Ernö Horváth

56405132200

Publications - 36

Localization robustness improvement for an autonomous race car using multiple extended Kalman filters

Krisztian Enisz Ernö Horváth Istvan Szalay

Publication Name: Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering

Publication Date: 2025-08-01

Volume: 239

Issue: 9

Page Range: 3771-3783

Description:

In this paper, we introduce a vehicle localization method designed for the SZEnergy race car, which competes in the Shell Eco-marathon. The proposed method comprises four different extended Kalman filter-based localization algorithms and a selection algorithm that determines the most suitable one based on vehicle speed, GNSS availability, and signal quality. The low-speed Kalman filters are based on a kinematic vehicle model while the high-speed variants are based on a dynamic vehicle model. Several measurements were performed during test maneuvers to evaluate the performance of the filters. The proposed method succesfully handles sensor miscalibration and GNSS outages.

Open Access: Yes

DOI: 10.1177/09544070241266281

Driver Clustering Based on Individual Curve Path Selection Preference

Ernö Horváth Gergo Igneczi Krisztian Nyilas Tamas Dobay

Publication Name: Applied Sciences Switzerland

Publication Date: 2025-07-01

Volume: 15

Issue: 14

Page Range: Unknown

Description:

The development of Advanced Driver Assistance Systems (ADASs) has reached a stage where, in addition to the traditional challenges of path planning and control, there is an increasing focus on the behavior of these systems. Assistance functions shall be personalized to deliver a full user experience. Therefore, driver modeling is a key area of research for next-generation ADASs. One of the most common tasks in everyday driving is lane keeping. Drivers are assisted by lane-keeping systems to keep their vehicle in the center of the lane. However, human drivers often deviate from the center line. It has been shown that the driver’s choice to deviate from the center line can be modeled by a linear combination of preview curvature information. This model is called the Linear Driver Model. In this paper, we fit the LDM parameters to real driving data. The drivers are then clustered based on the individual parameters. It is shown that clusters are not only formed by the numerical similarity of the driver parameters, but the drivers in a cluster actually have similar behavior in terms of path selection. Finally, an Extended Kalman Filter (EKF) is proposed to learn the model parameters at run-time. Any new driver can be classified into one of the driver type groups. This information can be used to modify the behavior of the lane-keeping system to mimic human driving, resulting in a more personalized driving experience.

Open Access: Yes

DOI: 10.3390/app15147718

An Improved IEHO Super-Twisting Sliding Mode Control Algorithm for Trajectory Tracking of a Mobile Robot

Mostafa MJAHED R. C. Pozna Ernö Horváth Abdeljalil EL KARI Nada EL GMILI Hassan AYAD Ahmed OULTILIGH

Publication Name: Studies in Informatics and Control

Publication Date: 2024-03-01

Volume: 33

Issue: 1

Page Range: 49-60

Description:

In recent years, trajectory tracking of a mobile robot has been one of the most addressed problems in the specilized literature, as a mobile robot must have the ability to follow a trajectory, while also compensating various external and internal disturbances. This paper proposes an IEHO-STSM controller based on the super-twisting sliding mode for the path tracking of a mobile robot. First, a new improved IEHO algorithm has been developed and introduced, based on the EHO (Elephant Herding Optimization) metaheuristic algorithm. The developed algorithm consisted in improving the performance of the basic EHO such as convergence speed, exploration and exploitation capabilities. Then, based on a dynamic model of the mobile robot, a super-twisting sliding mode (STSM) controller was designed to guide the robot to the desired trajectory. Finally, the improved IEHO algorithm was applied for adjusting the parameters of the super-twisting sliding mode (STSM) controller. The analysis of the proposed IEHO algorithm has been done by comparing it with EHO, PSO (Particle Swarm Optimization) and GWO (Grey Wolf Optimizer) algorithms, by employing it in tuning the STSM. The simulation results show that the proposed IEHO-STSM can reach both high precision and high speed capability, by overcoming external and internal disturbances.

