Imagine a scenario where you’re exhausted after a long day, yet you still need to drive home. Or perhaps you’ve had a drink or two and think you’re the most sober among your friends. Wouldn’t it be great if your car could take over and get you home safely? This is the promise of self-driving cars, a concept that has been around since 1939 when General Motors introduced it at the World’s Fair.
Fast forward to today, and this dream is becoming a reality. Recently, Nevada granted Google’s self-driving car the first license for an autonomous vehicle, allowing it to be tested on public roads. California is considering similar legislation, indicating that autonomous cars are not just a futuristic concept but are becoming part of our present.
At Stanford University, we’re also working on autonomous vehicles, but with a unique twist. Our focus is on developing robotic race cars that can push the boundaries of physical performance. Why race cars, you ask? There are two compelling reasons.
Firstly, before people trust autonomous cars, these vehicles need to perform as well as the best human drivers. If you’re like most people who believe they’re above-average drivers, you’ll understand the high standards we aim to meet.
Secondly, race car drivers utilize every bit of friction between the tires and the road to maximize speed. We want our autonomous cars to use these capabilities to avoid accidents, especially in challenging conditions like icy roads. The goal is to create a car that can handle any situation safely.
There’s a third reason for our focus on race cars: a passion for racing. In our lab, we’ve developed what we believe is the world’s first autonomously drifting car. This car, named P1, is a student-built electric vehicle that can drift around corners like a rally car, maintaining control even on slippery surfaces.
We’ve also collaborated with Volkswagen and Oracle to create an autonomous race car that has reached speeds of 150 mph on the Bonneville Salt Flats and navigated the challenging Pikes Peak Hill Climb in Colorado—all without a driver.
Through our work, we’ve gained a deep appreciation for human race car drivers. These drivers can map out a racetrack and find the fastest route without the aid of algorithms. They consistently push their cars to the limits, lap after lap, showcasing extraordinary skill.
Curious about what happens in their minds, we decided to study the brain activity of race car drivers. By placing electrodes on the head of John Morton, a seasoned driver, we monitored his brain activity as he raced around the track. Our goal was to understand the mental processes involved in high-speed driving.
Neuroscientists have identified patterns in brain waves that indicate cognitive activity. For instance, alpha waves are prevalent when the brain is at rest, while beta waves are associated with tasks requiring visual processing and decision-making. By measuring these waves, we can gauge the mental workload of a driver.
We conducted our research at the Laguna Seca Raceway, known for its challenging Corkscrew curve. As John navigated this complex section, his mental workload spiked, as expected. However, when the car began to slide and he corrected it, his mental workload remained unchanged, suggesting that these actions were instinctive.
These findings have inspired us to make our autonomous vehicles more intuitive. Instead of relying solely on algorithms, we aim to incorporate the reflexive actions of skilled drivers into our cars. This approach could lead to autonomous systems that not only drive as well as humans but also enhance our driving experience.
As we advance in this technological journey, we must consider the ideal balance between human and machine. Can technology help us reach our full potential by complementing our natural abilities? As we ponder this question, let’s draw inspiration from the remarkable capabilities of the human mind and body.
Thank you for joining us on this exploration of the future of autonomous vehicles.
Create a simulation of a self-driving car using software like MATLAB or Python. Focus on programming the car to navigate a virtual racetrack, incorporating elements like speed, friction, and obstacle avoidance. This will help you understand the complexities of autonomous vehicle navigation and control.
Conduct a study on brain wave patterns using EEG data. Analyze how different brain waves, such as alpha and beta waves, correlate with cognitive tasks. This activity will give you insights into the mental processes involved in high-speed driving and decision-making.
Participate in a debate on the advantages and disadvantages of autonomous vehicles compared to human drivers. Consider aspects such as safety, efficiency, and ethical implications. This will encourage you to critically evaluate the role of technology in driving.
Work in teams to construct a small-scale autonomous race car using kits like Arduino or Raspberry Pi. Program the car to complete a set course, focusing on speed and precision. This hands-on project will enhance your understanding of robotics and autonomous systems.
Write a paper discussing the ethical considerations of self-driving cars, such as decision-making in accident scenarios and data privacy. This will help you explore the societal impacts of autonomous technology and the responsibilities of engineers and developers.
