Raivo Sell

Verified

Raivo verified their affiliation via an institutional email.

Learn more

Verified

Raivo verified their affiliation via an institutional email.

Learn more

• Ph.D
• Professor at Tallinn University of Technology

This book and its offshoots were prepared to provide comprehensive information about the Internet of Things on the engineering level. Its goal is to introduce IoT to bachelor students, master students, technology enthusiasts and engineers willing to extend their current knowledge with the latest hardware and software achievements in the scope of th...

This paper presents Camera-LiDAR Fusion Transformer (CLFT) models for traffic object segmentation, which leverage the fusion of camera and LiDAR data using vision transformers. Building on the methodology of visual transformers that exploit the self-attention mechanism, we extend segmentation capabilities with additional classification options to a...

This paper presents VREL NextGen, an international Internet of Things (IoT) education platform developed through European university collaboration. The platform addresses hands-on IoT education needs in the Industry 5.0 context through three distinct implementations: a microcontroller laboratory at the Silesian University of Technology, a building...

Highlights What are the main findings? A general mathematical methodology and calculation model have been proposed, which allow taking into account most of the important factors that determine the impact of the introduction of first-mile autonomous vehicles on the daily time use of suburban residents. Following the compact modelling approach, an ea...

Critical research about camera-and-LiDAR-based semantic object segmentation for autonomous driving significantly benefited from the recent development of deep learning. Specifically, the vision transformer is the novel ground-breaker that successfully brought the multi-head-attention mechanism to computer vision applications. Therefore, we propose...

Autonomous driving vehicles rely on sensors for the robust perception of their surroundings. Such vehicles are equipped with multiple perceptive sensors with a high level of redundancy to ensure safety and reliability in any driving condition. However, multi-sensor, such as camera, LiDAR, and radar systems raise requirements related to sensor calib...

Agricultural productivity depends primarily on energy, water, and land resources, which are increasingly becoming more scarce and expensive. Electricity generation with photovoltaic (PV) solar energy technology requires significant amounts of space, especially in densely populated countries, generating a societal debate about allocating land (that...

Autonomous driving vehicles rely on sensors for the robust perception of surroundings. Such vehicles are equipped with multiple perceptive sensors with a high level of redundancy to ensure safety and reliability in any driving condition. However, multi-sensor, such as camera, LiDAR and radar, systems bring up the requirements related to sensor cali...

Current academic courses are the subject of widely accepted conversion from classical paper and book-based teaching towards multimedia presentation. The young generation no longer demands classical study but, instead, a mixed model where they can choose to study online and on-site, moreover willing to change it day to day and week to week to fit th...

Validation and Verification (V&V) of Artificial Intelligence (AI) based cyber physical systems such as Autonomous Vehicles (AVs) is currently a vexing and unsolved problem. AVs integrate subsystems in areas such as detection, sensor fusion, localization, perception, and path planning. Each of these subsystems contains significant AI content integra...

To embrace safety while bringing autonomous vehicles (AVs) to public roads, AV manufacturers need to validate and verify the functionality and reliability of the control software. Real-road testing is time-consuming, tedious, costly, and unsafe for validation. Hence, simulation testing has been playing an important role in the market as a viable so...

The article presents a monocular visual localization system based on fiducial markers for autonomous docking in industrial applications. The design has been tailored for direct use with the docking of a mobile logistic robot under storage racks that requires high robustness, usable accuracy, and easy maintenance at a very low cost. The elaborated s...

Autonomous vehicles are a growing technology that aims to enhance safety, accessibility, efficiency, and convenience through autonomous maneuvers ranging from lane change to overtaking. Overtaking is one of the most challenging maneuvers for autonomous vehicles, and current techniques for autonomous overtaking are limited to simple situations. This...

Environmental awareness and technological advancements for self-driving cars are close to making autonomous vehicles (AV) a reality in everyday scenarios and a part of smart cities’ transportation systems. The perception of safety and trust towards AVs of passengers and other agents in the urban scenario, being pedestrians, cyclists, scooter driver...

