The fleet of self-driving Cruise cars testing in San Francisco takes into account petabytes each month from its suite of sensors on the road and in simulation, like other configurations offered by other autonomous car manufacturers on autonomous vehicles. By the way, a petabyte represents a million gigabytes.
So, to correct all this information, Cruise – through a hackathon – has created a open source data visualization platform called Webviz. Other autonomous vehicle companies offer different aspects of the autonomous driving process, such as Baidu's Apollo open source self-driving platform. Now, Cruise opens its application to anyone who works with robotics.
With Webviz, engineers can understand autonomous vehicle data, analyze what cars do on the street, and decide how they should drive or approach different situations. Even though there are robot-specific aspects, Cruise says all members of the robotics community can use the program.
For example, a person working with a distribution robot or a humanoid imitating human movement can plug in the data inputs from their cameras and sensors and arrange and view them for further analysis and interpretation, as do the teams autonomous vehicles.
Cruise says it uses the platform to watch live simulations or to review past runs from an older data set. here is a live demo to see how the data is displayed.
Cruise previously opened its 2D and 3D scene rendering library, Worldview, and Uber created its tool Autonomous visualization system available to the public at about the same time in February to turn car encounters into 3D scenes.
Anyone who wants to start looking into their robotics data can now go on and use Webviz.
. (tagsToTranslate) cruise (t) autonomous driving (t) data visualization (t) tech (t) transport</pre></pre>