Open Access: Yes

DOI: 10.24846/v33i1y202405

Curve Trajectory Model for Human Preferred Path Planning of Automated Vehicles

R. Tóth Ernö Horváth Gergo Igneczi Krisztian Nyilas

Publication Name: Automotive Innovation

Publication Date: 2024-02-01

Volume: 7

Issue: 1

Page Range: 59-70

Description:

Automated driving systems are often used for lane keeping tasks. By these systems, a local path is planned ahead of the vehicle. However, these paths are often found unnatural by human drivers. In response to this, this paper proposes a linear driver model, which can calculate node points reflective of human driver preferences and based on these node points a human driver preferred motion path can be designed for autonomous driving. The model input is the road curvature, effectively harnessed through a self-developed Euler-curve-based curve fitting algorithm. A comprehensive case study is undertaken to empirically validate the efficacy of the proposed model, demonstrating its capacity to emulate the average behavioral patterns observed in human curve path selection. Statistical analyses further underscore the model's robustness, affirming the authenticity of the established relationships. This paradigm shift in trajectory planning holds promising implications for the seamless integration of autonomous driving systems with human driving preferences.

Open Access: Yes

DOI: 10.1007/s42154-023-00259-8

Teaching Aspects of ROS 2 and Autonomous Vehicles †

Ernö Horváth Miklos Unger Rudolf Krecht Gergo Igneczi Norbert Marko

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

The advancement of autonomous vehicles (AVs) has brought forth a substantial need for effective education in robotic operating systems, particularly ROS 2, which serves as the backbone for many autonomous vehicle (AV) applications. This paper explores the academic approach and instructional methodologies tailored for teaching ROS 2 in the context of autonomous vehicle technology. It highlights the critical components and architecture of ROS 2, emphasizing its modularity, real-time communication capabilities, and robust ecosystem which make it ideal for AV development. Through a detailed curriculum outline, we describe hands-on learning activities, simulation-based exercises, and project-driven modules that facilitate deep understanding and practical skills acquisition. The effectiveness of these teaching methods is evaluated through a mixed-methods study involving student feedback, performance assessments, and project outcomes. Results indicate significant improvements in student comprehension and proficiency in both ROS 2 and autonomous vehicle systems. This research contributes to the body of knowledge by providing a comprehensive framework for educators to effectively teach ROS 2, thereby fostering the next generation of engineers proficient in developing and deploying autonomous vehicle technologies.

Open Access: Yes

DOI: 10.3390/engproc2024079049

Review of Vehicle Motion Planning and Control Techniques to Reproduce Human-like Curve-Driving Behavior †

Ernö Horváth Gergo Igneczi

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

Among the many technological challenges of automated driving development, there is an increasing focus on the behavior of these systems. Behavior is usually associated with multiple layers of control. In this paper, we focus on motion planning and control, and how these layers can be tailored to produce different behavior. Our review aims to collect and judge the most used techniques in the field of path planning and control. It has been revealed that model predictive planning and control provides high flexibility, with the cost of high computational capacity. There are simpler algorithms, such as pure-pursuit and Stanley controllers, however, these have very few parameters, therefore, the number of possible behavior patterns is limited.

Open Access: Yes

DOI: 10.3390/engproc2024079020

Human-Like Behaviour for Automated Vehicles (HLB4AV) Naturalistic Driving Dataset

Ernö Horváth Gergo Igneczi

Publication Name: Sisy 2024 IEEE 22nd International Symposium on Intelligent Systems and Informatics Proceedings

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: 491-496

Description:

Human-Like Behaviour for Automated Vehicles (HLB4AV) dataset is a collection of data of drivers, driving naturally in a rural road segment. The instructions were always to drive with their own, instinctive style, without knowing the goal of the measurement. The measurements took place always during the day, on weekdays, with no or low traffic, good sight visibilities and dry weather conditions. There are always reference measurements of the given road sections, where professional drivers were asked to drive a well-sensored test vehicle. Dataset contains information of accurate vehicle kinematics, lane edge geometry, test vehicle localization and surrounding traffic. The dataset is unique as besides physical vehicle data metadata of the drivers in terms of driving frequency, experience and age is also added. The data can be used to analize the basic path and speed selection of drivers on rural roads, their reaction on other traffic participants or lane offset selection. The data continuously grows, new measurement platforms as well as new drivers and road sections are planned to be added.

