Waymo's co-CEO Dmitri Dolgov has pushed back against the idea that cameras alone can deliver fully autonomous driving.
During a talk at Y Combinator's Startup School, he argued that such systems hit a safety ceiling long before reaching the level needed to operate without a human behind the wheel.
>>> Ram Rumble Bee Supercharger Boosts Output Past 900 HP With Warranty
Dolgov did not name Tesla directly, but his comments were aimed at the company's camera-centric approach.
Tesla has built its autonomous-driving strategy around cameras, dismissing lidar and, more recently, radar and ultrasonic sensors.
Elon Musk famously called lidar “a fool’s errand” in 2019, saying “anyone relying on lidar is doomed.”
Why Lidar and Radar Matter
Waymo uses a combination of cameras, lidar, and radar. Cameras provide high-resolution color information, while lidar maps the three-dimensional world and radar measures velocity directly.
These sensors also work in darkness, glare, fog, rain, and snow.
Dolgov stressed that the sensors are not just backups for each other.
Each uses a separate processing system before the data is fused into a more complete picture of the environment.
He pointed to examples from Waymo's testing, such as lidar identifying a pedestrian during a Phoenix dust storm when cameras could barely see anything.
“Humans of course can drive with just eyes,” Dolgov said.
>>> Soldier's Car Repossessed Despite Deployment Orders; Dealer to Pay
“If the goal were to just approximately match human performance or to build an assist product, that’s a very reasonable way to go.”
