Recognition of objects (pedestrian, vehicle) is especially important in the case of autonomous vehicles. We have 3 types of sensors: LIDARs, cameras, radars. During the researches we apply traditional and artificial intelligence-based solutions.
Autonomous Transport Systems Center
Function of the Center
Our main research areas are the development and education issues of the autonomous transport systems and the understanding of the collaboration between people and vehicles. We expect fully automated transportation to be safe and suitable, so we are already preparing for the new technology of future by the researching of the autonomous vehicles. By the developments, we gain unique knowledge of informatics, mechatronics, robotics and artificial intelligence. We are working that the transport of future be uncompromising, safe and sustainable.
Professional leader: Dr. Ernő Horváth
Contact – e-mail address: firstname.lastname@example.org
Operative leader: Péter Kőrös
Contact – e-mail address: email@example.com
The current position of the detected-objects is really important information for the vehicle control algorithms. Aware of this information, the vehicle estimate the position and movement of the pedestrian and the algorithm modify the original trajectory of the vehicle to avoid an accident.
One of our main research directions is free space estimation, or drivable area recognition. The vehicle’s computer filters out free spaces from the data of the sensors. Then, vehicle’s control algorithm forms an image of the potentially drivable area and plots movements in that area.
We develop neural networks (NN) on the field of artificial intelligence (AI). The neural networks are well-applicable for perception and decision-making. Our active research-area is the detection issues of sensor systems.
The area – where the vehicle is moving – is described by an environmental representation. Our main research area is the automatically creation of environmental representation from vehicle sensor-data. The HD map consists of a point-cloud map, traffic lanes and other signs. The point-cloud map contains more information than a simple map.
One of the inputs of HD map is the point-cloud, that we generate from the LIDAR data. The accurate position and orientation are required for simultaneous localization and mapping solutions (SLAM).
Remote control is a typical autonomous vehicle function. This function is traditionally solved by camera, but we are also examining the LIDAR-based solutions.
Our active research area is the issues of the localization. The modern GPS systems have not high accuracy for autonomous vehicle control and these systems are not available in parking houses. These and similar problems are solved by using other sensors (LIDAR, IMU). One of the appropriate direction is the point-cloud-based localization of the vehicle.
The free space or drivable area, detected-objects and accurate localization are given to vehicle control algorithms and these programs design a smoothed, traceable, collision-free and continuous trajectory. Under trajectory we mean the complete route including time and velocity data.
Our research areas is the trajectory tracking considering the kinodynamic constraints of the vehicle. We develop trajectory tracking algorithms and our aim is that the steering movement and braking not be aggressive or unpleasant for passengers.
Our research areas are the traditional V2X-based system and the modern 5G mobile network-based system. The technology is well-illustrated by the scenario, where a vehicle with distinctive sign (police car, ambulance car) sends messages to the infrastucture, that it wants to reach its destination as soon as possible. The vehicle will drive through a green wave as the result of the vehicle-to-infrastructure communication.
Autonomous robots and vehicles can be characterised by a large variety of on-board equipment, sensors, or even purpose. Because of the complexity and diversity of these systems, continuous testing is required. Despite being a complex task, computer simulation creation can largely increase the efficiency of real-life tests by accelerating iterative development.
Our research center shares the acquired-knowledge, algorithms and data, where our work allows it. Since our systems are based on the open-source ROS/ROS2 ecosystem, our algorithms can be developed in Matlab / Simulink, LabVIEW, C++, and Python.
During the provision of our expert services, our specialists make suggestions and give advice on artificial intelligence-based business processes. They rank the optimized-solutions according to different aspects with the help of the unique finite element methodology.
During the provision of our expert services, our specialists develop the reporting systems and the audit of internal business processes. They accomplish automated reporting systems and automated business processes.
During the provision of our expert services, our specialists make predictive business analysis and research the robotized business processes.
During the provision of our expert services, our specialists perform economic situation analysis and provide crisis management guidance services for the concerned companies. They work out steps for the development of the financial-liquidity situations.
During the provision of our expert services, our specialists compile and check the required documentation for the tenders for the potential foreign investors. They give advice on international accounting issues.
During the provision of our expert services, our specialists perform economic situation analysis and they work out steps for the development of the financial-liquidity situations. Our experts make analysis of market-supplier relationships, suppliers, supply chains. They make suggestions to client for the most efficient use of supply chains and management of crisis situation.