So, hello everyone. I hope you're all keeping safe. Uh My name is Palak and I work as a senior safety engineer at LYFT level five and I also act as a safety advisor for the University of Toronto Self Driving Car team.I'm really excited to speak at the conference today and share some thoughts around autonomous vehicle safety challenges. And with that, let's get on to the first slide. Now, uh before we get into talking about some key technical and regulatory challenges for A VS, I'd like to take a moment to talk about the of transportation that has increased over the past years from early cars with minimal electronics and with driver performing all the functions to L one autonomy, with driving assist features like AC C adaptive cruise control or lane keep, assist to L four autonomy where the driver is not required to intervene at all.

However, for L four autonomy, there are some restrictions as full autonomy mode can only be activated in certain geo fenced areas all the way to L five autonomy where the vehicle is capable of performing all functions under all conditions through, you know, through ability to sense its surroundings.

Now, as the level of transportation has increased. Over the past years, the level of safety has also increased significantly all the way going from having minimal electronics to support the driver to having multiple levels or layers of autonomy software stack with vehicle, you know, enabling all the functions of vehicle, performing all the functions under all conditions through ability to sense its surroundings.

Now, before I get into, you know, to talk about some of the key technical and regulatory challenges when it comes to deploying A vs on public roads. And at scale, I'd like to give a bird's eye view of different pillars of autonomous vehicles so that you know, when we get into challenges, it will basically give you a good understanding of the scope uh of those challenges. So starting with sensors now, starting with the very top of the vehicle, we have sensors, sensors, you know different sensors like camera, radar and liar. They collect or gather information 360 degrees around the vehicle. That information is fed into autonomy. Now, sophisticated algorithms um you know, they they gather or the process the sensor data enabling the autonomous vehicles to understand its environment. H algorithms like neural networks. They help process information, learn and classify the objects in the surrounding environment.

That information is fed into vehicles controls, that is engines, uh engine brakes and steering system to to um to operate the vehicle or to control the vehicle last. But not least we have electrical electrical signals that moves through the vehicle's controls that connect the computer to the engine brakes and steering system to operate the vehicle. Now, these different pillars of autonomous vehicles, they comprise of key technical terms that you might have used or even heard before. Um And some of them are just highlighted here uh like perception prediction, planning and localization that fall under autonomy software stack that help uh process the information, they process the sensor data. And then based on where the predicted uh or the motion of you know, the surrounding object, it's gonna be, it basically plans a route for the vehicle and that information is fed to vehicles controls. And along with that, we have some other terms like power management, weatherproofing and integrated design. Now each pillar in here, it has its own complexity. And when you combine these different pillars of autonomous vehicles, um the level of safety just increases altogether.

And you know, with that, let's talk about some of the key technical challenges for Avis starting with managing complexity at scale. Now, uh traditional automotive companies uh for the past so many years, they have been manufacturing vehicles with compliance to functional safety standard that is, is 026262 now with autonomy stack and with added complexity, the level of safety increases significantly all the way going from or ranging from detecting sensor failures, uh like detecting camera radar or light or sensor failure to effectively detect localize and classify objects in the surrounding environment is is one of the challenges when it comes to minimizing perception errors.

Also to make sure that the vehicle's controls um like brakes, steering and engine they operate or they basically send out correct. And in a timely fashion, actuator commands is also another area where safety plays an important role. Now, when you talk about functional safety, functional safety is only focused on detecting system failures and reacting to those failures, right? So what happens if there is a sense of failure? What happens, you know if the system or the autonomy software tag does not um you know, detect the obstacle correctly. Um What happens if there is a delay in the actuator command to the vehicle? So all of these are categorized under system failures now consider a scenario where there is no system failure. But because of some technological limitations, like sensor performance limitation or inability to address or inability to comprehend a situation and operate safely or inadequate or having inadequate training data set to, you know, operate under different or in different uh for different conditions or under different conditions.

Now, because of these, you know, corner cases or use cases which is outside of system failure that uh the output of the function is unintended or in other words, the vehicle is not doing what it's supposed to do. And this is where the second challenge or even the second standard comes in the picture which is called sort of now sort of stands for safety of the intended functionality. Sort of standard focuses on, you know, providing design uh verification and validation measures and applying these measures.

