Autonomous Ground 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:

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.

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 1). Based on the signals from these targets, it calculates its position and maps a route using a built-in algorithm.

In addition to laser triangulation, other navigation methods are also used, such as:

• Inertial navigation,
• Grid navigation,
• Magnetic navigation,
• Wired navigation,
• Optical navigation.

Examples of vehicles with assisted navigation:

• AGV (Automated Guided Vehicles),
• AGC (Automated Guided Carts),
• LGV (Laser Guided Vehicles).

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 ).

Examples of vehicles with smart navigation:

• AMR (Autonomous Mobile Robot),
• AIV (Autonomous Indoor Vehicle),
• VGV (Vision Guided Vehicle),
• UGV (Unmanned Ground Vehicle),
• SDV (Self-Driving Vehicle),
• SGV (Self-Guided Vehicle).

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.

Ultimately, the development and implementation of autonomous technologies can contribute to, among other things:

• improving road safety,
• increasing road capacity,
• reducing road traffic congestion,
• increasing the speed and reliability of deliveries,
• reducing emissions from the transport sector,
• reducing labor costs,
• increasing the mobility of young, disabled, and infirm people,
• increasing economic innovation,
• increasing the available urban space,
• improving travel comfort,
• increasing the popularity of shared mobility,
• changes in the planning and development of urban areas,
• reducing the cost of motor insurance.

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 idea of autonomous vehicles is enjoying increasing popularity among drivers and passengers of passenger cars. This increased interest can also be observed 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, also focusing more broadly on autonomous vehicles in urban public transport.

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, driving 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 features appeared on 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, attempting to create a fully autonomous car.

Figure ##REF:Ref.Sensory devices## shows the components that make up an autonomous car - sensory devices that monitor and analyze the environment.

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) responsible for braking assistance and distance control.