Communications of the ACM
Accident Prevention Software for Autonomous Vehicles
Researchers at Germany's Technical University of Munich (TUM) say they have created accident-preventing software for autonomous vehicles that anticipates variations of traffic scenarios.
Credit: LV4260/iStock
Researchers at Germany's Technical University of Munich (TUM) say they have created accident-preventing software for autonomous vehicles that anticipates variations of traffic scenarios.
The software analyzes and predicts events while driving, recording sensor data and re-assessing the traffic situation each millisecond, calculating all possible movements for every traffic participant (provided they comply with traffic regulations).
The system projects three to six seconds ahead and from this ascertains movement options for the vehicle, while simultaneously calculating potential emergency maneuvers.
TUM's Matthias Althoff said testing the software in simulations proved "that the safety module does not lead to any loss of performance in terms of driving behavior, the predictive calculations are correct, accidents are prevented, and in emergency situations the vehicle is demonstrably brought to a safe stop."
From Technical University of Munich (Germany)
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found