It just, you know, helps us achieve safety without failures. So if there is no system failure, then how do we make sure that the system or the the functionality of the vehicle is still intended that it's supposed to, it's doing what it's supposed to do. Now, you know, someone might ask this question like uh how do we achieve safety? In other words, how do we measure safety? How do we know that the system is safe enough? You know, or in other words, how do you define a metric for safety for, for the safety of the system? And this is where the third challenge comes in the picture, verification and validation. Now with, again, going back to the previous thing with autonomy stack and with added complexity, the level of safety increases. And another hand in parallel, the level of testing that's needed, it also increases significantly, you know, for autonomy stack, you have to make sure that you have, you know, captured all the use cases and corner cases that does not just rely on system failures, but also on these sort of specific use cases.

For example, if there is a bright sunlight on camera lens, right, it's still doing what it's supposed to do there is no system failure or malfunctioning behavior, but it might not work the way it's supposed to, which could lead to some unintended functionality. So making sure that, you know, to find a metric for that, it's it's a big challenge last but not least we have cybersecurity now, you know, due to the extreme connectivity within autonomous vehicle components uh with other vehicles that is V two X or in other words, uh vehicle to vehicle communication and their operating environment.

One of the challenges is to protect fleet and customers from cybersecurity attacks. You know, uh connectivity additions include like it backing system or new interfaces between the connected functions or between the control functions of the connected vehicles and other external information sources.

Uh this rich cyberattack or this rich attack surface, it basically creates considerable interest for uh malicious actors with lots of, you know, with, with a again, going back to the complexity and going back to integrated design of the system, uh going to some of the regulatory challenges.

Um you know, along with these key technical challenges where it's still, you know, a lot of things are unknown and we are still working on defining standards for those. Uh There are also some regulatory challenges um when it comes to deploying A vs on public roads and at scale starting with proving customer safety. And this is something that, you know, a lot of people that I've worked with or even you know, I talked to they, you know, and basically think about this and even I do sometimes and I started to work on safety that is proven customer safety right now before any reasonable on roll, roll out customer or consumer safety has to be paramount with rigor testing with rigorous testing for all autonomous vehicle components.

Now, if you think of it in terms of statistics, um in a recent survey, 2/5 respondents, they expressed comfort with low speed. A however, that dropped when asked about a high-speed environment. In other words, or another way to think of it is the expectation from A S is to reduce the number of crashes or especially fatal crashes as compared to human driven cars, right? Because they are run by machines that have less scope of errors. And if A VS are not able to establish this clearly, it will be a significant setback for the adoption and roll out of a, the second one that you think about is liability right now. Current liability laws, they, they mandate manufacturers to, to be liable for safety incidents.

Now, because of the steady shift uh in vehicles responsibility from the driver to an autonomous car may see a similar change in liability from the driver to the manufacturer. So developing unsafe products, it implies that manufacturers will be legally responsible for accidents involving their products.

Last but not least we have building a v conducive infrastructure which is where uh you know, government will have to closely monitor the, the development and evolution of A vs and they, they'll have to determine the impact this technology will have on road infrastructure, our cities and communities when it comes to deploying A vs uh on public roads and at scale short and sweet from my end.

Um And I'm just next to Q and A as I'm open to, you know, answer any questions that you might have. Um or I'm happy to take any comments, suggestions from any of you and obviously, you know, happy to connect to you on linkedin.

Thank you so much for lack. And now we're seeing a wild kaleidoscope of your shared screen. There you go.

Sorry, always wild.

Um Yeah, I mean, so far from your conversation, there's a few things I think that stand out. I know sometimes when you're um kind of moving quickly to, to get all the information in for us, there's sometimes things that you think to yourself, I would have spent more time there, but I wanted to make sure, you know, everything was said correctly within my time seeing as we do have a little bit more time.

Is there one piece you'd love to kind of like give us a little bit more on while we have you.

Um Sure, I think when it comes to, you know, implementing safety strategies are key different principles of safety, right? When, when you talk about building uh safety principles for A VS, we basically start with functional safety as a basis as I mentioned before, you know, traditional automotive companies, they have been uh manufacturing vehicles with compliance to this ISO 26262 or functional safety standard for like so many years when we talk about implementing safety principles for A VS, we basically start from scratch.

