5 – 03 Localization V1

The very first problem I’m trying to solve is called localization. It involves a robot that’s lost in space. It could be a car, it could be a mobile robot. So he has his environment and the poor robot has no clue where it is. Similarly, we might have a car driving on a highway and this car would like to know where it is. Is it inside the lane or is it crossing lane markers? Now, the traditional way to solve this problem uses satellites, and these satellites emit signals that the car can perceive. That’s known as GPS, short for Global Positioning System. It’s what you have in your dashboard if you have a car with GPS that shows you the maps and shows you where you are. Now unfortunately, the problem with GPS is it’s really not very accurate. It’s really common for a car to believe to be here but it has two, all the way up to 10 meters of error. So you try to stay in the lane with 10 meters of error, you are far off and you’re driving right over here and you crash. So for our self-driving cars to be able to stay in lanes using localization, we need something like 2 to 10 centimeters of error and then, we can drive with GPS in lanes. So the question is, how can we know where we are with 10-centimeter accuracy? That’s the localization question.

%d 블로거가 이것을 좋아합니다: