If this is the first time you read about Kalman Filters, you are just starting…
What do these articles have in common? Kalman Filters.
When I got started, I was shocked to see the number of people interested in Kalman Filters.
Today, I’d like to tell you exactly if it is really important and if you should start to learn it. I will also tell you how it is used in self-driving cars.
Do you know about Kalman Filters? I didn’t learn it at school, and maybe you didn’t as well! In self-driving car online courses, it is taught a little in sensor fusion modules. In some GitHub repositories, you might find their use for tracking obstacles.
When I arrived at the self-driving car startup, I heard the term Kalman Filter a lot. It was used by people working on totally different domains. When I learned about it, I thought it could only be used for sensor fusion.
But imagine, people from Computer Vision use it. People from Localization use it. People from radio communication use it. People from safety understand it.
And this is only for the self-driving car world. Since it was invented, Kalman Filters have been used for mapping, rocket building, trajectory estimation, geolocalization, augmented reality, it’s in our phones, and in basically every IoT device.
A Kalman Filter is a tool that can predict the future measurement based on a few, or improve the measurement at time t. How? It used math to calculate the state (what you are measuring) and the uncertainty. With time, the state changes and the uncertainty gets lower. If a sensor sends noisy data, you can make it more certain. A few noisy measurements become as good as a very accurate one.
As an example, In sensor fusion, Kalman Filters are used because you have data coming from different sensors with different errors and you need to make one unique estimation.
If the LiDAR says the car is 10 meters away and the radar tells 12, who to trust? How to make a final decision knowing the LiDAR is more precise? Should we get rid of RADARs? A Kalman Filters says we can still benefit from the RADAR, and have a better estimate in the end than if we had a LiDAR alone. But in Computer Vision, suppose you are to detect a lane line, what is the need? The need comes from avoiding false detections and sudden changes. In an autonomous robot, robustness is one of the most important criteria to consider.Building something that isn’t robust is like selling a car that can at any time make a 90° turn.
In Localization, the same principle is used. If your localization module suddenly moves from 30 or 40 cm, you can risk going into the sidewalk.
You can have the use of Kalman Filters in multiple dimensions, you can even use it in drones. It can be used in speed detectors on the road, it is even used in space rockets.
Should you learn Kalman Filters?
I would say yes. But keep in mind that this is a difficult topic and that your filter may be hard to design.
As it turns out, I have created a course to learn Kalman Filters easily, and with total understanding of what’s inside. After it, you’ll have the ease to implement a Kalman Filter from scratch in any situation. If you’re interested in the topic, you should check it out.
📩 If you’d like to receive daily emails like this one to go further, I invite you to join the Think Autonomous’s Daily emails.
This is the most efficient way to understand autonomous tech in depth and join the industry faster than anyone else.