to proceed into intersections with obstructed views.
Credit: Daniela Rus et al
Massachusetts Institute of Technology (MIT) and Toyota researchers have developed a model to help autonomous vehicles determine when it is safe to proceed into intersections with obstructed views.
The model uses its own uncertainty to estimate the risk of potential collisions or other traffic disruptions at intersections.
The system considers critical factors including nearby visual obstructions, sensor noise and errors, the speed of other cars, and the attentiveness of other drivers. Based on its measured risk, the system may instruct the car to stop, pull into traffic, or move slightly forward to gather more data.
The researchers tested the system in more than 100 trials of remote-controlled cars turning left at a busy, obstructed intersection in a mock city, with other cars constantly driving through the cross street; the system helped the cars avoid collisions 70% to 100% of the time.
From MIT News
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found