Open Access: Yes

DOI: 10.1109/SISY62279.2024.10737549

Performance Analysis of Position Estimation and Correction Methods †

Krisztian Enisz Ernö Horváth Zoltan Szeli József Gábor Pázmány Norbert Marko

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

There are several global and local position estimation and refinement techniques based on the GNSS (Global Navigation Satellite System) and environmental monitoring (e.g., LIDAR, Light Detection and Ranging). These are usually based on a combination of multiple sensors using some form of sensor fusion, together with a filtering or observation technique. The behavior of these algorithms may vary depending on the applied sensor signals and on their accuracy under different environmental conditions and for different vehicle types. In the case of systems that also use GNSS signals, different procedures must also be prepared for signal dropouts and, in the worst case, drastic fluctuations in accuracy. The aim of this research is to present and compare the performance of different estimation procedures for different vehicles and environmental conditions.

Open Access: Yes

DOI: 10.3390/engproc2024079061

Analysis of Drivers’ Path Follow Behaviour

Attila Borsos Ernö Horváth Gergő Ferenc Ignéczi

Publication Name: Proceedings of the International Conference on Informatics in Control Automation and Robotics

Publication Date: 2024-01-01

Volume: 2

Issue: Unknown

Page Range: 93-100

Description:

Lane keeping is a complex, multi-dimensional problem in terms of driving tasks. The lane-following driver models typically treat the control task as an end-to-end problem where the entire control chain is modelled as a human driver. However, the driver does not actively control the vehicle all the time, but follow a drift and compensate strategy, resulting in oscillations around their planned path. We have separated this oscillation scheme by filtering drivers’ selected offset to the centerline of the lane. It has been shown that there is a certain amount of offset error up to which drivers drift away from the planned path. At this point drivers intervene by applying torque to the steering wheel and steer the vehicle back onto the path. This type of drift and compensate strategy was modelled using Model Predictive Control (MPC) with event-based weights of its cost function. The proposed driver model calculates both the intervention point and the weights of the MPC based on real drivers’ data. As a result, the model together with the MPC can accurately plan the oscillation path of the drivers, contributing to a better understanding of how the driver tolerates offset errors.

Open Access: Yes

DOI: 10.5220/0012889100003822

Towards Robust LIDAR Lane Clustering for Autonomous Vehicle Perception in ROS 2

R. C. Pozna Ernö Horváth Dániel Pup Miklos Unger

Publication Name: Proceedings 2024 IEEE International Conference on Mobility Operations Services and Technologies Most 2024

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: 229-234

Description:

From LIDAR pointclouds traffic lanes, racetracks, parking lanes can be extracted with clustering algorithms. However, standard clustering algorithms like DBSCAN, K-means, and BIRCH may exhibit limited robustness in recognizing these specific geometric patterns. The current paper proposes a modification of the well-known DBSCAN algorithm which is designed for autonomous vehicle lane detection. The main idea of the proposed work is to add extra steps into the classic DBSCAN algorithm, thus regulate the cluster expansion. This modification introduces some challenges too, their subsequent resolution will be addressed in detail. To reproduce our work, both the dataset and the accompanying source code in python is shared publicly.

Open Access: Yes

DOI: 10.1109/MOST60774.2024.00031

Deep Learning-Based Approach for Autonomous Vehicle Localization: Application and Experimental Analysis

Krisztian Enisz Ernö Horváth Istvan Szalay Norbert Marko

Publication Name: Machines

Publication Date: 2023-12-01

Volume: 11

Issue: 12

Page Range: Unknown

Description:

In a vehicle, wheel speed sensors and inertial measurement units (IMUs) are present onboard, and their raw data can be used for localization estimation. Both wheel sensors and IMUs encounter challenges such as bias and measurement noise, which accumulate as errors over time. Even a slight inaccuracy or minor error can render the localization system unreliable and unusable in a matter of seconds. Traditional algorithms, such as the extended Kalman filter (EKF), have been applied for a long time in non-linear systems. These systems have white noise in both the system and in the estimation model. These approaches require deep knowledge of the non-linear noise characteristics of the sensors. On the other hand, as a subset of artificial intelligence (AI), neural network-based (NN) algorithms do not necessarily have these strict requirements. The current paper proposes an AI-based long short-term memory (LSTM) localization approach and evaluates its performance against the ground truth.

Open Access: Yes

DOI: 10.3390/machines11121079

Network Optimization Aspects of Autonomous Vehicles: Challenges and Future Directions

Tamás Budai Ernö Horváth Akos Kovacs Miklos Unger Rudolf Krecht Norbert Marko

Publication Name: IEEE Network

Publication Date: 2023-07-01

Volume: 37

Issue: 4

Page Range: 282-288

Description:

Global megatrends, such as urbanization, population growth, and emerging network solutions are accelerating the development of the Connected and Autonomous Vehicles (CAVs) industry. There are many truths, some misconceptions, and even some excitement about CAVs in the public's opinion. The main objective of the current article is to provide a comprehensive review, eliminate misconceptions, and outline the future of the network optimization aspects of autonomous vehicles by presenting various multidisciplinary methods, such as cooperative perception. Given our extensive experience with CAVs, we are aiming to share some of the insights and knowledge we have gained, along with relevant use-cases and experiment results.

