How self-driving cars work and how safe they are, according to Data Engineer

  • Ben Foxall is interested in how people and technology work together.
  • He started working for Wayve, a startup that uses AI to teach cars to drive.
  • Foxall explained how cars “learn” to drive and why he believes this is the future.

This essay is based on a conversation with Ben Foxall, a data engineer in London. It has been edited for length and clarity.

I’m a data engineer at Wayve, an AI company for self-driving cars, where I lead the robot web team. My team oversees the entire process of how self-driving cars work. We create interfaces – platforms where we can see how the AI ​​software and the car interact – to see what’s happening in Wayve’s robotic cars.

I sometimes describe our user interface as a “window into the robot”. It allows us to see what is going on with the model operating the car. It lets us see what’s happening in the vehicle’s cameras and sensors, as well as its speed, steering, turn signals and braking functions.

We also have an outward-facing UI, which is essentially the tablet that passengers can see on the dashboard when they board a Wayve vehicle. This shows the basic details a passenger needs to know, e.g. B. where the car is at a certain point in time.

Models created by our researchers drive our cars

Our models use a specific approach to the self-driving technology called AV2.0, which can drive with end-to-end deep learning.

Our technology uses a lot of reinforcement learning, taking into account examples from experienced security experts, virtual data generated in our in-house simulator and real-world testing experiences.

With reinforcement learning, you experience something once and learn what needs to be done. We don’t physically code pre-programmed rules into the car that tell it exactly what to do.

It’s similar to how you or I would learn how to drive from experience and the “data” we take in while driving. For example, if you have experienced what to do at a traffic light, you know what to do in a different location in such a traffic light scenario.

We build the model and train it based on the data so that it develops knowledge of, for example, how to stop at a traffic light.

The models our applied scientists generate act as the “driving intelligence” of Wayve’s vehicles. When programmed into our vehicles, which my team is doing, it enables them to drive autonomously.

An incident that happened when I was younger drew me to this industry

I had a friend at school who died in a car accident. She did a classic maneuver and didn’t check her blind spots.

It is tragic that people can die in very avoidable situations. But I think there is significant potential for technology to be more secure than humans because technology can perceive a larger amount of data and doesn’t get tired.

Autonomous vehicle safety officers need to be in our cars when we test a model on the road. They train for three months and are ready to intervene if necessary. Because the model learns from behavior, if a security operator needs to intervene, it knows not to do so again.

I have a feeling people are getting used to the idea of ​​autonomous cars

When I first started working in self-driving technology, people said to me, “Is this safe? Aren’t you afraid of it?” But in recent years it’s changed to, “When will it happen?”

Wayve’s headquarters are in King’s Cross, one of the busiest areas in central London, so it’s a really challenging environment to drive in. Driving around in one of Wayve’s autonomous cars for the first time, I was incredibly impressed to see how our models handled it. Honestly, there are times when you forget you’re in an AI-powered vehicle.

Right now we are building commercial fleets of self-driving cars for urban areas to deliver the last mile of groceries. We have already started trials with our partners at Asda and Ocado Group, two major UK grocery chains.

Humanity’s relationship to technology is constantly changing. My favorite example is light switches. When electricity first appeared they were so mystical, magical. But over the years they have become something we trust, despite the complexity of how they work.

Self-driving cars are incredibly complex and incredible. But being a passenger in an autonomous car will be like flipping a light switch in the future.

Leave a Reply

Your email address will not be published. Required fields are marked *