Our Lidar-less approach uses just cameras. Lack of specialized mapping vehicles, crowdsourcing and AI processing dramatically lowers 3D map generation and update costs.
Avoiding the need for specialized mapping fleets allows us to quickly source data for updates. Coupled with AI processing, our 3D map updates much faster than the competition.
Camera based 3D mapping allows for crowd sourcing at world scale. We do not require mapping fleets to either create and update the 3D maps. The cloud based AI pipleine can be quickly scaled based on load.
Our 3D HD maps provide detailed information, sufficient for safe and reliable operation of autonomous vehicles. Information including the base map, lanes, road signs, traffic light positions, pedestrian crossings, construction and even right-of-way rules in complex intersections are updated rapidly. Our maps provide industry-standard 10 cm accuracy, while our deep learning based mapping pipeline enables rapid scaling at the rate of 1000s of km per day.
To fully harness the power of HD maps, autonomous vehicles need to accurately pinpoint their position. Known positioning systems such as GPS do not provide the accuracy nor reliability required to safely operate autonomous vehicles. Our localization stack combines geometric computer vision and semantic understanding with INS and GNSS to provide accurate and reliable localization, with the ability to handle adverse weather conditions.
Our founding team has over 30 man-years of experience at Fortune 50 companies building products at the intersection of state of the art research and cutting edge engineering. We believe that with the right people anything is possible. Our team has homes in Seattle, USA and Belgrade, Serbia.
We are very grateful to be supported by amazing partners.
We would love to partner with you.