Synthesis AI has enhanced its ability to simulate driver behaviours in its synthetic data technologies, boosting car makers’ abilities to build future safety systems for both driven and driverless automobiles.

Through the company’s synthetic data-as-a-service FaceAPI solution, manufacturers can now test intelligent sensing configurations and driver safety monitoring systems across a broader set of environments and solutions without compromising customer privacy.

The new capabilities are particularly applicable to car makers targeting European Union markets. 

Beginning in 2022, all new cars entering the EU market must be equipped with advanced safety systems. Among the mandatory safety measures is distraction recognition and alert systems on trucks and buses to warn when vulnerable road users, such as pedestrians or cyclists, are in close proximity.

To meet the new requirements, automobile companies will need to collect diverse datasets to train AI models. As a result of the cost and other issues, it is likely that synthetic data will play an increasingly important role in overcoming these bottlenecks.

Synthetic data provides manufacturers with the ability to mimic driver behaviour in virtual car environments to test and iterate their models across a broader set of settings and situations without building and deploying fleets of vehicles. 

To meet the data demands of the in-cabin driver safety monitoring systems, Synthesis AI’s FaceAPI is designed to provide on-demand generation of thousands of unique identities with granular control of emotion, gaze angle, head pose, accessories, environments, camera systems (e.g., RGB, NIR, TOF), and more. Since the data is generated, the image data comes with an expanded set of pixel-perfect labels, including facial landmarks, gaze, angle, depth maps, segmentation, surface normals, and facial meshes. 

According to Synthesis AI, their data allows automotive manufacturers to build more robust training models in a fraction of the time and cost of traditional human-annotated real-world data approaches.

“For safe and general deployment of automobiles, especially AVs, Artificial Intelligence (AI) systems need to perceive the world reliably and make proper decisions across a wide range of situations,” said Yashar Behzadi, CEO of Synthesis AI. “With recent attention directed to driver monitoring systems to improve road safety, it’s inevitable that the demand for synthetic data and its simulation capabilities will only increase, as the technology is uniquely positioned to accelerate the development of driver safety and autonomous systems.”

“The new EU regulations demonstrate the growing expectation for car manufacturers to have a comprehensive understanding of all the human variables that can impact road safety. Synthetic data will play an instrumental role in meeting this need,” said Dr. Rana el Kaliouby, Deputy CEO of Smart Eye, and former Co-Founder and CEO of Affectiva. “Our collaboration with Synthesis AI has allowed us to test our computer vision models with large sets of diverse data that are indicative of real-world use-cases. As a result, we’re able to deliver advanced driver monitoring and Interior Sensing systems that meet the requirements of automakers today and in the future.”