Global vehicle-to-vehicle (V2V) communication network leader Nexar issued a challenge to researchers to develop a geography-adaptive autonomous driving perception model.
For the challenge, Nexar released its NEXET image dataset that includes more than 55,000 street-level images from over 80 countries.
The aim of the challenge is to initiate a collaborative effort to address the problem of building a driving perception that performs consistently over different geographies.
The key element for developing an all-weather, all-road, all-country driving perception is the ability to obtain data from an large and diverse training dataset. NEXET was carefully curated to contain scenarios of varying lighting, weather, and topographical conditions, as well as varying driving cultures in different countries to offer a comprehensive dataset.
Bruno Fernandez Ruiz, co-founder and CTO of Nexar, said, “The robustness of learning driving policy models depends critically on having access to the largest possible training dataset exposing the true diversity of the 10 trillion miles that humans drive every year in the real world. Current approaches are trained using homogenous data from a small number of vehicles running in controlled environments, or in simulation, which fail to perform adequately in the true diversity of real-world dangerous corner cases.”
Safe driving requires continuously resolving a long tail of those corner cases. The only way to ensure safety in Advance Driver Assistance System (ADAS) is to continuously capture as many of these cases as possible. By releasing this diverse dataset, Nexar is setting challenge to researchers to help it to develop these algorithms and together create more robust ADAS models – essential to a safe autonomous future, he added.