Automated vehicle (AV) minibuses, i.e., AV shuttles, are gaining popularity in the testing of new types of transportation services in real traffic conditions. AV shuttles have moved from closed test areas to low-traffic public sites such as local residential areas, technology parks, university campuses, etc. These types of vehicles are usually low-...

Object segmentation is still considered a challenging problem in autonomous driving, particularly in consideration of real-world conditions. Following this line of research, this paper approaches the problem of object segmentation using LiDAR–camera fusion and semi-supervised learning implemented in a fully convolutional neural network. Our method...

This paper proposes a reliable optimized sigmoid-based path planning algorithm that ensures smooth, fast and safe overtaking maneuver, while maintaining the necessary safety distance. In the proposed method, the desired smoothness of trajectories, the changes in steering angle and the lateral acceleration are controlled in a robust way. This paper...

Autonomous vehicles (AVs) are moving from test areas to the streets, which is one of the key components of smart cities and the future of mobility as a service (MaaS). In 2020, two AV services were operated in Tallinn. This paper focuses on one of these services, and its set-up process. The pilot project took place in Ülemiste City, a tech park wit...

The autonomous vehicle (AV) industry aims to design strategic plans to ensure the safety of the developed systems before their mass deployment. Real-road testing is shown to be impractical for validating these systems as it requires many years if not decades of testing in different environmental conditions. For solving this issue, the method should...

Self-driving vehicles and mobile robots are used more and more in public transportation and industrial companies. Multiple experimental platforms, which can be operated in an urban or industrial environment, have been developed recently. The key development for robust and safe control of the robots operation relies on the low-level cyber-physical s...

Self-driving vehicles and mobile robots are used more and more in public transportation and industrial companies. Multiple experimental platforms, which can be operated in an urban or industrial environment, have been developed recently. The key development for robust and safe control of the robot’s operation relies on the low-level cyber-physical...

In this work, we investigated two issues: (1) How the fusion of lidar and camera data can improve semantic segmentation performance compared with the individual sensor modalities in a supervised learning context; and (2) How fusion can also be leveraged for semi-supervised learning in order to further improve performance and to adapt to new domains...

Autonomous driving is becoming increasingly popular worldwide. Currently, there is a high number of successful use cases and pilot projects around the world, but the market solutions are limited to restricted areas and advanced driving assistance systems. The main reason is the challenging shift from simulation and test tracks to the real world, wh...

Autonomous vehicles (AVs) are entering from test areas to the streets, which is one of the key components of smart cities and the future of mobility as a service (Maas). In 2020, two AV services were operated in Tallinn. This paper focuses on one of the services, including how it was set up. The route was set up in Ülemiste City, a tech park with 1...

The Autonomous Vehicle (AV) industry aims to design strategic plans to ensure the safety of the developed systems before their mass deployment. Real-road testing is shown to be impractical for validating these systems as it requires many years if not decades of testing in different environmental conditions. Therefore, this method must be complement...

The rapid development of intelligent control techniques has brought changes to the automotive industry and led to the development of autonomous or self-driving vehicles. This paper presents self-driving autonomous vehicle (AV) shuttles in the smart city context and discusses different aspects necessary to consider when deploying AV shuttles. The sm...

This book and its offshoots were prepared to provide a comprehensive introduction into the domain of the autonomous system. The primary target audience is vocational schools and higher educational institutions running study programmes or modules on autonomy and autonomous systems. This book is also designated for teachers and educators willing to e...

This report examines the current interaction points between humans and autonomous systems, with a particular focus on advanced driver assistance systems (ADAS), the requirements for human-machine interfaces as imposed by human perception, and finally, the progress being made to close the gap. Autonomous technology has the potential to benefit perso...

