With Nexar’s added driving data and technological expertise, the Consortium will take on key initiatives to merge deep learning with automotive perception and bring computer vision technology to the forefront of the automotive industry.

We are glad to have Nexar join the consortium, enabling us to fuel our research with the large amount of real-world driving data that Nexar is collecting. The only way of developing credible algorithms that will have robust performance in real-world edge cases is to rely on large amounts of data from different lighting, road and weather conditions.

—Professor Trevor Darrell, Faculty Director of the BDD Center at UC Berkeley

Since its launch in February 2016, Nexar has tracked upwards of 20 million miles and recorded more than a half-million instances of driving incidents worldwide. This has provided the company with a large and diverse panel of data of real-world driving conditions, a databank that continues to expand every day and that can serve as a resource for the future success of the autonomous car industry.

Backed by the BDD Consortium’s advanced research, Nexar can now better analyze and understand this data in order to ultimately gain the best perception of driving and road conditions. With this information, Nexar will further develop its vehicle-to-vehicle network.

The BDD Consortium’s multi-disciplinary center is housed at the University of California, Berkeley and is led by Professor Trevor Darrell, Faculty Director of PATH, with Professor Ken Goldberg and Thomas West serving as associate directors. Amongst its sponsors are firms such as Volkswagen, Ford, Toyota, Samsung, Bosch, Honda, Hyundai, Qualcomm and NVIDIA.