**Sanitized Transcript:**
[Music][Applause]
So, how many of you have ever gotten behind the wheel of a car when you really shouldn’t have been driving? Maybe you were out on the road for a long day and just wanted to get home. You were tired but felt you could drive a few more miles. Perhaps you thought, “I’ve had less to drink than everybody else; I should be the one to go home.” Or maybe your mind was just entirely elsewhere. Does this sound familiar to you?
Now, in those situations, wouldn’t it be great if there was a button on your dashboard that you could push, and the car would get you home safely? That has been the promise of the self-driving car, the autonomous vehicle, and it’s been a dream since at least 1939 when General Motors showcased this idea at their Futurama booth at the World’s Fair.
This dream has always seemed about 20 years in the future. However, two weeks ago, that dream took a step forward when the state of Nevada granted Google’s self-driving car the very first license for an autonomous vehicle, clearly establishing that it’s legal for them to test it on the roads in Nevada. Now, California is considering similar legislation, which would ensure that the autonomous car is not just something that has to stay in Vegas.
In my lab at Stanford, we’ve been working on autonomous cars too, but with a slightly different spin. We’ve been developing robotic race cars that can actually push themselves to the very limits of physical performance.
Now, why would we want to do such a thing? There are two really good reasons for this. First, we believe that before people turn over control to an autonomous car, that car should be at least as good as the very best human drivers. If you’re like me and the other seventy percent of the population who know that we are above-average drivers, you understand that’s a very high bar.
There’s another reason as well. Just like race car drivers can use all of the friction between the tire and the road and all of the car’s capabilities to go as fast as possible, we want to use those capabilities to avoid any accident we can. You may push the car to the limits not because you’re driving too fast, but because you’ve hit an icy patch or the conditions have changed. In those situations, we want a car that is capable enough to avoid any accident that can physically be avoided.
I must confess there’s kind of a third motivation as well: I have a passion for racing. In the past, I’ve been a race car owner, a crew chief, and a driving coach—though maybe not at the level you might expect. One of the things we’ve developed in the lab is what we believe is the world’s first autonomously drifting car. This is another one of those categories where maybe there’s not a lot of competition.
This is P1, an entirely student-built electric vehicle that can drift around corners using its rear-wheel drive and front-wheel steer-by-wire. It can get sideways like a rally car driver, always able to take the tightest curve even on slippery surfaces without spinning out.
We’ve also worked with Volkswagen and Oracle on an autonomous race car that has raced at 150 miles an hour through the Bonneville Salt Flats, gone around Thunderhill Raceway Park in the sun, wind, and rain, and navigated the 153 turns and 12.4 miles of the Pikes Peak Hill Climb route in Colorado with nobody at the wheel.
I guess it goes without saying that we’ve had a lot of fun doing this. But in fact, there’s something else we’ve developed in the process of creating these autonomous cars: a tremendous appreciation for the capabilities of human race car drivers.
As we looked at how well these cars performed, we wanted to compare them to our human counterparts, and we discovered that human drivers are amazing. We can take a map of a racetrack, a mathematical model of a car, and with some iteration, we can actually find the fastest way around that track. We line that up with data recorded from a professional driver, and the resemblance is absolutely remarkable.
Yes, there are subtle differences, but the human race car driver is able to drive an incredibly fast line without the benefit of an algorithm that compares the trade-off between going as fast as possible in a corner and shaving a little time off the straight. Not only that, they can do it lap after lap, consistently pushing the car to the limits every single time. It’s extraordinary to watch.
You put them in a new car, and after a few laps, they find the fastest line in that car and they’re off to the races. It really makes you think. We’d love to know what’s going on inside their brains.
As researchers, that’s what we decided to find out. We decided to instrument not only the car but also the race car driver to get a glimpse into what was going on in their heads as they raced around the track.
Now, this is Dr. Elena Harbout applying electrodes to the head of John Morton, a former Can-Am and IMSA driver who is also a class champion at Le Mans—a fantastic driver and very willing to put up with graduate students and this sort of research. She’s putting electrodes on his head so we can monitor the electrical activity in John’s brain as he races around the track.
Clearly, we’re not going to put a couple of electrodes on his head and understand exactly what all of his thoughts are on the track. However, neuroscientists have identified certain patterns that let us tease out some very important aspects of this. For instance, the resting brain tends to generate a lot of alpha waves, while beta waves are associated with cognitive activity like visual processing—things where the driver is thinking quite a bit.
