00:00:00 · Brandon Basso, Ruby Justice Thelot
[00:00:00] S0: And I think there's gonna be a big shift in 2027 into 2028 when we move from... So so look. Way... Wayve is working on these systems that are these l two plus driver assist systems where you can take your hands off the vehicle. What we need to do is move beyond L two plus to L three systems where sometimes those are referred to as not just hands off, but eyes off systems. So those are systems where you can truly check out, do other tasks, and the system is responsible for safety. [00:00:28] S1: Hello everyone, and welcome back to MTS. Today, I am joined by Brandon Basso, who runs the simulation and validation at Wayve, the company teaching cars to drive with end to end AI. So Brandon, welcome to MTS. [00:00:42] S0: Thank you so much for having me. [00:00:43] S1: Thank you for joining. This is pretty exciting. I know we often... We're living here in San Francisco. We see things like Waymo's and Zoox and all of these existing autonomous cars. But what you guys are doing is you're teaching new cars how they can too be anonymous. Tell us a big picture for people who aren't familiar with Wayve.
00:00:43 · Ruby Justice Thelot, Brandon Basso
[00:00:43] S1: Thank you for joining. This is pretty exciting. I know we often... We're living here in San Francisco. We see things like Waymo's and Zoox and all of these existing autonomous cars. But what you guys are doing is you're teaching new cars how they can too be anonymous. Tell us a big picture for people who aren't familiar with Wayve. [00:01:00] S0: Yeah. So like you mentioned, we're in San Francisco, and it's hard to not run into an autonomous car here, whether, you know, it's a Waymo or a car from Zoox or any of the many other providers out there. But there's also every other car on the road that isn't yet autonomous, and Wayve's mission is to have ubiquitous autonomy everywhere for everyone. So all vehicles, not just Teslas, every other vehicle out there. And this starts with a level of autonomy that we call l two or l two plus, which is sort of like you can take your hands off the steering wheel. It can drive you in urban settings, highway settings, and then we're working on all the way up to l four Robotaxi where we have a public pilot in London currently, supervised pilot. [00:01:44] S1: What is the hardest part about this?
00:01:44 · Ruby Justice Thelot, Brandon Basso
[00:01:44] S1: What is the hardest part about this? [00:01:47] S0: Oh my gosh. So many things. Well, I am the safety validation person. Nice. For job security reasons, I have to say that part. But there's so many hard aspects. I mean, as an industry, we've been at this problem for two decades going back to foundational research happening at Berkeley and Stanford and many other institutions around the world. And there's so many hard parts. I I would broadly split it into two big categories, and they're very much addressed in some of the the content that we put out today. So one is how do we make a driver drive better than a human, superhuman, an AI driver? And then two, how do we validate that it's doing what it's doing? Because it's, of course, not good enough to just say, well, we built this great model, and here you go. We have to prove that it works. And both of those parts have their own challenges. I personally focus a lot on the proof part, but they're both extremely hard when you think of the breath of driving that can happen scenarios, weather conditions throughout the entire world, which is what Wayve focuses on literally everywhere. [00:02:49] S1: Tell me a little bit more about safety. Why is safety such a difficult engineering problem?
00:02:49 · Ruby Justice Thelot, Brandon Basso
[00:02:49] S1: Tell me a little bit more about safety. Why is safety such a difficult engineering problem? [00:02:56] S0: Yeah. So, I mean, let's start today with the status quo. The status quo today for driving is not great. It is, a very risky thing that we do. It's costly in terms of time, but also just insurance costs for minor accidents. And then, you know, we don't even need to motivate the the major safety challenges and the populations affected by vehicular accidents in The United States everywhere throughout the world. So it is, I think, incumbent upon us as engineers, as scientists, as product managers, researchers, to think about how we improve all of those problems. So it kinda is one of those things that really, I think, needs no motivation, And why it's such an intent focus for Wayve, well, I mean, it's a focus of every self driving car company out there, whether you're working on l two or l four. We have this novel approach to self driving that we refer to as AV two point o or end to end systems, And there hasn't been a lot of rigorous thinking yet about how we prove the safety of those systems. It's exactly the same problem that folks at Anthropic and OpenAI think about when they are thinking about frontier safety. How do they prove that what the model is outputting is correct performance, not going to mislead you, not going to deceive you, aligned with human expectations. It's the same problem, but the physical interpretation of it.
00:02:56 · Brandon Basso, Ruby Justice Thelot
[00:02:56] S0: Yeah. So, I mean, let's start today with the status quo. The status quo today for driving is not great. It is, a very risky thing that we do. It's costly in terms of time, but also just insurance costs for minor accidents. And then, you know, we don't even need to motivate the the major safety challenges and the populations affected by vehicular accidents in The United States everywhere throughout the world. So it is, I think, incumbent upon us as engineers, as scientists, as product managers, researchers, to think about how we improve all of those problems. So it kinda is one of those things that really, I think, needs no motivation, And why it's such an intent focus for Wayve, well, I mean, it's a focus of every self driving car company out there, whether you're working on l two or l four. We have this novel approach to self driving that we refer to as AV two point o or end to end systems, And there hasn't been a lot of rigorous thinking yet about how we prove the safety of those systems. It's exactly the same problem that folks at Anthropic and OpenAI think about when they are thinking about frontier safety. How do they prove that what the model is outputting is correct performance, not going to mislead you, not going to deceive you, aligned with human expectations. It's the same problem, but the physical interpretation of it. [00:04:18] S1: So there isn't this golden North Star benchmark for what this means. What does that look like when you're trying to innovate at the frontier to define what safety means?
00:04:18 · Ruby Justice Thelot, Brandon Basso
[00:04:18] S1: So there isn't this golden North Star benchmark for what this means. What does that look like when you're trying to innovate at the frontier to define what safety means? [00:04:29] S0: Yeah. So many things. So we we break it down into four core concepts. So safety, of course, has to do with the safety of road users outside of the car, but also the people in the car. There's a comfort element, which is sometimes safety related or adjacent. You know, if you're heartbreaking or swerving or things like that, doing uncomfortable things, sometimes those are precursors of safety. Honestly, equally important is compliance. So there is a dizzying array of traffic rules throughout the world. How you behave with certain signs in Japan versus in Germany is quite different. [00:05:06] S1: Because you're doing London and all across