{"id":6090,"date":"2026-08-27T15:48:45","date_gmt":"2026-08-27T15:48:45","guid":{"rendered":"https:\/\/silvybrand.com\/?p=6090"},"modified":"2026-08-27T15:48:45","modified_gmt":"2026-08-27T15:48:45","slug":"waymo-tesla-lidar-camera-robotaxi-cybercab-musk","status":"publish","type":"post","link":"https:\/\/silvybrand.com\/?p=6090","title":{"rendered":"In a swipe at Tesla, Waymo says \u2018cameras\u2026 aren\u2019t enough\u2019"},"content":{"rendered":"


\n<\/p>\n

\n
\n

As Tesla gears up for the official launch of its steering wheel and pedal-less Cybercabs<\/a>, Waymo is issuing a stark warning about Elon Musk\u2019s approach autonomous driving.<\/p>\n<\/div>\n

\n

Srikanth Thirumalai, Waymo\u2019s VP of Onboard Software, doesn\u2019t specifically call out Musk or Tesla in a blog post, published Wednesday<\/a>, entitled \u201c10 AI Lessons from Driving 200+ Million Fully Autonomous Miles.\u201d But his intention is clear: Tesla\u2019s system is insufficient to the task of fully autonomous driving.<\/p>\n<\/div>\n

\n

\u201cCameras are incredible, but they aren\u2019t enough,\u201d Thirumalai writes. \u201cFor years, there\u2019s 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.\u201d Waymo uses cameras, in addition to lidar and radar, to create \u201ca rich, redundant world view that no single sensor can replicate,\u201d he adds.<\/p>\n<\/div>\n

\n

Musk, of course, would beg to differ. The occasional trillionaire has over the years made his distaste for lidar widely known<\/a>, calling the laser-based sensor \u201ca crutch\u201d and predicting that any company relying on the powerful but expensive tech is \u201cdoomed.\u201d The crux of his argument is that humans make driving decisions primarily through the use of their eyes, so why not autonomous vehicles?<\/p>\n<\/div>\n

\n

In recent months, Tesla has doubled down on this position. In a recent earnings call<\/a>, Tesla\u2019s head of AI Ashok Elluswamy ripped into other companies who have adopted a multi-sensor approach. \u201cHistorically, the so-called experts have always claimed that you need lidars, radars, HD maps, and the entire kitchen sink to drive safely,\u201d he said. \u201cHere we show that such is not true. You can have safe, comfortable, and affordable autonomy with just cameras. This record should be a huge validation of Tesla\u2019s entire AI approach.\u201d<\/p>\n<\/div>\n

\n

Of course, Tesla is mostly alone in this position. The vast majority of AV operators, from Waymo to Zoox to Motional, use lidar, in addition to radar and camera, as part of their on-board suite of sensors. They believe that autonomous vehicles need to be better than humans with regard to their perception systems, which requires a redundant multi-sensor approach. If one sensor fails, the vehicle wouldn\u2019t be fully blinded as other sensors can help guide it to safety.<\/p>\n<\/div>\n

\n

Tesla\u2019s camera-only approach could shut it out of certain markets, depending on how certain policy debates turn out. New Jersey\u2019s state legislature is currently considering a bill<\/a> that would legalize robotaxis, but only if they include multiple sensors. Tesla would be banned under such a law.<\/p>\n<\/div>\n

\n

Thirumalai goes on to outline other differences between Waymo and Tesla. While Musk thinks the use of high-detail maps to help chart an autonomous vehicle\u2019s course is \u201ca really bad idea,\u201d Waymo believes that HD maps are a powerful \u201cprior.\u201d Waymo uses HD maps to \u201cjump-start our validation process, so we can provide a fully autonomous service to riders from our first trip,\u201d Thirumalai says. \u201cAs we drive, we treat our maps as another input \u2014 like our sensors, but acting as a mental memory.\u201d<\/p>\n<\/div>\n

\n

Musk believes autonomous vehicles need to be able to drive without a map; after all, roads change, lanes get repainted, construction zones appear, as do potholes. Musk believes that you need an instant analysis system that\u2019s so good it gains little from maps \u2014 and that HD maps in particular can slow down the development of that necessary system.<\/p>\n<\/div>\n

\n
\n
\n
\n
\n
\"AUSTIN,<\/a><\/div>\n<\/div>\n<\/div>\n

AUSTIN, TEXAS – APRIL 8: Tesla Cybercabs are lined up on a lot at Tesla Giga Texas in Austin, Wednesday, April 8, 2026. (Jay Janner\/The Austin American-Statesman via Getty Images)<\/figcaption><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\n

But Waymo isn\u2019t resting on its mapping laurels. The robotaxi company uses an AI-driven mapping system to ensure its maps are \u201ccontinuously updated,\u201d Thirumalai writes, \u201cproviding the vehicle with a reliable, high-fidelity reference to lean on during complex maneuvers.\u201d In other words, mapping is useful, but it\u2019s not an end-all-to-be-all.<\/p>\n<\/div>\n

\n

Thirumalai goes on to describe some of Waymo\u2019s other principles \u2014 closed-loop simulation can help identify more edge cases, Vision-Language Models are great reasoning tools \u2014 before concluding with his most direct swipe at Tesla yet: you can\u2019t build a fully autonomous system on a Level 2 driver assist one.<\/p>\n<\/div>\n

\n
\n

The final lesson is that 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.<\/p>\n<\/blockquote>\n<\/div>\n

\n

This, of course, gets at the heart of the Tesla proposal: that with enough data and enough miles and enough training, eventually its advanced driver assist systems, Autopilot and Full Self-Driving (Supervised), will evolve into Level 4 capable, fully autonomous platforms.<\/p>\n<\/div>\n

\n

Today, Tesla\u2019s FSD system is still classified as a Level 2 system<\/a>, meaning drivers need to monitor the driving at all times and be ready to take control at a moment\u2019s notice. If a crash occurs while FSD is being used, Tesla will always blame the driver, claiming that the company\u2019s terms of service require constant driver monitoring. But that\u2019s not how Musk and other executives talk about FSD. In fact, Tesla was forced to add \u201cSupervised\u201d to its marketing materials after regulators complained that the company was misleading customers.<\/p>\n<\/div>\n

\n

So who\u2019s right? Waymo or Tesla? Waymo operates its fully autonomous vehicles in 11 cities, conducting 500,000 paid trips a week. Tesla has its own robotaxis, some of which are supervised by human safety drivers, but an increasing number of which are unsupervised<\/a>. And the company is on the cusp of launching its purpose-built Cybercab \u2013 though its unclear how widespread it will be at launch.<\/p>\n<\/div>\n

\n

But after boasting about his company\u2019s autonomous capabilities for years<\/a>, Musk is still very clearly trailing behind Waymo. It\u2019s unlikely he\u2019s going to suddenly shift his tactics to embrace lidar, but he is undoubtedly aware that he is lagging behind Alphabet\u2019s robotaxis. What he plans on doing about that will become increasingly clear in the months ahead.<\/p>\n<\/div>\n

Follow topics and authors<\/strong> from this story to see more like this in your personalized homepage feed and to receive email updates.<\/span><\/p>\n