Please enable JavaScript.
Coggle requires JavaScript to display documents.
AV Perception - Coggle Diagram
AV Perception
FAQ
Accuracy
The error between the true value and its measurement, which may include noise levels and external interference rejection parameters
Resolution
The minimum difference between two measurements (often much lesser that the actual accuracy of the sensor)
Sensitivity
The smallest value that can be detected or measured
Dynamic range
The minimum and maximum values that can be (accurately) detected
Perspective
Quantities such as sensor range or its field of view (FOV)
Active VS Passive
Whether the sensor emits energy or radiation that illuminates the environment or relies on ambient conditions
Timescale
Quantities such as update rate of sensor output and the frequency bandwidth of the measurement output over time
Output or interface technology
How the information is transmitted from the sensor to controller (eg. Analogue voltage or current, digital outputs, serial or network data streams)
Challenges
Poor weather and light conditions
Complex urban environments
Autonomous driving without heavy reliance on pre-existing perception data
Utilisation of connected vehicle technology to improve accuracy, certainty, and reliability of perception
Development of safety measures in case of faulty sensors/perception
AV
Self-sensing
use sensor to measure current state of vehicle, wheel speed (usually measured by hall effect sensor) , vehicle dynamic state, transmission gear and differential state, driver inputs, brake pressure, Engine and exhaust variables
Eg. Hall effect sensor, inertial measurement unit ( measures and reports a body's acceleration, angular rate, and sometimes the orientation of the body, usually using accelerometers (measures linear acceleration), gyroscopes (Measure rotational rate), and sometimes magnetometers ( measures direction, strength or relative charge of a magnetic field. In IMUs, vector magnetometers are used to measure the direction of the magnetic field to determine the vehicle's heading))
Localisation
Uses sensors to determine vehicle's global and local position, uses GLobal navigation satellite system that uses satellites to determine location, the receivers use time signals transmitted along a line of sight by radio from multiple satellites.
Eg. Global positioning system (GPS), Globalnaya Navigatsionnaya Sputnikovaya sistema (GLONASS), Galileo, BeiDou Navigation Satellite system (BDS)
Surrounding sensing
Uses sensor to sense surroundings, road markings, road slopes, traffic signs, weather conditions, the state ( position, velocity, acceleration, etc.) of obstacles including other vehicles, and even the state of the driver.
Eg. camera, Light Detection and Ranging (LiDAR) which measures distances by illuminating the target with laser light and measuring the reflection with a sensor, Radio Detection And Ranging (RADAR) uses radio waves to determine the range, angle, or velocity of objects, Ultrasonic sensor, Image processing sensor,
GNSS
GNSS augmentation
Method of improving a navigation system's attributes, such as accuracy, reliability, and availability, through the integration of external information into the calculation of process
Dead reckoning using IMU
Process of calculating current position by using a previously determined position by using estimations of speed and course over elapsed time.
More accurate positioning especially when GNSS signal is weak
Inertial Measurement Unit (IMU)
IMUs are often integrated into Inertial Navigation Systems (INS) which utilise raw data from the accelerometers, gyroscopes and magnetometer within the IMU to calculate attitude, angular rates, linear velocity and position relative to global reference frame.
A major disadvantage is accumulated error as acceleration is continuously integrated to calculate velocity and position.