ZOOX has been testing our L3 vehicles in Las Vegas and the Bay Area for over four years. The company says that allowed them to gain significant knowledge about how their hardware and software behave in those areas. The company says they don't want to change mobility in a few states but reimagine transportation for the whole world. To do that, they must prepare for unfamiliar roads and novel conditions. Enter Seattle.
Testing in a new city gives their vehicle and AI the chance to experience fresh challenges, including different weather and infrastructure, different by-laws, and different driving culture. These challenges will help us iterate their hardware and software, ultimately broadening the capabilities of Zoox.
It rains more frequently in Seattle than it does in San Francisco. Human drivers rely on windshield wipers and defrosters to drive safely in adverse weather conditions; they have built special hardware into their sensor architecture to remove water and debris. Frequent rain provides more opportunities to collect data and validate these innovations.
ZOOX is also planning to open an office in the Seattle area in 2022. It will be their fourth base and testing site, following San Francisco, Las Vegas, and its headquarters in Foster City.
The company will be deploying a small number of our L3 vehicles to get the lay of the land, assessing the complexity and demands of Seattle.
Toyota Highlanders are outfitted with the latest software stack and have a safety driver to control if needed. Zoox says they are the only AV company with the same sensor architecture in L3 and L5 fleets, which means the data they gather in Seattle will be directly applicable to their whole fleet, including purpose-built vehicles.
Each vehicle sensors work together to build a picture of each vehicle's surroundings. Testing these sensors in varied conditions will highlight specific areas to help Zoox systems evolve.
"A smooth sea never made a skilled sailor, and it's the exact same principle for our technology. The challenges of Seattle will let us hone our software stack and ultimately improve the behavior of our vehicles."
Kai Wang, Director of Prediction
The early data collected in Seattle is also crucial for our Calibration, Localization, and Mapping, Simultaneously (CLAMS) and Zoox Road Network (ZRN) teams, who will start creating a 3D map of the city and populating it with road features: bike lanes, speed limits, traffic lights, and so on. That means when the L5 vehicles are eventually deployed in the city, they'll have a full working knowledge of their environment from day one.
コメント