Self-driving Vehicle or Autonomous Vehicle is a new technology that could provide mobility alternatives to consumers. This post explores information about What is a Self-driving Vehicle (Autonomous Vehicle), it’s architecture, how it works, advantages and disadvantages.
What is Self-Driving Vehicle
Self-driving Vehicle, also known as Autonomous Vehicle is capable of sensing its environment and operating without human involvement. These vehicles are able to guide themselves from an origin point to a destination point desired by the individual.
Fig. 1 – Introduction to Self-driving Vehicle
No human is required to take control of the vehicle at any time, nor required to be present in the vehicle at all. It can go anywhere a traditional vehicle goes and do everything that an experienced human driver does.
It can-steer itself, accelerate itself, go and stop itself. Self Driving is no longer a lab experiment. Many big companies like Mercedes-Benz, General Motors, Continental Automotive Systems, Bosch, Nissan, Toyota, Audi, Volvo, and Google have been working on sensor-based and communication-based Self-Driving Vehicle technologies and its implications.
Fig. 2 – Companies investing in Self-driving Vehicle
Architecture of Self-Driving Vehicle
The architecture consists of components namely:
Allows vehicle to perceive their environment and make sense of it. Perception refers to the ability of the system to gather information about its surroundings like detection of obstacles, location of landmarks, road signs etc. If the current state-of-the-art Perception system is improved then Self-Driving Vehicles will be more reliable, robust and safe.
Localization is one of the prime modules in architecture of self driving vehicles. The car locates itself in the 3D world. Self driving accuracy depends on localization. For localizing the position of the vehicle at any time depends on the Landmarks. Mixed Integer Linear Program (MILP) helps in computing the best path for the Autonomous Vehicle and ensures that at least 2 Landmarks are in the sensor range of the vehicle. It helps the Robot to determine its position with respect to its environment.
This module tries to replicate decision making and thinking power as humans do while driving. The process includes the decisions that the vehicle takes; right from the source point to destination avoiding obstacles, taking optimal path etc.
Control unit executes or implements the planned actions that are generated by higher order processes. It helps the Autonomous Vehicle to be in motion, stop, take deviation etc.
Fig. 3 – Architecture of Self-driving Vehicle
Most vehicles will come with multiple sub components such as:
- Global Positioning System (GPS)
- Light Detection and Ranging (LIDAR)
- Cameras (Video)
- Ultrasonic Sensors
- Central Computer
- Radar Sensors
- Dedicated Short-Range Communications-Based Receiver
GPS in Self-Driven Vehicle
Triangulates position of vehicle using satellites. It allows Self-driving vehicles to navigate without human input.
LIDAR in Self-Driven Vehicle
It is a combination of laser scanning and 3D imaging. Vehicle based on LIDAR systems make use of invisible, eye-safe laser beams. These are emitted from transmitters attached to a vehicle and reflects off light rays from all the objects located within a maximum of 500 meters. Such objects can be either stationary or moving.
Cameras in Self-Driven Vehicle
Cameras used in self-driving cars have the highest resolution of any sensor. The data processed by cameras and computer vision software can help identify edge-case scenarios and detailed information of the car’s surroundings.
Ultrasonic Sensors in Self-Driven Vehicle
They are also called as Parking Sensors. They are good at detecting obstacles within close range. Sound waves of high frequency are generated. They evaluate the target object when the object reflects the signals back and the distance between the target object and Autonomous Vehicle is calculated.
Centralized Processor in Self-Driven Vehicle
For Self-driving software to interface with the hardware components in real-time, processing all sensor data efficiently, it needs a Centralized Processor with the processing power to handle this amount of data.
Radar in Self-Driven Vehicle
Radar (Radio Detection and Ranging) is one of the primary means that self-driving cars utilize to see. Radar is radio wave-based; it can see through things like rain or snow.
DRSC Receiver in Self-Driven Vehicle
It enables vehicle to communicate with another vehicle (V2V). DRSC is a wireless communication standard that enables reliable data transmission in active safety applications. NHTSA (National Highway Traffic Safety Administration) has promoted the use of DSRC.
How does Self-Driving Vehicle Work
Self-driving Vehicle rely on sensors, actuators, complex algorithms, machine learning systems, and powerful processors to execute software. It creates and maintains a map of their surroundings based on a variety of sensors situated in different parts of the vehicle. Radar sensors monitor the position of nearby vehicles.
Fig. 4 – Technology used in Self-driving Vehicle
Video cameras detect traffic lights, read road signs, track other vehicles, and look for pedestrians. Lidar (Light Detection and Ranging) sensors bounce pulses of light off the vehicle’s surroundings to measure distances, detect road edges, and identify lane markings. Autonomous Vehicle, thus chooses the optimal path to reach its destination.
Advantages of Self-Driving Vehicle
The advantages of Self-driving Vehicles include:
- Being able to get things done while in traffic or on the road.
- Fewer traffic collisions.
- Pollution decreases.
- Higher speed limits can be controlled effectively.
- Reduction in traffic police.
- Reduce traffic congestion.
- Removal of limitations on drivers.
Disadvantages of Self-Driving Vehicle
The disadvantages of Self-driving Vehicles include:
- Liability for damage.
- Software reliability.
- Implementation of legal framework and establishment of government regulations for Self-driving vehicle.
- If situations arose requiring manual driving, drivers may be inexperienced.
- Loss of driving-related jobs.
- Expensive technology.
- Hacking problem.
These vehicles seem to be a part of the near future transportation, if they are successfully deployed across roadways and it will be a revolution not just for drivers and traffic patterns but also for the transportation industry.