Ford releases self-driving vehicle data
The Ford Motor Co. announced that its self-driving vehicle data package is available to the academic and research community, in collaboration with Amazon Open Data Program, which can help create advanced simulations based on real data. The goal of the release is to support the next generation of engineers and improve the way self-driving vehicles navigate and interact with vehicles, pedestrians, and other self-driving vehicles.
In a recent blog, Tony Lockwood, Ford’s Autonomous Vehicle Manager for Virtual Driver Systems, detailed how as part of this data package, the company is releasing a year’s worth of data from multiple Ford-owned, self-driving research vehicles within the Metro Detroit area. This includes full resolution, time-stamped data from the four LiDARs on the two vehicles, seven camera sensors, GPS and trajectory information, multi-seasonal data and 3D point cloud, as well as ground reflectivity maps.
While a self-driving vehicle is operating, it is continuously collecting data about its surroundings. Through the use of LiDAR and cameras, it is able to detect pedestrians, other vehicles, and traffic signs, while radar helps the vehicle sense how fast things are moving around it.
“Without all this data, self-driving cars wouldn’t even be able to leave a parking lot,” said Lockwood. “These vehicles need to process a constant stream of information to safely navigate their surroundings, but even before they can do that, high-quality data is needed to help engineers and researchers create software that can properly teach self-driving vehicles how to analyze their environments.”
That’s why Ford is releasing says it is release its dataset to the academic and research community. According to the company, there are a number of reasons why these data points are noteworthy to researchers. One being that the years’ worth of data includes varied environments and seasonal variations, from snowy weather to sunny days, busy city streets and quiet neighborhoods.
Another is that the sensor information is from two vehicles, increasing the amount of data received, as well as offering new data when the two vehicles encounter one another on their routes. The company says this could potentially open up new routes for multi-vehicle communication, localization, perception, and path planning.
For more information, visit https://avdata.ford.com.