We can measure this and look at the relative power between the theta waves and the alpha waves, giving us a measure of mental workload—how much the driver is actually challenged cognitively at any point along the track.
We wanted to see if we could record this on the track, so we headed down south to Laguna Seca, a legendary raceway about halfway between Salinas and Monterey. It has a curve called the Corkscrew, which is a chicane followed by a quick right-hand turn as the road drops three stories.
The strategy for driving this, as explained to me, was to aim for the bush in the distance, and as the road falls away, you realize it was actually the top of a tree. Thanks to the REVS program at Stanford, we were able to take John there and put him behind the wheel of a 1960 Porsche Abarth Carrera. Life is way too short for boring cars!
Here you see John on the track, going up the hill. You can see his mental workload measuring here in the red bar as he approaches. He has to downshift, then turn left, look for the tree, and down. Not surprisingly, you can see this is a pretty challenging task, and his mental workload spikes as he goes through it, as you would expect with something that requires this level of complexity.
But what’s really interesting is to look at areas of the track where his mental workload doesn’t increase. We’re going to take you around now to the other side of the track, turn three, where John’s going to go into that corner, and the rear end of the car is going to begin to slide out. He’ll have to correct for that with steering.
Watch as John does this here; watch the mental workload and the steering. The car begins to slide out, and he makes a dramatic maneuver to correct it, yet there’s no change whatsoever in the mental workload. It’s not a challenging task—in fact, it’s entirely reflexive.
Our data processing on this is still preliminary, but it seems that these phenomenal feats that race car drivers perform are instinctive. They are things that they have simply learned to do, requiring very little mental workload for them to perform these amazing feats. Their actions are fantastic; this is exactly what you want to do on the steering wheel to catch the car in this situation.
This has given us tremendous insight and inspiration for our own autonomous vehicles. We started to ask the question: can we make them a little less algorithmic and a little more intuitive? Can we take this reflexive action that we see from the very best race car drivers and introduce it to our cars? Maybe even into a system that could be in your car in the future?
That would take us a long step along the road to autonomous vehicles that drive as well as the best humans. But it’s made us think a little bit more deeply as well. Do we want something more from our car than simply being a chauffeur? Do we want our car to perhaps be a partner, a coach—someone that can use their understanding of the situation to help us reach our potential?
Can technology not simply replace humans but allow us to reach the level of reflex and intuition that we’re all capable of? So, as we move forward into this technological future, I want you to pause and think about that for a moment. What is the ideal balance of human and machine?
As we think about that, let’s take inspiration from the absolutely amazing capabilities of the human body and the human mind.
Thank you.
[Music]
Autonomous – Capable of operating independently without human intervention, often through the use of advanced control systems and algorithms. – Autonomous vehicles are designed to navigate and make decisions on the road without human input.
Vehicles – Machines, typically motorized, used for transporting people or goods from one place to another. – Engineers are developing electric vehicles to reduce carbon emissions and reliance on fossil fuels.
Racing – The competitive activity of driving vehicles at high speeds, often on a track, to determine which is the fastest. – The engineering team focused on optimizing the car’s aerodynamics for the upcoming racing event.
Performance – The efficiency and effectiveness with which a machine or system operates, often measured in terms of speed, power, and reliability. – The performance of the new engine was tested under various conditions to ensure its reliability.
Friction – The resistance that one surface or object encounters when moving over another, often affecting the efficiency of mechanical systems. – Reducing friction in the engine components can significantly improve fuel efficiency.
Speed – The rate at which an object covers distance, often a critical factor in the design and testing of vehicles. – The speed of the prototype was measured using advanced sensors to ensure it met the design specifications.
Drivers – Individuals who operate vehicles, or in a technical context, software or hardware components that control devices. – The new software drivers were installed to enhance the performance of the robotic arm.
Algorithms – Step-by-step procedures or formulas for solving problems, often used in computing and engineering to process data and make decisions. – The navigation system relies on complex algorithms to calculate the most efficient route.
Technology – The application of scientific knowledge for practical purposes, especially in industry, including the development of machinery and equipment. – Advances in battery technology have made electric vehicles more viable for long-distance travel.
Intuition – The ability to understand or know something immediately, often used in engineering to make quick decisions based on experience and insight. – Engineers often rely on their intuition to troubleshoot unexpected issues during testing.
