
CEO at @wayve_ai teaching cars how to drive with machine learning 🇳🇿
London, UK
Joined March 2017
- Tweets1.3K
- Following736
- Followers18.5K
- Likes3.1K
"The way that we've built the driving stack is with safety as an intrinsic property vs. an extrinsic bolt-on property".
Revisiting Brandon Basso on @MTSlive last week, where he explained our learned approach to embedding safety in our AI Driver, visualized through the Wayve LSE.
Thank you, Governor Koike and @Tokyo_gov, for visiting our London HQ and riding with our AI Driver on London’s streets. A privilege to exchange ideas on the future of urban mobility. 🇬🇧 🇯🇵
self-supervised, end-to-end trained safety which can predict risk in dynamic and complex scenes
Last week we released our three part series on how to solve safety and validation within an end-to-end learning paradigm. Something we've been working on for a long time! Brandon Basso shares more on @MTSlive here:
youtu.be/XEJtFxyWlXk?is=yCrF…
Alex Kendall retweeted
私もちゃっかり映り込んでしまいましたw
小池都知事、英国でロボタクシー視察 AIでロンドンとも連携強化 - 日本経済新聞 nikkei.com/article/DGXZQOUC0…
This week in Japan I met many Government officials. What resonated in every conversation: importance of self-driving for national strategy, belief in end-to-end AI, desire to bring autonomy broadly, especially to rural and aging population and kei cars! @wayve_ai will support!
Wayve's Brandon Basso demos how its self-driving AI learns what safe driving looks like, rather than relying on HD maps and external safety checkers:
"The way that we've built the driving stack is with safety as an intrinsic property vs an extrinsic bolt-on property."
"Lots of systems have high-definition maps that are really like checkers. What if the stop sign isn't there? What if it moved? What if there's a temporary stop sign? What if the stop sign is connected to a bus that's moving?"
"The checker systems tend to be the ultimate bottleneck and limit of system performance."
"What you see on the screen here is a learned representation of safety. You can think of this as like a future occupancy map. The red areas are the don’t drive in areas."
"We use this system not as a bolt-on checker, but as an explicit head, a task that we learn, on how to drive safely."
@wayve_ai
Replying to @wayve_ai
First, we embed it into behavior. Safety assessment is part of how the Wayve AI Driver makes decisions. The Wayve Learned Safety Envelope (LSE) anticipates risk and makes safety-relevant judgments observable, showing where it is and isn’t safe to drive.
Together with defined safety responsibilities, it helps answer: how should the AI Driver act, what is safe, and can it continue with confidence?
wayve.ai/thinking/building-a…
Alex Kendall retweeted
Replying to @alexgkendall
I had a very great & safe experience in the car today!
Since 2017, I've been repeatedly told that end-to-end AI can't be safe, and traditional rule-based systems are required for autonomous driving.
But we persevered. Today we are releasing our strategy for Learned Safety, the result of a decade of research.
wayve.ai/technology/learned-…
🏗️ Build it: The Wayve Learned Safety Envelope wayve.ai/thinking/building-a…
🧪 Validate it: Closed-loop simulation with GAIA, learned evaluation through GRADER wayve.ai/thinking/validating…
📚 Ground it: Language and reasoning wayve.ai/thinking/language-s…
2
6
752
Great to meet Japan's Minister of Transport @T_Ibayashi today in Tokyo alongside our partners @NissanMotor, @TAXI_HINOMARU and @Uber, to share our strategy for upcoming robotaxi launch 🤝
城内成長戦略相 AI搭載の自動運転車に試乗 “国が企業支援”
news.web.nhk/newsweb/na/nd-2… #nhk_news
Alex Kendall retweeted
城内成長戦略担当相、自動運転システム搭載車に試乗…技術支援に取り組む考え強調
news.ntv.co.jp/category/poli…
I'm back in Japan this week! After we met in London it was an honour to host Minister @minoru_kiuchi for a @wayve_ai drive in Tokyo and hear about how Japan has selected physical AI and autonomous driving as a key technology to accelerate economic growth 🇯🇵
Covered in Nikkei here:
nikkei.com/article/DGXZQOUA0…
5
607
Alex Kendall retweeted
“I think robotics is going to go through a hype cycle just like autonomy did.” - @alexgkendall, CEO of @wayve_ai
Alex’s argument is that the route to a general-purpose robotics company runs through self-driving. Driving is where you can deploy millions of vehicles doing useful work today, and the data and revenue from that is what funds the move into everything else.
End-to-end deep learning is not only the best approach for driving models, but also for safety, world and reward models.
I was back in San Francisco last week to share more about our vision at the #LongHorizon summit on Embodied AI.
Alex Kendall retweeted
Proud to collaborate with @wayve_ai and @Stellantis, alongside the French Government, to advance safe, responsible AV deployment in France. 🇫🇷
The Wayve AI Driver will integrate NVIDIA Halos OS on NVIDIA Hyperion.
📖 wayve.ai/press/wayve-stellan…
Wayve, @Stellantis , @nvidia, and the French Government are collaborating to advance safe, responsible AV deployment in France. 🇫🇷
Stellantis’ L4-Ready Platforms™. The Wayve AI Driver. NVIDIA Halos OS on NVIDIA Hyperion. Together, these capabilities position France as the base for an ecosystem spanning the full AV value chain, from silicon to vehicles.
Wayve, @Stellantis , @nvidia, and the French Government are collaborating to advance safe, responsible AV deployment in France. 🇫🇷
Stellantis’ L4-Ready Platforms™. The Wayve AI Driver. NVIDIA Halos OS on NVIDIA Hyperion. Together, these capabilities position France as the base for an ecosystem spanning the full AV value chain, from silicon to vehicles.




















