惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

WordPress大学
WordPress大学
博客园 - 司徒正美
小众软件
小众软件
H
Help Net Security
博客园 - 聂微东
宝玉的分享
宝玉的分享
Jina AI
Jina AI
酷 壳 – CoolShell
酷 壳 – CoolShell
阮一峰的网络日志
阮一峰的网络日志
M
MIT News - Artificial intelligence
博客园 - 【当耐特】
U
Unit 42
大猫的无限游戏
大猫的无限游戏
Apple Machine Learning Research
Apple Machine Learning Research
S
SegmentFault 最新的问题
腾讯CDC
MongoDB | Blog
MongoDB | Blog
云风的 BLOG
云风的 BLOG
J
Java Code Geeks
I
InfoQ
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Martin Fowler
Martin Fowler
博客园 - 三生石上(FineUI控件)
Vercel News
Vercel News

Ars Technica

Microsoft issues emergency update for macOS and Linux ASP.NET threat Anthropic tested removing Claude Code from the Pro plan Coyote vs. Acme is finally getting released—with a killer trailer Google unveils two new TPUs designed for the "agentic era" Tabloid reports linking 10 missing and dead scientists spur FBI probe Physicists think they've solved the muon mystery New court ruling blocks many of the government's anti-renewable policies Indian med student rakes in thousands with AI-generated MAGA hottie As EV batteries improve, ChargePoint debuts 600 kW fast charger Our favorite gear at Sea Otter Classic wasn't the bikes—it was the accessories Investors lost billions on Trump’s memecoin. Another gala won’t fix that. Pentagon wants $54B for drones, more than most nations’ military budgets Mozilla: Anthropic's Mythos found 271 security vulnerabilities in Firefox 150 Supreme Court arguments make it clear that FCC fines are "nonbinding" Silo S3 teaser hints at the wasteland's origins Framework's CEO on the RAM crisis and creating a "MacBook Pro for Linux users" Florida probes ChatGPT role in mass shooting. OpenAI says bot "not responsible." Report: Meta will train AI agents by tracking employees' mouse, keyboard use Microsoft removes Call of Duty from Game Pass, lowers subscription pricing Framework Laptop 13 Pro is a major overhaul for the modular, upgradeable laptop Framework Laptop 16 upgrades make it look less like an unfinished prototype Internal emails show how Amazon raises prices across the Internet, lawsuit says Anthropic gets $5B investment from Amazon, will use it to buy Amazon chips CATL's new LFP battery can charge from 10 to 98% in less than 7 minutes AMD Ryzen 9 9950X3D2 Dual Edition review: Tons of cache for tons of dollars What's the deal with spacesuits for the Moon? Will they be ready in time? Loneliness in older adults can often lead to memory impairment Contrary to popular superstition, AES 128 is just fine in a post-quantum world Pentagon pulls the plug on one of the military's most troubled space programs John Ternus will replace Tim Cook as Apple CEO
Start with the sensors, then design the rest: How Zoox bu...
Jonathan M. Gitlin · 2026-04-28 · via Ars Technica

These days, the hype is all about AI and robots, but almost a decade ago, the tech du jour was self-driving. You couldn’t swing a lanyard at CES for the latter half of the last decade without hitting a robotaxi; post-COVID, the number of startups has shrunk, but the technology has definitely matured. Go to the right cities—San Francisco and Austin, Texas, spring to mind—and you might see dozens of sensor-festooned vehicles among the downtown traffic.

The pod-like robotaxis belonging to Zoox stand out. Other robotaxi developers are retrofitting existing vehicles like Hyundai Ioniq 5s with sensors and the computing power necessary for self-driving. Zoox, which was bought by Amazon in 2020, did that with its test fleet, but as it starts to offer ride-hailing services—currently in Las Vegas and San Francisco—it’s doing so with a purpose-built design that looks like it just drove off the set of a big-budget sci-fi production.

“A robotaxi is not a car; it’s not a human-driven vehicle, and the requirements are wildly different, although it has to live in that world,” explained Chris Stoffel, director of robot industrial design and studio engineering at Zoox.

It all starts with the sensors, each perched on a little ledge projecting from the top four corners of the robotaxi’s body. From up there, each has an unobstructed, high-level view, giving the Zoox robotaxi good situational awareness, particularly straight ahead. “Because we don’t have a traditional hood, we’ve optimized our frontal coverage in a way that would be nearly impossible on a retrofitted vehicle,” said Zoox director of sensor engineering Ryan McMichaels.

A Zoox robotaxi picks up riders

Zoox’s robotaxi has a friendly, welcoming design.

Credit: Zoox

Zoox’s robotaxi has a friendly, welcoming design. Credit: Zoox

Then there’s the fact that the robotaxi doesn’t care whether it’s coming or going, thanks to its symmetrical, bidirectional design. The advantages are tantalizing, particularly for a vehicle that’s going to be summoned on demand. There’s no more need for a three-point turn, and with its symmetrical steering axles, it should have unparalleled agility. For example, since both axles have the same degrees of steering, the Zoox robotaxi can crab walk far more effectively than the GM Hummer EV performing its party trick.