An Israeli startup that tests the behavior of driverless cars has partnered with a major US technology company on a new solution for autonomous vehicle (AV) training.
Ramat Gan-based Foretellix has integrated technology from chip maker Nvidia to enable high-fidelity sensor simulation on its Foretify platform, which models real-world behavior when training AVs.
Autonomous vehicles rely on multiple sensors, including video and radar, while driving to accurately identify, track and react to objects on the roads – such as other cars or pedestrians.
Simulating these sensors allows car-makers to ensure that the system is working correctly, a process called verification and validation (V&V).
“With high-fidelity sensor simulation, the Foretify platform delivers a complete toolchain for training and V&V of autonomous vehicles,” said Foretellix co-founder and CEO Ziv Binyamini.
“By integrating the Nvidia Omniverse Cloud APIs, we can streamline and automate the development process, helping customers accelerate the deployment of autonomous technologies on a global scale and reduce development costs,” he said.
“The AV industry is expanding the use of end-to-end AI models, which require physically based sensor simulation,” said Zvi Greenstein, Vice President of Autonomous Vehicle Infrastructure at Nvidia.
“By leveraging Nvidia Omniverse Cloud APIs, Foretellix is enhancing its Foretify toolchain with new sensor simulation capabilities and setting a new standard for AV development and validation.”
Facebook comments