One of the primary verification criteria of the autonomous vehicle is safe interaction with other road users. Based on studies, real-road testing is not practical for safety validation due to its time and cost consuming. Therefore, simulating miles driven is the only feasible way to overcome this limitation. The primary goal of the related research...

In this innovative practice full paper we present the implementation of the distant laboratory for the Internet of Things teaching and training. The recent outbreak of the SARS-COV-2 virus and related COVID-19 pandemic throughout the world has caused governments across the world to shut down schools and universities, to slow down the spread of the...

A compact empirical model for approximate description of green vegetation reflectance (GVR) spectra in the visible and near infrared wavelength range from 400 to 900 nm is proposed. The aim is to simplify the development of cyber-physical systems for forestry, agriculture, military, and environmental monitoring where distinguishing of artificial ob...

Autonomous driving is no longer just an idea of technology vision instead a real technical trend all over the world. The continuing development to a further level of autonomy requires more on mobile robots safety while bringing more challenges to human-vehicle interaction. A robot autonomous vehicle (AV) as a research platform operates an experimen...

The autonomous vehicles need to be validated with a reliable and repeatable methodology to be accepted by the public. In this paper, we present our methodology to develop a validation regime for the decision making system of an autonomous vehicle operating in a certain road network. The methodology starts with the thorough analysis of the selected...

The paper introduces an educational and research project ISEAUTO, targeted to using self-driving cars to solve urban mobility issues. The project focusses on the design and development of an autonomous shuttle as a collaboration between academic staff of the university, students, and a partner company. The paper presents an account of the experienc...

The current business model of the automotive industry is based on individual car ownership, yet new ridesharing companies such as Uber and Lyft are well capitalized to invest in large, commercially operated, on-demand mobility service vehicle fleets. Car manufacturers like Tesla want to incorporate personal car owners into part-time fleet operation...

The current trend of automation and manufacturing is digitalization called Industry 4.0. The digitalization is not only the manufacturing process upgrade but also logistics and intelligent transport solutions. Rapid development of intelligent control techniques has also brought changes in automotive industry and led to developments of autonomous ve...

The paper is focusing on the research of current technologies of multi-purpose mobile robots, including implementation of modular layout, open software frameworks, self-organization with plug and play (PnP) capability and adaptive sensor fusion. The hardware layout is studied in detail and modular architecture is proposed as an optimal solution of...

The paper introduces ISEAUTO project, the first self-driving vehicle in Estonia that is implemented at Tallinn University of Technology (TalTech) in cooperation with Estonian automotive company AuVeTech and ABB. ISEAUTO is a research and educational project, targeted to design and develop self-driving vehicles. The result of the cooperation and joi...

This book and its offshoots were prepared to provide comprehensive information about the Internet of Things. Its goal is to introduce IoT to the bachelor students, master students, technology enthusiasts and engineers that are willing to extend their current knowledge. This book is also designated for teachers and educators willing to extend their...

A laboratory guide for VREL projects

Automated driving system (ADS) technology and ADS-enabled/operated vehicles - commonly referred to as automated vehicles and autonomous vehicles (AVs) - have the potential to impact the world as significantly as the internal combustion engine. Successful ADS technologies could fundamentally transform the automotive industry, civil planning, the ene...

Paper studies the modeling and control approaches of a tactical unmanned aerial vehicle (TUAV) as a coaxial unmanned helicopter with ducted fan configuration via implementation of three-rate control and neural network techniques to achieve more stabilized flight height control. The single-rate and three-rate control strategies for selected type of...

The paper investigates energy efficiency validation of unmanned ground vehicles (UGVs). The energy efficiency of the vehicle platform depends on the design elements and the environment as well as navigation algorithms. Verification of all UGV design factors that have measurable influence on energy efficiency involves an integrated measurement syste...

Studies on self-driving cars are growing popularity nowadays. It is a multidisciplinary topic, which includes artificial intelligence, communication systems, control algorithms, electrical and mechanical applications, etc. A lot of effort is put on the objects recognition and artificial intelligence learning topics, however, the propulsion motor dr...

