This inventor holds 1 USPTO granted patent. Top assignee: Zenseact Ab. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Adam Lilja and Road Geometry Estimation for Vehicles.
Introduction
Adam Lilja is an inventor based in Gothenburg, Sweden. His patent work includes a method for estimating road geometry and identifying road objects from vehicle camera images.
Latest Patents
Lilja is associated with 1 patent, titled “Road Geometry Estimation for Vehicles.” The invention describes a method that processes images from one or more vehicle cameras across consecutive time steps. Machine-learning algorithms encode the images into features representing visible road objects. The method transforms those features into a Bird’s Eye View (BEV) representation, then uses transformer-based algorithms to extract object embeddings. It decodes those embeddings to determine each road object’s position and class.
Career Highlights
Lilja is associated with Zenseact AB, a company working in vehicle technology. His patent describes a machine-learning approach to interpreting camera imagery and representing road objects around a vehicle.
Collaborations
The provided information names Junsheng Fu and Lars Hammarstrand as Lilja’s coworkers. Their specific roles in the patent or related work are not stated.
Conclusion
Adam Lilja’s patent presents a camera-based, machine-learning method for estimating road geometry and identifying road objects, reflecting his association with Zenseact AB.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile