Tesla & Waymo: Same goals, different approaches

Recently Tesla and Waymo have been passing jabs over who has the best approach when it comes to autonomous driving. Waymo CEO John Kraficik, head of Alphabet’s autonomous car subsidiary, has claimed that Tesla will never be able to reach ‘fully’ autonomous level, of which Elon Musk has responded by pointing to his Tesla’s AI Hardware and Software is better than Waymo’s.

 

 

John Krafcik has said that he does not believe Tesla will be able to turn its Autopilot and Full Self-Driving mode into a totally autonomous system, further adding that the technology is currently at Level 2. According to the SAE’s definition, Level 4 and 5 is what provides ‘true’ autonomy.

Tesla’s approach relies on radar, sensors and cameras to let the car understand its surroundings. Whilst other auto companies, including Waymo, relies on Lidar and extensive 3D maps to help a vehicle understand where it is.

Elon Musk back in 2019 says that anyone relying on lidar are doomed.

Lidar is a fool’s errand,” Elon Musk said. “Anyone relying on lidar is doomed. Doomed! [They are] expensive sensors that are unnecessary. It’s like having a whole bunch of expensive appendices. Like, one appendix is bad, well now you have a whole bunch of them, it’s ridiculous, you’ll see.

Waymo however sees the benefits of Lidar, explaining that they are used in conjunction with radar and camera systems which “complement each other” and that Waymo takes the best of each.

Drago Anguelov, head of research, said Lidar gives “much richer data that’s much more accurate.” Plus it’s safer, he argued. While Musk is a big believer in the power of cameras, Anguelov said, “just using cameras is more limiting.”

Tesla counters this by pointing out Tesla’s “neural network”, which continuously builds out its predictive behaviour to better understand the world from the thousands of Tesla cars already on the road. This will then be used for the eventual implementation of a fully autonomous vehicle in the near future.