Mercedes-Benz Selects Algolux for AI-SEE Project to Enhance Vehicle Vision in Low Visibility Conditions

Algolux has been selected to participate in the AI-SEE project led by Mercedes-Benz, the Montreal-based computer vision software company announced. Algolux will cooperate with 20 world-class partners, including OEMs and suppliers, over a period of three years to enable Level 4 autonomy for mass-market vehicles. The intent is to build a novel and robust sensor system supported by artificial intelligence to enhance vehicle perception in low visibility situations.

The project is co-funded by the National Research Council of Canada Industrial Research Assistance Program (NRC IRAP), the Austrian Research Promotion Agency (FFG), Business Finland, and the German Federal Ministry of Education and Research BMBF under the PENTA EURIPIDES label endorsed by EUREKA.

“Algolux is proud to be selected to the AI-SEE consortium as part of a group of world-leading ADAS and AV expert partners,” said Matthias Schulze, VP Europe & Asia at Algolux. “We look forward to working together on solving the safety-critical issue of perception in low light and inclement weather conditions to enable tomorrow’s Level 4 mass-market vehicles.”

Role of Algolux With AI-SEE

To help the AI-SEE project meet its objectives, Algolux will lend its technology and expertise in critical areas, including deep learning and AI algorithms, the fusion of data from distinct sensor types, long-range stereo sensing, and radar signal processing.

“Automated vehicles can be ready for market introduction only if they can operate in a reliable manner at all times,” Algolux said in a statement. “This requires an all-conditions capable autonomous driving system that can ensure safe travel in every relevant weather and lighting condition such as snow, heavy rain, or fog.”

Importance of Robustness

As noted by Algolux, many existing systems fail in poor visibility conditions due to a lack of redundant information. According to Algolux, an excellent example of this is how sensor measurements become distorted in one area (e.g., LiDARs and backscatter in snow) and not others (intensity cameras). Algolux relies on a “smart fusion” approach that acts as the control center or “brain” of the system to overcome these and similar issues while offering redundancy in good conditions. According to Algolux, this approach creates a more robust perception platform for better performance regardless of the lighting or weather conditions.

“We know that delivering very accurate and robust perception is a fundamental pillar for the industry right now,” explained Dave Tokic, VP of Marketing and Strategic Partnerships at Algolux, during AutoSens Detroit 2020. “However, it’s difficult for OEMs and Tier 1s to scale their systems to support different sensors and architectures and do so in a timely and impactful way.”

“Algolux is one of the few companies in the world that is well versed in the end-to-end deep neural networks that are needed to decouple the underlying hardware from our application,” said Dr. Werner Ritter, Consortium Lead, Mercedes Benz AG. “This, along with the company’s in-depth knowledge of applying their networks for robust perception in bad weather, directly supports our application domain in AI-SEE.”

Algolux In The News

Algolux was named to the 2021 CB Insights AI 100 List of the world’s most innovative AI startups. The company was also named for Most Outstanding AV Technology Innovation at the 2021 Tech.AD Europe Awards. Algolux recently secured $18.4 million in Series B funding and joined the Partners for Automated Vehicle Education to help educate consumers on the role computer vision plays when it comes to autonomous vehicles.

ADAS Guide 2021 Banner