According to TechCrunch, Aurora, a self-driving car startup scheduled to be listed on the Nasdaq next week,It is turning to a senior team that used to work at Pixar to help the computer simulation tools used to test and train its autonomous driving system more like the real world.
The three-person computer graphics startup Colrspace has been operating in secret, and the company is joining Aurora’s perception team. Aurora will also own Colrspace’s intellectual property, especially the technology that combines CGI and machine learning. This trio includes Michael Fu, Allen Hemberger, and Alex Harvill, who have developed a technique that can reconstruct 3D objects and materials from photos or images. In essence, it makes the simulation more “realistic”, which Aurora and other self-driving car developers believe will help make the test more effective.
Fu, Hemberger and Harvill will join Aurora’s perception team, which already includes people from 7D, a simulation startup founded by former Pixar software engineer Magnus Wrenninge. TechCrunch learned in 2019 that it had acquired 7D.
Although competitors such as Aurora and Argo AI, Cruise and Waymo often conduct real-world tests on closed courses and public roads, computer simulations are seen as an important tool for testing, training and validating their autonomous vehicle technology. Simulation can be used to help autopilot systems test various scenarios or replay what is happening in the real world. The final game is to train and evaluate the software stack to be safe in the real world.
It is not uncommon for the largest autonomous driving companies to conduct thousands or even millions of simulations every day. For example, Aurora estimates that its simulator is equivalent to running more than 50,000 trucks continuously. Aurora’s computer simulator is called a “virtual test suite” and runs through a variety of different driving conditions and common and uncommon (edge case) scenarios to detect errors as early as possible, and then deploy them on public roads. Running vehicles. The data captured while driving on public roads is also fed back to the simulator.
This year, Aurora invested more energy and resources to expand the scale of its simulation project. Aurora said this month that it expects to drive the equivalent of more than 9 billion miles of simulated miles by the end of this year, of which 6 billion miles will be completed so far in 2021.