Waymo Reveals Custom Chip Powering 4,000 Robotaxis Across U.S. Cities
7 Sources
[1]
Waymo lifts the lid on the 'brain' powering its robotaxis
What's in the trunk of your car? Shopping bags? A spare tire? Jumper cables? What about a high-powered computer capable of performing up to one quadrillion operations a second? Only if you're Waymo. For the first time, Waymo revealed key details about the heavy compute "brain" housed in the trunk
[2]
Waymo has designed a robocar chip to stay ahead of Tesla
To reach their destinations safely, autonomous vehicles have just milliseconds to ingest and process streaming data from more than a dozen cameras. It's a job that's been handled with off-the-shelf AI components thus far, but Waymo has begun rolling its own AI ASICs to optimize the process. It's
[3]
Waymo's custom chip decides what the car sees
Waymo has published the architecture of the computer in its robotaxis, a custom 5nm chip it designed, and the names of its seven hardware suppliers. Nvidia and AMD are still two of them. The chip handles sensor data before the driving system sees it. Waymo has published what is in the boot of its
[4]
Waymo details custom AI silicon for autonomous vehicles
The company said its 'purpose-built 5nm ASIC' chip aims to optimise AV systems for 'low-latency performance'. Waymo, the Alphabet-owned autonomous vehicle (AV) manufacturer, has built a custom AI chip to improve the future performance of its robotaxis. In a blogpost yesterday (20 August) written
[5]
Waymo details the custom chip in its autonomous driving system
Waymo details the custom chip in its autonomous driving system Waymo LLC today shared new details about the computing module that powers its autonomous taxis. The Alphabet Inc. unit operates about 4,000 vehicles in 11 U.S. cities. Most are based on the Jaguar I-Pace crossover, while the rest are
[6]
Waymo Unveils First Custom Robotaxi Chip With More Than 1,000 TOPS of AI Processing Power - Alphabet (NAS
Alphabet Inc.'s (NASDAQ:GOOG)(NASDAQ:GOOGL) Waymo has revealed its first custom-designed robotaxi chip, a purpose-built 5-nanometer ASIC delivering more than 1,000 TOPS of machine-learning performance for front-end sensor processing in its newest Ojai vehicles. Custom Chip Handles Real-Time Sensor
[7]
Waymo's driverless cars run on a secret weapon
Ten years ago, most smartphone makers ran on the same handful of processors from Qualcomm or Samsung. Apple broke that pattern by designing its own chips, and the shift reset who controlled profit and speed in mobile computing, they did the same with their computers. The same fight over who owns
Share
Copy Link
Waymo disclosed the architecture of its autonomous driving system, including a custom 5-nanometer ASIC chip delivering over 1,000 TOPS of machine learning performance. The Alphabet-owned company operates approximately 4,000 vehicles conducting 500,000 paid trips weekly, relying on hardware suppliers including AMD, Nvidia, and TSMC.
Waymo Opens the Trunk on Custom Chip Architecture
Waymo has lifted the curtain on the computing hardware powering its robotaxis, revealing for the first time the custom AI silicon and system architecture that enables its autonomous driving fleet
1
. The Alphabet Inc. subsidiary operates approximately 4,000 vehicles across more than 10 cities, conducting roughly 500,000 paid trips weekly1
5
. The disclosure includes detailed specifications of a custom 5-nanometer ASIC chip, processor capabilities, and a list of seven hardware suppliers the company partners with to build its autonomous vehicle systems3
.Custom AI Silicon Delivers 1,000 TOPS for Real-Time Processing
At the heart of Waymo's system sits a purpose-built 5-nanometer ASIC manufactured by TSMC, designed specifically to handle the massive influx of raw sensor data before it reaches the core machine learning brain
2
4
. The custom chip delivers over 1,000 TOPS of machine learning performance dedicated to front-end processing, handling data extraction from lidar, radar, and camera streams3
4
. This ASIC performs temporal denoising to improve low-light perception in real time, then feeds processed information into a separate inference engine running sensor fusion models3
5
. The chip processes data from 13 high-resolution cameras, four lidar sensors, and six radars simultaneously1
5
.Three Non-Negotiable Design Principles Shape the System
Waymo built its autonomous driving compute around three core requirements: responsive, ruggedized, and redundant
1
. The system must process sensor data with ultra-low latency, making split-second decisions within milliseconds without human backup1
4
. Waymo has scaled compute power 20 times over the past eight years to minimize what the company calls "pixels-to-actuation" delay1
3
. For ruggedization, the hardware endures constant vibration, shock, and temperature swings from Midwest winters to Phoenix summers, using the vehicle's liquid cooling system to maintain optimal temperatures2
5
. Redundancy comes through dual ASICs that normally run as a single unit but can take over if one develops a fault2
3
.Related Stories
AMD and Nvidia Remain Key Partners in Heterogeneous Architecture
Waymo emphasized that its custom chip adds capability rather than replacing merchant silicon from established suppliers
3
. The company describes a "balanced, heterogeneous system" pairing custom machine learning silicon with CPUs, GPUs, and accelerators from AMD, Nvidia, Micron, Samsung, Sandisk, Socionext, and TSMC1
3
. Non-ML tasks like orchestration, data movement, and logging continue to run on components from these partners2
. Waymo states the ASIC is "just one of several exciting custom components we're developing," indicating more in-house silicon is coming3
.Design Draws on 200 Million Autonomous Miles and Challenges Tesla's Approach
The custom chip incorporates insights from more than 200 million miles of fully autonomous driving experience, optimized for both traditional convolutional neural networks and modern transformer models
2
3
. Waymo's disclosure directly counters Tesla CEO Elon Musk's criticism of multi-sensor systems, with Musk calling lidar a "crutch" and arguing that sensor fusion between cameras, radar, and lidar creates dangerous "sensor contention"1
. Waymo contends its robust sensor fusion architecture enables deployment at scale, processing high-fidelity data from all sensors simultaneously to deliver improved perception capabilities that traditional camera-only systems miss1
. The system is now being deployed in the Zeekr-built Ojai four-seater, which Waymo opened to all riders in Los Angeles, Phoenix, and San Francisco3
.References
Summarized by
Navi
[2]
[3]
[4]
[5]
Related Stories
Waymo's sixth-generation robotaxi is ready for passengers and built for high-volume production
12 Feb 2026•Technology
Tesla Unveils AI5 Chip: A Game-Changer in Performance and Manufacturing Strategy
23 Oct 2025•Technology
Alphabet's Waymo Considers Personal Ownership of Robotaxis, Challenging Tesla's Autonomous Vehicle Strategy
25 Apr 2025•Technology
Recent Highlights
1
OpenAI Claims AI Math Breakthrough on Navier-Stokes, Sparks Controversy Over Credit and Future of Research
Science and Research
2
Anthropic Researcher Quits, Warns Self-Improving AI Poses Existential Risk to Humanity
Policy and Regulation
3
Nvidia CEO Jensen Huang Declares AGI Has Arrived With OpenAI's GPT-6 Astra Release
Technology
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
