ZF Unveils AI-Powered ADAS Tool

Sign up for our weekly email to stay on top of the latest news and insights!

ZF Annotate is revolutionizing the development and validation of advanced driver assistance systems (ADAS) and automated driving (AD) systems with its new AI-driven, cloud-based reference system. This innovation, which provides substantial time and cost savings, was introduced at the ZF Global Technology Day on June 27, 2024.

Key Highlights:

• Faster Validation Process: ZF Annotate uses artificial intelligence to speed up sensor data validation by up to 10 times, reducing the process from 12 to two months.
• Significant Cost Savings: The system is 80 percent cheaper compared to traditional manual validation methods.
• Comprehensive Sensor Data: The service uses cameras, radar, lidar, and ultrasonic sensors to create a precise, three-dimensional image of the vehicle’s environment.
• High Accuracy: By providing the “ground truth” through AI-analyzed sensor data, ZF Annotate ensures accurate and reliable data for ADAS and AD system development.

Modern automated driver assistance systems require precise analysis of the vehicle’s environment using a multitude of sensors. These sensors collect data to create a detailed three-dimensional image, allowing the system to recognize objects in real time, including vehicles, pedestrians, lanes, and traffic signs. ZF Annotate enhances this process by comparing collected sensor information with high-precision reference data, significantly improving accuracy.

Dr. Holger Klein, Chairman of the Board of Management, highlights the innovative nature of ZF Annotate: “ZF Annotate combines the advantages of a robust and independent reference sensor set with a scalable cloud service that uses intelligent 2D and 3D tracking algorithms.”

Traditional systems relied primarily on 2D annotation for data validation, mapping the environment in distance and horizontal angle. ZF Annotate, however, adds height information, creating a more comprehensive and precise data set. This improvement makes ZF Annotate a unique solution in the industry, optimizing a previously labor-intensive and costly process.

Time and Cost Efficiency: ZF Annotate’s use of AI not only speeds up the validation process but also reduces costs. According to Dr. Klein, “Thanks to artificial intelligence, we can speed up the validation process by up to 10 times and thus reduce an annotation from 12 to two months. This saves our customers time and money.”

Klaus Hofmockel, Head of Research and Development in the Driver Assistance Systems and Electronics division, adds, “With the ability to work 24 hours a day, seven days a week, our cloud-based service completes the validation of reference data in a remarkably short time compared to the market, without any loss of quality.”

Flexible and Comprehensive Application: Depending on customer requirements, ZF Annotate can be used in various modes, including a “Pursuit” mode, where the sensor set is mounted on a separate reference data vehicle. This flexibility makes ZF Annotate independent of specific sensor manufacturers, reducing the need for cost-intensive modifications to test vehicles.

The system can also provide a comprehensive 360-degree view of the vehicle’s surroundings, depending on customer needs, ensuring a detailed and precise representation of the environment.

ZF Annotate’s cloud-based service is designed for use across all vehicle classes in both the passenger car and commercial vehicle sectors. As Dr. Klein emphasizes, “Reliability and efficiency are significant when it comes to validating reference data in the development of increasingly popular advanced driver assistance systems. ZF Annotate offers both in a scalable system.”

In conclusion, ZF Annotate represents a significant advancement in the validation of ADAS and AD systems, offering a faster, more cost-effective, and highly accurate solution. By leveraging artificial intelligence and cloud-based technology, ZF is paving the way for the development of safer and more efficient automated driving systems.