Building a self-driving car is an undertaking that requires multidisciplinary collaboration from mechanical and electrical engineering, mechatronics, electronics, computer systems and software engineers. ISEAUTO [1] is a first Estonian self-driving car developed in cooperation between Tallinn University of Technology (TalTech) and Silberauto AS. IS...

The rapid development of intelligent control technology has also brought about changes in the automotive industry and led to development of autonomous or self-driving vehicles. To overcome traffic and environment issues, self-driving cars use a number of sensors for vision as well as a navigation system and actuators to control mechanical systems a...

The paper introduces a research and educational project targeted to self-driving cars and urban mobility issues. The project focuses on design and development of the self-driving car in cooperation with a partner company, university researchers, and students. Research and implementation results of simulations, software development and mechanical de...

The model of Assessment of Academic Staff Work Performance and Feedback has been designed at Tallinn University of Technology (TTU). The model links the main stages of the assessment process from collecting data for compiling a personal portfolio and analyzing personal training needs, to conducting the development and career interview and finalizin...

This paper presents a novel approach to traction effort calculation for a self-driving car. Self-driving cars usually require reliable and accurate path planning algorithms to operate in dynamically changing environment. The first self-driving car project in Estonia started with the cooperation of Tallinn University of Technology and Estonian compa...

Raamat annab lihtsa ja kiire ülevaate Arduino platvormist ja selle esmastest kasutusvõimalustest. Raamat on jagatud kolmeks loogiliseks osaks: tarkvarakeskkond, riistvaraplatvorm ja praktilised projektid. Suur rõhk on pandud näiteprojektidele, mis käsitlevad erinevate sisend-väljund seadmete ühendamist ja juhtimist.

RESEARCH REPORT ON GOOD PRACTICES Robotics as blended learning approach for training A " good practice " can be defined as follows: A good practice is not only a practice that is good, but a practice that has been proven to work well and produce good results, and is therefore recommended as a model. It is a successful experience, which has been tes...

This paper describes test case of an energy efficiency validation method. Test case is selected as surveillance mission which is simple and common case for universal unmanned ground vehicle where environment dynamics has major influence. The prototype UGV platform is equipped with combined measurement system providing data about dynamic parameters...

This paper presents an innovative framework concept combined with online labs for teaching and learning of engineering subjects. The concept integrates comprehensive approaches of different classical and innovative aspects. The paper gives an overview of current state-of-art technologies in remote and virtual labs and some existing activities for t...

This paper presents one of the successful co-operation activities during last 10 years which is initiated by conference series REM - Research and Education in Mechatronics. Projects are dealing mostly about innovative educational tools and learning materials in mechatronics. Several innovative solutions like Distance- and VirtualLab are created as...

This paper presents an innovative framework concept combined with online labs for teaching and learning of engineering subjects. The concept integrates comprehensive approaches of different classical and innovative aspects. The paper gives an overview of current state-of-art technologies in remote and virtual labs and some existing activities for t...

This paper describes energy efficiency validation during unmanned ground vehicle and environment dynamic interaction testing. The compound measurement system provides data about dynamic parameters. Platform energy efficiency is evaluated on several stages, enabling to evaluate both mechanical design and control system algorithms. In addition, envir...

The paper investigates the data acquisition method and a system of wheeled mobile unmanned ground vehicles (UGV) for characterization and optimization of motion and energy efficiency. This enables to conduct real-time and conditional field tests. The obtained results are used for an advanced methodology framework for robotic design targeted on the...

Raamat on mõeldud abivahendiks nii koolidele kui ka teistele hobirobootikaga tegelejatele, rõhudes just praktilisele küljele. Raamatu näidete baasiks ATxmega128 mikrokontroller koos Robootika Kodulabori riistvara moodulite ja tarkvarateegiga. Lisaks praktilistele näidetele sisaldab raamat AVR mikrokontrolleri arhitektuuri ülevaadet ja tüüpiliste pe...

