Autonomous Visualization System from Uber ATG
Uber ATG recently released an open-source visualization tool called AVS — Autonomous Visualization System. Many autonomous vehicle companies write their own visualization and simulation tools. The goal here is to provide an off-the-shelf, open-source solution to get teams started faster.
AVS enters a crowded field of solutions that are all trying to gain traction. MathWorks Automated Driving System Toolbox, dSPACE RTMaps, CARLA, Cognata, Microsoft AirSim, Baidu Apollo Simulation, Applied Intuition, Metamoto, RightHook, and ROS RViz are all working in the space. Some of these are focused sensor playback, some on generating simulated data, some on simulating multi-vehicle scenarios.
The weird thing is that so many teams evaluate this landscape and decide to build their own solutions. Waymo’s Carcraft is the most famous, but we made the same decision at Udacity a few years ago. We evaluated the simulation solutions on the market in the fall of 2016, found that none of them quite met our needs, and decided to build our own simulators in Unity.
Over time, maybe this decision will shift more toward using off-the-shelf solutions. When Udacity needs a simulator today, we are more likely to reach for an existing solution than we were a few years ago. Similarly, our former colleagues at Voyage have a prominent partnership with Applied Intuition. Both of those companies actually appear in the Uber blog post announcing AVS.
That struck me as pretty interesting, too. We’ve seen lots of partnerships in the traditional automotive industry, as car makers position themselves to compete with tech and ridesharing companies. Announcements from the tech and ridesharing space, however, tend to feel more like supplier relationships than partnerships. This blog post is has the feel of an Uber-Voyage-Applied Intuition partnership.