Differences

This shows you the differences between two versions of the page.

--- en:safeav:softsys:autonomousgroundvehicles [2025/10/22 13:47] – rczyba
+++ en:safeav:softsys:autonomousgroundvehicles [2026/03/30 13:44] (current) – pczekalski
@@ Line 3: / Line 3: @@
 ===== UGV and AGV Vehicles =====
-Use of autonomous ground vehicles (AGVs) and unmanned ground vehicles (UGVs) is rapidly growing as multiple industries race to replace repetitive, labor intensive, and dangerous tasks, improving efficiency, productivity, and safety. While the terms AGV and UGV are often used interchangeably, there are a few differences. One key difference is that AGVs are used within buildings, such as in warehouses while UGVs are primarily used outdoors. Other key differentiators are:
+The use of autonomous ground vehicles (AGVs) and unmanned ground vehicles (UGVs) is rapidly growing as multiple industries race to replace repetitive, labour-intensive, and dangerous tasks, thereby improving efficiency, productivity, and safety. While the terms AGV and UGV are often used interchangeably, there are a few differences between them. One key difference is that AGVs operate within buildings, such as warehouses, whereas UGVs primarily operate outdoors. Other key differentiators are (table {{ref>UGVtab1}}):
-<table tab_label>
+<table UGVtab1>
+<caption>UGV sifferentiation criteria</caption>
 ^ AGVs ^ UGVs ^
 | * Operate indoors  | * Operate outdoors  |
@@ Line 14: / Line 15: @@
 </table>
-Autonomous mobile vehicles, such as AGVs (Automated Guided Vehicles) and AMRs (Autonomous Mobile Robots), are widely used in warehouses and manufacturing plants. Their primary goal is to increase safety, efficiency, and productivity by automating the transport of materials or products. They can reduce the risk of accidents and lower operating costs. Furthermore, the use of smaller automated vehicles allows for maximum warehouse space compared to larger, manually operated vehicles. Autonomous vehicles are divided into two types: assisted navigation vehicles and smart navigation vehicles.
-=== Assisted Navigation ===
+Autonomous mobile vehicles, such as AGVs (Automated Guided Vehicles) and AMRs (Autonomous Mobile Robots), are widely used in warehouses and manufacturing plants. Their primary goal is to increase safety, efficiency, and productivity by automating the transport of materials or products. They can reduce the risk of accidents and lower operating costs. Furthermore, the use of smaller automated vehicles allows for greater warehouse space utilisation than larger, manually operated vehicles. Autonomous vehicles are divided into two types: assisted-navigation vehicles and smart-navigation vehicles.
+** Assisted Navigation **\\
 AGVs, or Automated Guided Vehicles, are vehicles controlled by "tags" detected by special sensors. The most common navigation method is laser triangulation. The laser sensor in the AGV scans reflective targets placed at specific locations within the facility (see Figure {{ref>Ref.AGV}}). Based on the signals from these targets, it calculates its position and maps a route using a built-in algorithm.
@@ Line 37: / Line 39: @@
   * LGV (Laser Guided Vehicles).
-=== Smart Navigation ===
+** Smart Navigation **\\
-AMRs are a more advanced version of AGVs. These vehicles do not require markers or reflective targets for navigation. They are equipped with advanced cameras, sensors, and algorithms supporting 2D or 3D mapping, enabling them to make autonomous decisions. AMRs use lidar (a laser sensor) to measure and map distances between objects and vehicles. This allows them to map complex environments and continuously track their position on the map. These systems allow AMRs to avoid obstacles and adapt their route in real time (see Figure ).
+AMRs are a more advanced version of AGVs. These vehicles do not require markers or reflective targets for navigation. They are equipped with advanced cameras, sensors, and algorithms supporting 2D or 3D mapping, enabling them to make autonomous decisions. AMRs use lidar (a laser sensor) to measure and map distances between objects and vehicles. This allows them to map complex environments and continuously track their position on the map. These systems allow AMRs to avoid obstacles and adapt their routes in real time (see Figure).
 <figure Ref.AMR>
@@ Line 58: / Line 60: @@
 ===== Autonomous cars =====
-Autonomous cars rely on sensors, actuators, complex algorithms, machine learning systems, and powerful processors to execute software. Autonomous cars create and maintain 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. 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 car’s surroundings to measure distances, detect road edges, and identify lane markings. Ultrasonic sensors in the wheels detect curbs and other vehicles when parking. Sophisticated software then processes all this sensory input, plots a path, and sends instructions to the car’s actuators, which control acceleration, braking, and steering. Hard-coded rules, obstacle avoidance algorithms, predictive modeling, and object recognition help the software follow traffic rules and navigate obstacles.