In other words, we start from the basic, so we have to apply functional safety, which you know, helps us define some key safety uh management related principles right beyond is where you know, a lot of unknowns and a lot of these corner cases and use cases that comes in the picture and which is where I think a lot of um focus is gonna go in and a lot of standards or a lot of organizations, either I triple E or SI E they have been working on right now.

Even A BS C which is a safety consortium, they have been trying to, you know, get to a point where you, you know, what, how do you achieve safe, how do you define a metric to safety, you know, for A vs? Because it's really difficult to, when someone asks me the question, like, you know, how do you know whether that's safe enough? You can do X number of hours of testing, you can, you know, you can do different levels of testing, you can test it, you know, at different levels, you can test it on the vehicle, you can go to a field to test the vehicle or you can do it on the, on the bench, right? Which is like a specific uh test set up for the safety. But how do you know it's safe enough? So I think defining a metric um or, you know, uh how do you measure safety is a big question or a challenge, you know, uh for eight,

do you feel like pack, like the speed of the safety um testing and mechanisms is going at the pace that you expect it should go.

Uh I guess yes and no, I mean, all the tech companies they are working on right now they are doing, you know, amazing job, right? But I guess it, that uh comes back to the question of uh what are they like whatever they are doing is that good enough? Um again, going back to the same thing, right? The speed at which they are going, I don't think that commercializing A VS is gonna happen right away or even for the next couple of years, it's gonna take a while for us to commercialize A VS. Right? And as we were talking about L four autonomy right now, we are only able to engage in autonomy for most of the, you know, uh tech companies that you talk about, we're only able to engage in autonomy and test it out uh just in certain areas or geo fenced area. Right, but commercializing that over like everything, it's gonna be a big challenge and I don't think we have the regulatory standards in place yet to even get to that. So even if we go to that L four autonomy going from L four to L five is gonna be a big jump.

And yeah,

do you think regulatory standards will happen in some countries before others? Like where legalization will happen earlier in certain areas of the world? And if so is there, is the US one of them, where is the kind of fastest moving process on the regulation side?

Um That's more on the regulatory side. I'm not so sure I know a lot more about regulatory because it goes back to compliance and legal side of things. But I know a lot of folks are actually working on it and Europe being one of those. Um I'm not sure if they are. Um and as compared to us, whether they are, you know, uh ahead or they are behind but, but yeah,

yeah. Well, I asked in that country just because that's where you're the office that you're at is located. But I think so interesting. So like where, what do you see the future as in this realm?

Um just sit back and relax, take a nap, you know, read a book and try and not think about safety, you know, and this is where the regulatory challenge, it's, it's very important because proving customer safety and, you know, uh, we'll have to make sure that, uh, there are different ways to do that, but I guess we'll have to make sure that we prove customer or consumer safe, deploy or start to deploy a vs on public roads and even at scale because if you can do that, then I think the, the only thing that I, I'm gonna do is just sit back, relax, take a nap or enjoy a drink and, you know, just let the, the car do its job.

Yeah. Yeah, absolutely. And I'm sure people are commenting and thinking that same thing, right, that you asked me to get to work on my food and not

need to do anything.

Um, well, I have a question in the chat too for you. How do you think A I is going to impact on autonomy, autonomous vehicles specifically?

Well, I, I guess a lot of it when you talk about autonomy software stack, right? Uh A I or machine learning, I think a lot of it is just interlinked together. So it's, you know, it's not interdependent, they're all so dependent. And when you think about all of these different levels of autonomy software stack, like prediction, perception, localization or planning, this is actually the bigger piece of us to ensure safety, right? Vehicle control is something that we have been doing in doing it, you know, before as well.

And for us to make sure that we are able to send out correct actuary commands to the vehicle. We still have some idea of how to do that but making sure that you're getting correct or adequate draining data set from neural networks or we are getting or we are, we don't have or minimizing perception errors that we are able to detect obstacles correctly and in a timely fashion, right?

How do you make sure of that? I think that this is where it's actually a big challenge and this is where I think A I and machine learning is, is gonna come in the picture. Of course.