Jennifer Healey

Jennifer Healey If cars were talking, accidents could be avoided

jennifer_healey

Η Jennifer Healey is a PhD of her s of computers from the MIT. Works on Intel Corporation Labs and researches devices and systems that will enable major innovations. In a lecture with "If cars could talk, maybe accidents could be avoided," he said TED Talks, showed us how he imagines a world without (traffic) accidents.

The translation into Greek was done by Nikolao Benia and the editing by Dimitri Katevati.
Watch the video

Let's face it: Driving is dangerous. It's one of the things we don't want to think about, but the fact that religious and charms are placed on boards around the world betrays the fact that we know this to be true. Traffic accidents are the leading cause of death among 16- to 19-year-olds in the US — the leading cause of death — and 75% of those accidents are not drug or alcohol related.

So what happens? No one can say for sure, but I remember my first crash. I was a new highway driver and in the lead car I saw the lights on the brakes. I think "Okay, all right, the guy slows down, I'll slow down too". I brake. But no, the guy did not slow down. The formula stopped, completely stopped completely on the highway. Did he go from 100 kilometers to 0? I hit the brake very hard. I felt the ABS kicking and the car was still moving, and it was not going to stop, and I know it will not stop, and the airbag opens, the car is broken, and fortunately, no one was injured. But I had no idea that that car would stop and I think we can do something much better than that. I think we can turn the road experience by letting our cars talk to each other.

I want you to think for a moment about what the road experience is like now. You get in the car. You close the door. You are in a glass bubble. You cannot directly sense the world around you. You are inside an extension of yourself. You have to navigate it on partially visible highways, in and between other metal behemoths, at superhuman speeds. Correctly; And the only things that guide you are your two eyes. Right, those are the only ones you have, eyes that aren't really designed for that purpose, but people ask you to do things, like when you want to change lanes, what's the first thing they ask you to do? Take your eyes off the road. Correctly. Stop looking where you're going, turn around, look in your blind spot and keep driving without looking where you're going. You and everyone else. This is the safe way to drive. Why do we do this? Because we have to, we have to choose, do I see here or do I see there? What is more important? And we usually do amazing picking and choosing what to look out for on the road. But, occasionally something will escape us. Occasionally we feel something either wrong or too late. In countless accidents, the driver says, "I didn't see that coming." And I believe that. I believe that. That much we can notice.

But now there is the technology that can help us improve this. In the future, with cars exchanging data between them, we can see not only three cars in front and three cars back, right and left, all at the same time, panoramic view. we can see inside these cars. We can see the speed of the car ahead, see how fast someone goes or stops. If someone stops completely, I'll know.

And with calculations, algorithms and predictive models, we will be able to see the future. You may think that this is impossible. How to predict the future? This is something very difficult. Actually, no. For cars, it's not impossible. Cars are XNUMXD which have a specific position and speed. They move on a road surface. They often follow predetermined routes. It's really not that hard to make reasonable predictions about where a car will be in the near future. Even if when you're in a car and a motorcyclist comes – boom! – at 140 km/h, switching lanes — I know you've had that experience — that guy didn't "come out of nowhere." This guy has probably been on the road for the last half hour. (Laughter) Right? I mean, someone has seen him. 15, 30, 50 kilometers before, someone has seen him, and once a car sees him and puts him on the map, he's on the map — position, speed, good estimate that he'll keep going at 140 km per hour. You'll know, because your car will know, because the other car whispered something in his ear, like, "By the way, five minutes, motorcyclist, watch out." You can make reasonable predictions about how cars behave. I mean they are Newtonian objects. That's the good thing about them.

So how do we get there? We can start with something as simple as sharing our location data between cars, just GPS sharing. If I have a GPS and a camera in my car, I have a pretty accurate idea of ​​where I am and how fast I'm going. With machine vision, I can estimate where the cars around me are, roughly, and where they're going. Same with the other cars. They can have an accurate idea of ​​where they are and a vague idea of ​​where the other cars are. What happens when two cars share this data, if they talk to each other? I can tell you exactly what's going on. Both models are improving. Everyone wins. Professor Bob Wang and του έχουν κάνει προσομοιώσεις σε για το τι συμβαίνει όταν ασαφείς εκτιμήσεις συνδυάζονται, ακόμα και σε μικρή συμφόρηση, όταν αυτοκίνητα απλά μοιράζονται δεδομένα GPS, και μεταφέραμε αυτή την έρευνα προσομοιώσεων υπολογιστή σε κλίνες δοκιμών ρομπότ που έχουν τους πραγματικούς αισθητήρες που υπάρχουν τώρα στα αυτοκίνητα, σε αυτά τα ρομπότ: στερεοφωνικές , GPS and XNUMXD laser rangefinders, which are common in backup systems. We also customized a token short range and the robots talk to each other. When these robots approach each other, they accurately track each other's position and can avoid each other.

Now we add more robots to the site and we have some problems. One of the problems, when you get a lot of chatter, it's hard to edit all the packages, so you have to set priorities and here the predictive model helps you. If robot cars follow the predicted paths, you do not pay much attention to these packages. You give priority to what seems to be going a little out of the way. This type can create a problem. And you can predict a new course. So, not only do you know it will go out of the way, you know how. And you know which guides you should warn to do aside.

And we wanted to do - what is the best way to alert everyone? How can cars whisper "Do you have to step aside?" It depends on two things: first, the ability of the car and second, the ability of the driver. If someone has a really good car but is using the phone or, you know, doing something, they are probably not in the best position to react in a sudden situation. So we started a separate research by modeling the driver's condition. Now, using a series of three cameras, we can detect if the driver is looking ahead, looking away, looking down, is on the phone or drinking coffee. We can predict the accident and we can predict who, which cars, are in the best position to move off course to calculate the safest route for everyone. Basically, these technologies exist today.

I believe that the biggest problem we face is our willingness to share our data. I think it's a very worrying concept, the idea that our cars will be watching us, talking to us on other cars, gossiping us all the time. But I think it can be done in such a way as to protect our privacy, just as now, when I see your car outdoors I really do not know about you. If I look at your traffic signs, I do not know who you are. I think our cars will talk about us behind our back.

(Laughs)

And I think it will be something very good. I want you to think for a moment if you really do not want the abstract teenager behind you to know that you are braking, that you intend to stop. With the voluntary sharing of our data, we can do the best for everyone.

So leave your car gossiping you. It will make roads safer.

Thank you.

iGuRu.gr The Best Technology Site in Greecefgns

every publication, directly to your inbox

Join the 2.100 registrants.

Written by giorgos

George still wonders what he's doing here ...

Leave a reply

Your email address is not published. Required fields are mentioned with *

Your message will not be published if:
1. Contains insulting, defamatory, racist, offensive or inappropriate comments.
2. Causes harm to minors.
3. It interferes with the privacy and individual and social rights of other users.
4. Advertises products or services or websites.
5. Contains personal information (address, phone, etc.).