+Autonomous cars rely on sensors, actuators, complex algorithms, machine learning systems, and powerful processors to execute software. Autonomous cars create and maintain a map of their surroundings using a variety of sensors located throughout the vehicle. Radar sensors monitor the position of nearby vehicles. 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 car’s surroundings to measure distances, detect road edges, and identify lane markings. Ultrasonic sensors in the wheels detect curbs and other vehicles when parking. Sophisticated software then processes all this sensory input, plots a path, and sends instructions to the car’s actuators, which control acceleration, braking, and steering. Hard-coded rules, obstacle avoidance algorithms, predictive modelling, and object recognition help the software follow traffic rules and navigate obstacles.
 Ultimately, the development and implementation of autonomous technologies can contribute to, among other things:
@@ Line 66: / Line 68: @@
   * increasing the speed and reliability of deliveries,
   * reducing emissions from the transport sector,
-  * reducing labor costs,
+  * reducing labour costs,
   * increasing the mobility of young, disabled, and infirm people,
   * increasing economic innovation,
@@ Line 83: / Line 85: @@
 ===== Autonomous Vehicles Market =====
-The autonomous vehicles (AV) market is set for exponential growth in 2025, driven by advancements in artificial intelligence (AI) and increased public and private investment. However, significant challenges remain concerning safety, regulation, and high development costs. According to Precedence Research, the global autonomous vehicle (AV) market is valued at approximately USD 273.75 billion in 2025 and is forecast to grow significantly, potentially reaching over USD 4,450.34 billion by 2034, with a compound annual growth rate (CAGR) around 36.3%. Key market drivers include a focus on safety, advancements in AI and sensors, government support through policies and pilot programs, and commercial demand from sectors like freight and ride-sharing. The market is expected to see continued growth in lower autonomy levels like Level 2, while higher autonomy levels (3, 4, and 5) are experiencing rapid expansion, particularly driven by commercial applications.
+The autonomous vehicles (AV) market is set for exponential growth in 2025, driven by advancements in artificial intelligence (AI) and increased public and private investment. However, significant challenges remain concerning safety, regulation, and high development costs. According to Precedence Research, the global autonomous vehicle (AV) market is valued at approximately USD 273.75 billion in 2025 and is forecast to grow significantly, potentially reaching over USD 4,450.34 billion by 2034, with a compound annual growth rate (CAGR) of around 36.3%. Key market drivers include a focus on safety, advancements in AI and sensors, government support through policies and pilot programs, and commercial demand from sectors like freight and ride-sharing. The market is expected to continue growing in lower-autonomy levels like Level 2, while higher-autonomy levels (3, 4, and 5) are experiencing rapid expansion, particularly driven by commercial applications.
 <figure Ref.Autonomous Vehicles Market>
@@ Line 89: / Line 91: @@
 <caption>Autonomous Vehicles Market ((https://www.precedenceresearch.com/autonomous-vehicle-market))</caption>
 </figure>
+===== Autonomous vehicles in urban public transport =====
+The idea of autonomous vehicles is enjoying increasing popularity among drivers and passengers of passenger cars. This increased interest is also evident in public transport. The need to move people and goods has accompanied humanity practically since its inception. Until now, however, there was a common element in every transportation plan – transport could not occur without the intervention of a human driver. This applied to all forms of transport: water, land, and air, as well as functions such as freight transport, cargo handling, vehicle and infrastructure maintenance, and responsibility for the provision of transport-related services. The emergence of autonomous vehicles on the market has presented a revolutionary approach in this context. Depending on the level of autonomy, the role of humans as supervisors overseeing the efficiency and safety of the journey has been significantly reduced or completely eliminated. In the dozen or so years since the first reports of autonomous vehicle testing, enormous progress has been made in this field, with a broader focus on autonomous vehicles in urban public transport.
+===== Progress in vehicle autonomy =====
+The 2000s significantly accelerated the development of autonomous vehicles. The US government funded research into ground vehicles for military purposes, intended to facilitate navigation on poor roads and avoid obstacles. In 2009, Google launched its own project exploring the capabilities of autonomous vehicles. In 2011, General Motors unveiled an electric car concept called the Electric Networked Vehicle (EN-V). A year later, in 2012, Volkswagen created a semi-automatic car pilot called TAP (Temporary Auto Pilot). TAP allowed for driving at speeds of up to 130 km/h. However, the driving system was designed in semi-automatic mode, as the project's goal was not to create a fully autonomous vehicle but rather a driver-assistance system to prevent car accidents, the main causes of which were driver fatigue and distraction. In 2014, a Mercedes car with a set of autonomous driving features was introduced to the market. It was tested in both city and highway driving at a maximum speed of 200 km/h. Meanwhile, key automotive companies, including Audi, General Motors, and Volkswagen, continued or launched similar research projects of their own, aiming to develop fully autonomous cars.
