Waymo Takes Aim at Tesla, Says Cameras Alone Aren't Enough for Autonomous Driving

“Cameras are incredible, but they aren't enough,” Thirumalai wrote. “For years, there's been a debate over whether cameras alone could solve full autonomy. Now, after more than 200 million real-world miles, the data is clear: safe, fully autonomous operations at scale require more.” Waymo combines cameras with lidar and radar to create “a rich, redundant world view that no single sensor can replicate,” he added.

Musk has long dismissed lidar, calling it “a crutch” and predicting that any company relying on it is “doomed.” His argument is that humans drive primarily with their eyes, so autonomous vehicles should do the same. But most robotaxi operators, including Waymo, Zoox and Motional, use lidar along with radar and cameras. They argue a redundant sensor suite ensures the vehicle can still operate safely if one sensor fails.

The sensor debate could have regulatory consequences. The Verge noted that New Jersey's state legislature is considering a bill that would legalize robotaxis only if they include multiple sensors; Tesla's camera-only vehicles would be banned under such a law.

Thirumalai also defended Waymo's use of high-definition maps, another difference with Musk, who has called HD maps “a really bad idea.” Waymo uses HD maps to “jump-start our validation process,” Thirumalai said. “As we drive, we treat our maps as another input — like our sensors, but acting as a mental memory.” He said Waymo's AI-driven mapping system keeps the maps continuously updated.

Musk has said autonomous vehicles must be able to drive without maps, because roads change, lanes get repainted and construction zones appear. He has argued that relying on HD maps can slow the development of the instant analysis system needed for full autonomy.

In the final lesson of the post, Thirumalai delivered his most direct challenge to Tesla's strategy: “There is no substitute for actual fully autonomous miles. Simply improving a driver-assist system (L2) for full autonomy is a false summit. True L4 maturity can only be safely achieved by a purpose-built system, validated on closed courses and hardened by the uncompromising experience of driving without a human in the car.”

This struck at the heart of Tesla's plan to turn its advanced driver-assist features, Autopilot and Full Self-Driving, into a fully autonomous platform. Tesla's FSD is still classified as Level 2, meaning the driver must monitor the road at all times and be ready to take control. If a crash occurs while FSD is in use, Tesla blames the driver, citing its terms of service. Tesla added “Supervised” to FSD marketing after regulators complained the name was misleading.

Waymo operates fully autonomous vehicles in 11 cities, according to The Verge.