There is high demand for qualified Information and Communication Technology (ICT) practitioners in the European labor market. In Estonia, the problem is not a low number of ICT students but a high dropout rate. The aim of this study is to find how it is possible to predict first-year dropout in higher education ICT studies and possibly to engage me...

Dropout in ICT studies is a big problem all over the world. This paper gives an overview of research in Estonian ICT student dropout and shows that progress in mathematics and programming courses is important in preventing dropout. Online tools could be used for making these kinds of courses more attractive and effective for students. Possibilities...

In the present paper the interactive demonstration of remote laboratories conducted with engineering didactics for creating real conditions for teaching and learning engineering has been presented. The article is focusing on international cooperation, offering the wide range of tools and methodology for effective and interactive teaching of embedde...

The paper investigates the data acquisition method and a system of wheeled mobile unmanned ground vehicles (UGV) for characterization and optimization of motion and energy efficiency. This enables to conduct real-time and conditional field tests. The obtained results are used for an advanced methodology framework for robotic design targeted on the...

Inductive principles in Engineering Pedagogy have been presented in the present paper on the example of remote labs. Inductive teaching is one way to help students learn to use the fundamental concepts for problem solving – focusing on cases that students could work on to help develop an understanding of the phenomenon. For effective inductive teac...

In this paper a SysML navigation models and early design methodology is briefly introduced. The methodology is offering tool and pre-defined models for mobile robot design in early design stage. The main target is reaching the optimal and efficient conceptual solution for detail design stage by using the pre-defined and validated SysML models accor...

To stay competitive in the global market the enterprises must find possibilities to make production more efficient. Taking into consideration the production process what is energy consuming it is also essential to look at the energy consumption in enterprise. European Union has started an initiative FoF (Factories of The Future), where main purpose...

This article reviews and analyses the educational research literature on interventions to increase the recruitment and retention of information and communications technology (ICT) students. The results show that three changes in computing pedagogy characterize successful interventions, and consequently offer promising ways to attract and prepare mo...

In this paper the interactive demonstration of remote laboratories conducted with engineering didactics for creating real conditions for teaching and learning engineering has been presented. The article is focusing on international cooperation, offering the wide range of tools and methodology for effective and interactive teaching of embedded syste...

Engineering education process is heavily relying on the practical hands-on experimentation. However, today’s education is involving more and more e-learning aspects and learners expect to get most of the content and activity available over the Internet. Practical experiments is not trivial to carry out over the Internet, but using novel ICT technol...

Inductive principles in Engineering Pedagogy have been presented in the present paper on the example of remote labs. Inductive teaching is one way to help students learn to use the fundamental concepts for problem solving – focusing on cases that students could work on to help develop an understanding of the phenomenon. For effective inductive teac...

Today's engineering education needs practical hands-on experimentation as it has been long time already. However the learning process is now moved into the Internet in many aspects and learners expect to get most of the content and activity available over the Internet. Practical experiments is not trivial to carry out over the Internet, but using n...

In this paper a comprehensive toolkit for education of Mechatronics and Computer Science (especially micro controller and embedded programming) will be presented. The idea is based upon material for internet assisted distance learning, home labs as well as for face-to-face education in classes. The concepts details are composed of special DistanceL...

This book is a collection of various mechatronics and automation projects presented in the form of learning situations. A learning situation is a new approach; it aims to support independent learning and presents a problem as a whole. Knowledge and skills are provided through practical activities and result-centred learning, not just as a declarati...

The paper presents an innovative concept of teaching and learning of embedded systems and mechatronics. On the frame of project NetLab, new learning situations are transferred, developed and applied into practice in Estonia, Germany and Finland. In addition, remote lab centers are established to allow remote access to different types of hardware ne...