Exclusive: Waymo says there's no AI shortcut to self-driving

Breakthroughs in AI are fueling hopes that more data and smarter models can provide a shortcut to self-driving vehicles. Waymo, after more than 15 years and 200 million driverless miles, says there is none.

Why it matters: The answer could determine whether the AV race is a long, expensive slog that rewards Waymo's head start — or a new track that lets newer rivals hit the road faster.

Driving the news: Srikanth Thirumalai, Waymo's vice president of onboard software, said in an exclusive interview with Axios that it takes more than just better AI to safely deploy AVs at scale.

• Waymo's goal from the start, he said, has been "demonstrably safe AI." But a growing reliance from competitors on single "end-to-end" AI systems introduces risks.
• "Even the best AI models with trillions of parameters still hallucinate... We don't have a choice to say, 'Let's hit refresh' ... There is no click reboot or reload or refresh [in] physical AI. You have to deal with the consequences of it."
• In a blog post published Wednesday, Thirumalai goes deeper on 10 AI lessons Waymo has gleaned from its first 200 million autonomous miles.

Catch up quick: Waymo got its start as Google's self-driving car project in 2009, well before the modern deep-learning revolution.

• In the early days, it relied on many specialized models — one for pedestrian detection, another to tell when a light turns green, for example. Gradually it shifted toward fewer, larger foundation models, "riding the AI wave," Thirumalai said.
• Now companies like Tesla, Wayve and Waabi are going even further, developing AV 2.0 systems they say are capable of humanlike reasoning — "end-to-end" neural networks that process raw sensor data and directly output steering commands.

Waymo says it has tried the same tools but concluded that there aren't enough safety guardrails.

• "What we found is that just pure end-to-end systems are not able to meet our safety bar at the scale that we operate," Thirumalai told Axios.

Reality check: Thirumalai said Waymo published the blog post to counter a narrative that AI can provide a shortcut to safe self-driving, with public trust in the AV industry on the line.

• At the same time, it's a flex. The safety standards Waymo wants the industry to embrace — not to mention regulators and rulemakers — also play to its biggest competitive advantage: a big head start built on years of testing and real-world driving data.
• While it didn't name specific competitors, it laid out reasons why newer approaches to building AV systems could carry risks — effectively raising the bar those companies would have to clear.

Zoom in: Waymo weighed in on one of the industry's biggest debates — whether cameras alone can solve full autonomy.

• When training its models, Waymo found that visibility was far better when cameras, lidar and radar worked together rather than when one or more sensors were eliminated.
• "The AI can only make sense of what it sees, and if you just can't see it, the AI can't do much," Thirumalai said.

Between the lines: It's a direct jab at Tesla, which is betting on a camera-only, end-to-end autonomous driving system.

• Better AI can't fully compensate for inadequate sensing, Thirumalai said.
• He added the same is true for high-definition mapping, which some rivals say is unnecessary.

The bottom line: Waymo spent more than 15 years building a commanding lead in robotaxis, and Thirumalai argued now that there is no "one silver bullet" to reaching safe autonomy.

• Waymo's experience as the industry leader gives its argument weight — but it doesn't settle the debate. Rapid advances in AI could still prove there's a faster path to autonomy.