AUTONOMOUS VEHICLES

An autonomous vehicle is capable of sensing its environment and navigating to its destination without human input. Autonomous vehicles are often called driverless, self-driving or robotic vehicles.

To achieve this feat of navigating autonomously, autonomous vehicles rely on the use of various kind of sensors well placed on the vehicle to detect and continuously observe location and the movement of other vehicles, people and traffic lights.

The sensors usually used are radar sensors in the front of the vehicle to monitor the position of other vehicles nearly, video cameras to detect traffic lights, read road signs, keep track of the position of other vehicles and look out for pedestrians and obstacles on the road, Lidar (light detection and ranging) sensors bounce pulses of light off the surroundings and thereby use the data  obtained to analyze and verify lane markings and the edges of roads , ultrasonic sensors are used to measure the position of objects very close to the vehicle such as curbs and other vehicles when parking and signals from GPS (global positioning system) satellites are combined with readings from tachometers, altimeters and gyroscopes to provide more accurate positioning than is possible with GPS alone. The information from all of the sensors is analyzed by a central computer that manipulates the steering, accelerator and brakes. The autonomous vehicle software must be programmed to understand the prevailing road rules and also be able to reflect immediately changes to these rules when necessary. Thus autonomous vehicles, combine sensors and map data and based on machine learning or experience can classify objects in their surroundings and predict how they are likely to behave, in relation to other moving vehicles, pedestrians, cyclist and stationary objects (e.g. signs, trees, traffic cones etc.). Based on what an autonomous vehicle can see and what it predicts nearby objects are likely to do; it can make decision about speed and steering inputs.

There are two types of autonomous technology system in use today; they are the Lidar system and the non Lidar system. Lidar is an active remote sensing system and an active system is a system that produces energy or light to quantify things on the ground. Light is emitted from a quick firing laser, this light goes to the ground and the light bounces off obstacles like trees or buildings, the bounced light then goes back to the Lidar sensor and then records it. Lidar sensors can achieve mapping precision of up to 1cm horizontally (x,y) and 2cm vertically and a range accuracy of 0.5 to 10mm relative to the sensor. As a result, they serve as particularly advantageous remote sensing equipment for mobile mapping. Lidar sensors may capture several returns from a single light pulse. This may be due to the fact that as light pulses travels from the sensor they may come in contact with many objects that will reflect the pulses such as leaves and branches of a tree canopy. Lidar sensors can record the data to produce a detail picture of both the tree canopy and the underlying structure.

The non-Lidar system relies heavily on onboard cameras. This method can detect vehicles and pedestrians on the road as well as some objects such as trees, but it cannot always discern the real shape or depth of the obstacles it encounters. To compensate for this, a minimum of eight cameras are connected to the vehicle to gather information so it can steer through the freeways, city streets and traffic. This is made possible by enhancing the software of the vehicle to compensate for it hardware deficiencies. This will create a virtual Lidar using eight cameras connected to its neural network.

Once the autonomous vehicle has scanned its environment, it can find its location on the road relative to other objects around it. This information is critical for lower level path planning to avoid any collisions with objects in the vehicles immediate vicinity. On top of that, in cases the user communicates the place they will like to go to in terms of geographic location, which translates to latitude and longitude. Hence in addition to knowing its relative position in the local environment, the vehicle needs to know its global position on earth in order to be able to determine a path towards the user’s destination. The default geolocalisation method is satellite navigation, which provides a general reference frame for where the vehicle is located on the planet. Different global navigation satellite system (GNSS) such as the American GPS , the Russian GLONASS, the European GALILEO or the Chinese BEIDOU can provide positioning information with horizontal and vertical resolution of a few meters.

Depending on the different sensors used onboard the vehicle, different software schemes can be used to extract useful information from the sensor signals. This software is built from algorithms that can be used to do a variety of things. These may be algorithm for 3d mapping, edge detection, motion detection, and motion tracking. Autonomous vehicles will also be connected to other vehicles and infrastructure by sending basic safety messages (BSM) transmitted 10 times per second. Also, other nearby vehicles and roadside equipment receive the message as well as drivers receive warnings and information to avoid potential crashes thereby improving mobility.

 

 

Sources.

• Smruti R. Sarangi.(2024). Basic computer architecture version 2.3. creative commons attribution.org.
• Welvover(2020). Autonomous vehicle technology report. Sponsored by nexperia.
• Self driving cars explained (2017). ucsusa.org/resourcres/self driving cars 101.
• gov: gps Accuracy.in:Gps.gov (5 dec 2017). www.gps.gov/system/gps/performace/accuracy/.
• Sezgin Ensoy, Tayyab Wagar.ed (2020). Autonomous vehicle and smart traffic. Intech open, London, united kingdom.
• Benjamin Quito,Larbi Esmahi (2023). Compare and contrast Lidar and non-Lidar technology in an Autonomous Vehicle: Developing a safety framework. Open journal of safety science and technology.
• Rasheed Hussain, Sherati Zeadally (2019). Autonomous cars: Research results, issues and future challenges. IEEE communication surveys and Tutorial.