There are 3 main sensors types used in self-driving cars for environment perception:
βͺοΈ Camera
βͺοΈ Radar
βͺοΈ Lidar
They all have different advantages and disadvantages. Read below to learn more about them.
Thread π
1οΈβ£ Camera
The camera is arguably the most important sensor - the camera images contain the most information compared to the other sensors.
Modern cars across all self-driving levels have many cameras for a 360Β° coverage:
βͺοΈ BMW 8 series - 7
βͺοΈ Tesla - 8
βͺοΈ Waymo - 29
This is an example from Tesla of what a typical camera sees and detects in the scene. Videos from other companies look very similar.
2οΈβ£ Radar
The radar is one of the oldest sensors used for automation - it is used since 1999 for adaptive cruise control.
It uses the Doppler effect to measure distance and relative velocity to other objects and is very accurate.
Again, modern cars usually have several radars.
Classical radars have fairly low resolution and the raw data is difficult to interpret visually. There is a new generation of imaging radars that promise much better resolution!
Take a look at this video to get an intuition what a radar "sees".
3οΈβ£ Lidar
This is the hot topic in self-driving cars currently!
A laser scanner shoots multiple rays measuring distance to objects and they do this very accurately.
360Β° lidars are typical for L4 cars, but smaller lidars are already being integrated into production cars.
There are many companies now working on solid state lidars that can be easily integrated in the grill of a car.
Take a look at this video to see how the point cloud from such a lidar looks like.
Comparison π
There is no perfect sensor - each of them has its own advantages and disadvantages! Take a look the the table below for a comparison.
The best way is to combine all of them for maximum redundancy and robustness! No everybody agrees to that, though... π€·ββοΈ
If you liked this thread and want to read more about self-driving cars and machine learning follow me @haltakov!
I have many more threads like this planned π
β’ β’ β’
Missing some Tweet in this thread? You can try to
force a refresh
There are different computer vision problems you need to solve in a self-driving car.
βͺοΈ Object detection
βͺοΈ Lane detection
βͺοΈ Drivable space detection
βͺοΈ Semantic segmentation
βͺοΈ Depth estimation
βͺοΈ Visual odometry
Details π
Object Detection ππΆββοΈπ¦π
One of the most fundamental tasks - we need to know where other cars and people are, what signs, traffic lights and road markings need to be considered. Objects are identified by 2D or 3D bounding boxes.
Relevant methods: R-CNN, Fast(er) R-CNN, YOLO
Distance Estimation π
After you know what objects are present and where they are in the image, you need to know where they are in the 3D world.
Since the camera is a 2D sensor you need to first estimate the distance to the objects.
Interesting results from the small experiment... π
This was actually a study reported in a Nature paper. Most people offer additive solutions (adding bricks) instead of substractive solutions (removing the pillar).
In this example, the most elegant solution is to remove the pillar completely and let the roof lie on the block. It will be simpler, more stable and won't cost anything.
Some people quickly dismiss this option assuming this is not allowed, but it actualy is π
This isn't because people don't recognize the value, but because many don't consider the substractive solution at all. Me included πββοΈ
The paper shows that this happens a lot in real life, especially in regulation. People tend to add new rules, instead of removing old ones.
End-to-end approach to self-driving π₯ πΈοΈ πΉοΈ
I recently wrote about the classical software architecture for a self-driving car. The end-to-end approach is an interesting alternative.
The idea is to go directly from images to the control commands.
Let me tell you more... π
This approach is actually very old, dating back to 1989 and the ALVINN model by CMU. It is a 3-layer neural network using camera images and a laser range finder.
A modern example is Nvidia's PilotNet - a Convolutional Neural Network with 250M parameters, which takes as input the raw camera image and predicts directly the steering angle of the car.
No explicit lane boundary or freespace detection needed!
Open-Source Self-Driving Car Simulators πΉοΈ π
You want to play around with self-driving car software and gather some experience? Check out these open-source self-driving car simulators!
Details below π
CARLA
CARLA is a great software developed by Intel. You can use it to work on any step of the pipeline, model different sensors, maps, traffic. It also integrates with ROS.
Another great simulator by Voyage - the self-driving company that was recently acuired by Cruise. It is built on the Unreal Engine and supports lots of features.
Useful online courses on self-driving cars π§ π
Here is a list of useful courses if you want to learn about software for self-driving cars.
Some of the courses are paid, but all platforms offer regular discounts and financial aids if you can't affor them.
Thread π
Udacity Self-Driving Car Nanodegree
This program offers hands on experience on all kind of relevant topics like perception, localization, planning and control. It takes a lot of time, but it is worth it.