The future of mobility demands vehicles that can perceive and understand their surroundings with human-like precision. Premium lighting systems pioneer ZKW is working to bring this reality forward, partnering with Kognic to develop advanced perception capabilities that will make autonomous driving safer and more reliable.
We spoke with Matthäus Artmann, Group Manager Electronics Engineering Predevelopment, and Andres Moreno, Electronics Engineer, about how Kognic's platform is helping ZKW accelerate their development of cutting-edge perception systems.
As a global leader in innovative premium lighting and electronics for the automotive industry, ZKW is already designing the technologies that will make autonomous driving possible. Their forward-thinking approach positions them at the forefront of what's next in automotive innovation.
Even self-driving vehicles need the right light - ZKW GROUP
This insight couldn't be more accurate. ZKW envisions lighting that transcends traditional illumination to become an intelligent communication interface between autonomous vehicles and their environment. Imagine braking paths projected onto roads, virtual crosswalks illuminated for pedestrians, and visual signage displayed for other road users – all helping autonomous vehicles communicate effectively with humans. The goal: creating lighting systems that enhance perception and safety, helping to realize accident-free transportation.
While these innovations are currently in pre-development phases, ZKW has partnered with Kognic to overcome a critical challenge on their journey: efficiently generating high-quality annotated data to train their AI systems. With Kognic's expertise in sensor-fusion annotation, ZKW is building the foundation for their autonomous driving technologies.
"At ZKW, we like to partner up with experts in different competencies for topics that are new to us. We wanted to go into AI and realized the importance of data in our development because Artificial Intelligence requires high quality annotated data - MATTHÄUS ARTMANN"
Why did ZKW choose Kognic? Their decision came down to three key differentiators:
Kognic stands out as the only ground-truth and perception analytics platform specifically designed for AD/ADAS development. For ZKW, who is just beginning their AI journey, having a partner with deep domain expertise in automotive perception was essential for success across all use cases.
Kognic delivers more than just annotations – we provide a comprehensive platform engineered to make safe perception possible, with quality and safety at the core. This focus on excellence comes from our tailored approach to each customer's specific requirements and use cases.
"Some companies are mainly focused on the end result, which is basically: we have the annotators, it will take this amount of time, this is our price and that's it. Kognic goes beyond and really guided us in the initial steps, and that helped us stay the course and achieve our initial goal" - ANDRES MORENO
Every Kognic project begins with establishing robust guidelines. Our Guideline Agreement Process (GAP) helps customers develop a deeper understanding of their specific use case through collaboration with Kognic's perception experts. This empowers customers to make informed decisions that lead to more accurate results, perfectly aligned with their requirements.
"The guidelines were a really good first step to initiate this annotation process. That was something that we didn't have. And starting smart with the right set-up made the difference." - MATTHÄUS ARTMANN
The guidelines process wasn't just about staying on track – it was crucial for ensuring ZKW focused on acquiring the right data from the beginning. In AI development, working with biased data can lead to significant problems down the line.
Kognic provided ZKW with a structured process for regularly evaluating outputs, discussing potential improvements relative to the established guidelines, and continually reassessing which data types would be most valuable moving forward.
"From my point of view, the main challenge is the quality of the data. The initial steps that any company has to take regarding data is the most important thing, because usually the artificial intelligence, doesn't take too much time to develop, but if the data is bias then there isn't any artificial intelligence that can overcome that - ANDRES MORENO"
Many organizations mistakenly view annotation as simply "drawing bounding boxes" and opt for the lowest-cost provider without carefully considering their specific needs or desired outcomes. This approach typically results in low-quality annotations that introduce bias into algorithms – issues that must be corrected later. Kognic emphasizes to customers that this process goes beyond basic labeling – it's about generating high-quality data that properly trains algorithms, teaching them the right lessons, and creating a clear roadmap for model optimization.
By taking a more comprehensive approach, ZKW achieved superior results quickly while reducing the total effort required. They focused not just on annotation quality, but also on optimizing their data handling process. This enabled them to work efficiently with their datasets – browsing, filtering, and identifying gaps that needed to be addressed.
"With Kognic, I knew we were processing the right kind of data, and could talk to the team about improving them, and I can select what data matters most, and what I need more of. Filtering, visualising - MATTHÄUS ARTMANN"
Kognic and the ZKW team share core values of efficiency, continuous learning, and relentless improvement. By establishing the project correctly based on ZKW's specific use case, ensuring quality throughout the process, and implementing regular check-ins for adjustments and enhancements, the team successfully achieved their initial objectives.
At Kognic, we're not just vendors – we're partners building lasting relationships based on trust, transparency, and shared growth. While ZKW has primarily focused on video imagery so far, their mission to enhance mobility through advanced lighting technologies now has them exploring new autonomous driving applications with Kognic's guidance, including LiDAR and additional sensor types.