+===== Characteristics of autonomous vehicles in road transport =====
+Figure {{ref>Ref.Sensory_devices}} shows the components that make up an autonomous car - sensory devices that monitor and analyse the environment.
+<figure Ref.Sensory_devices>
+{{ :en:safeav:softsys:autonomous-levels-infographic-v2-720.png?600 |}}
+<caption>Sensory devices of an autonomous car ((https://www.aptiv.com/en/insights/article/what-are-the-levels-of-automated-driving))</caption>
+</figure>
+** Radars**\\
+The purpose of the radars is to continuously emit radio waves that help the system detect objects and obstacles. Depending on the designed target range of the transmitted waves, the following supporting functionality can be distinguished: short-range radar applications (24 GHz), which support blind-spot monitoring, lane-keeping, and parking; and long-range radar sensors (77 GHz), which support braking assistance and distance control.
+** Cameras **
+Cameras are responsible for recording the vehicle's surroundings and interpreting objects and obstacles. They are designed to function similarly to the human eye. Modern technology allows for a full 360-degree field of view, provided the monitoring devices are properly deployed. Cameras with a long operating range (100 meters or more) can recognise road signs, calculate distances to distant objects, classify objects, estimate the speed of moving objects, and monitor roadsides. However, the drawback of these solutions is their variable reliability, as weather conditions can affect the system's interpretation.
+** Lidars **
+The final component described is a technology known as lidar (Light Detection and Ranging). Lidar enables the recording and processing of information about the positions of objects using laser light. The laser emits a beam of light (continuous or in the form of intermittent pulses), which is dispersed and then detected by the receiver's photosensitive elements. The processor analyses the intensity of the reflected beam and its recording time, determining the object's position in space and the distance between the vehicle and the object. As with cameras, the appropriate arrangement of monitoring devices allows for a full range of observation (a 360-degree field of view). Lidar is the most expensive and reliable technology used in autonomous vehicles. This technology also holds the greatest promise for creating fully autonomous vehicles that require no human supervision.
+** Advantages of autonomous vehicles **
+Autonomous vehicles in urban public transport can have a positive impact on the environment. Using the increasingly popular driving technique known as eco-driving (smoother driving that puts less strain on the engine) can reduce vehicle emissions and save fuel.
+The idea of autonomous vehicles is fostering the widespread use of shared vehicles and/or shared travel costs, also known as car sharing.
+Another key advantage is ensuring a higher level of road safety. Computer-controlled driving would significantly reduce risky behaviour (such as reckless driving or recklessness) on the road, and consequently, the number of people injured would be significantly reduced.
+Urban public transport is intended to facilitate travel for everyone, but a significant portion of society uses it are the elderly and people with disabilities. Using autonomous public transport not only increases the mobility of people with disabilities but also reduces social isolation and potential psychological distress.
+The widespread adoption of autonomous driving, including among passenger car drivers, will contribute to a significant reduction in congestion on public transport routes. The ability to constantly monitor the surroundings and other vehicles, as well as to adapt appropriately to traffic conditions, contributes to improving the situation.
+Given changing purchasing patterns, a growing number of courier and food delivery companies are interested in autonomous vehicles.
+** Disadvantages of autonomous vehicles **
+An ethical issue – as studies have shown, users are more willing to forgive the error of a human driver than an autonomous vehicle.
+Another drawback may be the legislative process designed to adapt legislation to the requirements and realities of autonomous transport. Current regulations stipulate that every vehicle operating independently on the road must have a driver present and that the driver must maintain constant control of the vehicle. In the future, this provision would need to be amended to accommodate autonomous driving. A proper transfer of responsibility for potential road accidents would also be necessary. In cases where the vehicle is fully controlled by a computer, identifying the perpetrator becomes problematic. Legislators would be forced to determine who bears ultimate responsibility for any system errors.
+An organisational drawback is the need to thoroughly scan the areas where autonomous road traffic is to be introduced. Detailed maps must be created based on the scanned areas, which will be processed by localisation systems based on the previously mentioned systems, such as Lidar, cameras, and radars. Such an undertaking involves enormous costs and liability.

en/safeav/softsys/autonomousgroundvehicles.1761130054.txt.gz · Last modified: 2025/10/22 13:47 by rczyba