2 - Technology

# Different types of technology in autonomous vehicle:
Autonomous Vehicles (AVs) use combinations of technologies and sensors to sense the roadway, other vehicles, and objects on and along the roadway.The key technologies and sensors are described in the figure below. 

* A combination of sensors:

Cameras are a relatively inexpensive type of sensor that can provide the basic visual information a human would gather as he or she drive; multiple cameras are used to provide depth of field.

Radar (Radio detection and ranging) already used for certain level 1 vehicle controls; Both short-range and long-range automotive-grade RADARs are used (mostly in the narrow-band i.e. 27–77 GHz) for AD applications. Short-range radars, as the name indicates, ‘senses’ the environment in the vicinity of a car (~30m) and, especially at low speeds; whereas, long-range radars cover relatively long distances (~200m) usually at high speeds. Generally, the radar sensor acquires information from nearby objects like distance, size, and velocity (if it is moving) and warns the driver if an imminent collision is detected. 

Lidar (light detection and ranging) is an onboard laser system that maps a car’s surroundings as it moves. You are probably familiar with LIDAR as the big spinning unit found on the top of most of Google’s test vehicles; solid-state LIDAR does not require spinning and is also being used in some autonomous vehicles now being developed. Although LIDAR creates highly accurate 3D mapping, it does have drawbacks; in addition to being very expensive, the technology is affected by weather, with its signal bouncing off of rain or snow.

Ultrasonic sensor: is a device that can measure the distance to an object by using sound waves. It measures distance by sending out a sound wave at a specific frequency and listening for that sound wave to bounce back. By recording the elapsed time between the sound wave being generated and the sound wave bouncing back, it is possible to calculate the distance between the sonar sensor and the object.

* A combination of localization:

GPS (Global Positioning Systems): Locate the vehicles by using satellites to triangulate its position. Althoug GPS has improved since 2000, it is only accurates within several meters.

INS ( Inertial NAvigaiton Systems): Inertial navigation systems come in all shapes and sizes. The sensors an INS uses are typically gyroscopes to measure rotation and accelerometers to measure velocity—and there are normally several of each inside. We'll look at how an INS actually works in a moment, for now the most important thing to realise is how inertial guidance systems differ from GPS—which you're probably more familiar with.

*Reference sources: 

http://css.snre.umich.edu/factsheets/autonomous-vehicles-factsheet

http://education.rec.ri.cmu.edu/content/electronics/boe/ultrasonic_sensor/1.html
http://www.oxts.com/what-is-inertial-navigation-systems-guide/
https://www.quora.com/What-sensors-do-driverless-cars-have
http://www.thedrive.com/tech/8657/heres-how-the-sensors-in-autonomous-cars-work

# Sensors Greater detail: 

Sensor Technology	Being used	Benefits	Drawbacks	Future        potential
Cameras	Generate images of vehicles’ surroudings, imitating human eyesight. They are also even capable of 3D vision – allowing for range determination. The most advanced camera systems do not only detect obstacles but also identify them and predict their immediate trajectories using advanced algorithms.	Detect color and font – and are therefore able to interpret traffic signs, traffic lights, or lane markings. They can also act as a back-up system should other systems fall – increasing the car’s system security	Weather limitation such as fog, rain, or a low sun currently increase the risk of failures and need to be overcome.	More different sizes, appearance and new functions that help them work in all kinds of weather.
Radar	Known from ship and plane navigation. Radar sensors send out electromagnetic waves. If they hit an obstacles, the waves are reflected, revealing how far away an object is and how fast it is approaching. The radar’s input may even engage advanced steering and braking controls to prevent the crash.	Track the speed of other vehicles in real time. They also contribute to the safety by increasing the redundancy of autonomous vehicles systems	Radar is only good at close range. Current 2D radar are not able to determine an object’s height as they only scan horizontally. This can cause problems, for instance when driving under a bridge.	Radars will provide more accurate information, be smaller, cheaper and more reliable.
Lidar	Scan the environment with a non-visible laser beam. The low intensity, non-harmful beam visualizes objects and measures ranges-creating a 3D image of the car’s environment.	Combined with the data of camera sensors, Lidar sensors allow obstacles to be accurately identified – for instance whether it is a vehicle or a pedestrian that is in front of the car.	Lidar sensors are currently much more expensive than radar sensors.	In future, with solid-state technology coming in, the cost will come down drastically making LiDARs indispensable for any AV.
Ultrasonic sensor	Imitating the navigation process of bats, ultrsonic sensors send out waves. When the waves hit an object the produce echoes – revealing the exact location of the obstacle.	Detect obstacles in the immediate vicinity – be it cars, pedestrians or bollards. They play an important role for automated parking.	Ultrasonic sensors can only be used at very low speeds.	They serve their intended purpose and there is currently no further development needed