Open Access: Yes

DOI: 10.1109/MNET.007.2300023

Node Point Optimization for Local Trajectory Planners based on Human Preferences

Ernö Horváth Gergo Igneczi

Publication Name: 2023 IEEE 21st World Symposium on Applied Machine Intelligence and Informatics Sami 2023 Proceedings

Publication Date: 2023-01-01

Volume: Unknown

Issue: Unknown

Page Range: 225-230

Description:

There is an increased number of Driver Assistance systems on the field, therefore the need of having naturalistic behavior of these functions is increasing. In our work the trajectory planning task is analyzed. A clothoid-based local trajectory planning algorithm is proposed, which relies on node points within the look ahead distance. The node point distances were optimized to yield a global trajectory which is close to the human drivers' path. Real driving data was used as the optimization reference. As a result of the optimization, we were able to determine a characteristic node point distance set which fits all drivers. We have also shown that three node points within a look ahead distance of 140 m are sufficient to describe the drivers' trajectory. Later this result will serve as a basis to build a driver model which calculates the lateral coordinates of the node points.

Open Access: Yes

DOI: 10.1109/SAMI58000.2023.10044488

A Linear Driver Model of Local Path Planning for Lane Driving

Ernö Horváth Gergo Igneczi Krisztian Nyilas

Publication Name: Sisy 2023 IEEE 21st International Symposium on Intelligent Systems and Informatics Proceedings

Publication Date: 2023-01-01

Volume: Unknown

Issue: Unknown

Page Range: 103-108

Description:

Modern lane centering assistance systems often use the mid-lane as a reference line for tracking. However, human drivers prefer to keep an offset to the mid-lane. Therefore, we have proposed in our previous work a driver model which calculates human-like offset values and enable the path planner to plan human-like paths. The driving data of 15 drivers have been analyzed. It has been revealed that drivers behave differently in left or right curves and choose to drive on either the left or the right side in straight road sections. Therefore, we extend our model to handle these traits. We have shown that the extended model outperforms the previous symmetric model.

Open Access: Yes

DOI: 10.1109/SISY60376.2023.10417953

Hybrid Particle Filter-Particle Swarm Optimization Algorithm and Application to Fuzzy Controlled Servo Systems

R. C. Pozna E. M. Petriu Radu Emil Precup Ernö Horváth

Publication Name: IEEE Transactions on Fuzzy Systems

Publication Date: 2022-10-01

Volume: 30

Issue: 10

Page Range: 4286-4297

Description:

This article presents a hybrid metaheuristic optimization algorithm that combines particle filter (PF) and particle swarm optimization (PSO) algorithms. The new PF-PSO algorithm consists of two steps: the first generates randomly the particle population;and the second zooms the search domain. An application of this algorithm to the optimal tuning of proportional-integral-fuzzy controllers for the position control of a family of integral-type servo systems is then presented as a second contribution. The reduction in PF-PSO algorithm's cost function allows for reduced energy consumption of the fuzzy control system. A comparison with other metaheuristic algorithms on canonical test functions and experimental results are presented at the end of this article.

Open Access: Yes

DOI: 10.1109/TFUZZ.2022.3146986

A Clothoid-based Local Trajectory Planner with Extended Kalman Filter

Ernö Horváth Gergo Igneczi

Publication Name: Sami 2022 IEEE 20th Jubilee World Symposium on Applied Machine Intelligence and Informatics Proceedings

Publication Date: 2022-01-01

Volume: Unknown

Issue: Unknown

Page Range: 467-472

Description:

The paper introduces a local trajectory planner designed specifically for lateral guidance of autonomous vehicles. The inputs of the planner are the lane edges in the form of corner point coordinates in a two-dimensional plane. The aim of the planner is to provide a series of trajectory points ahead of the vehicle. The trajectory shall be well-conditioned which means no border violation (safety), no high lateral acceleration (comfort) and good tracking properties. The optimal conditions for driving have been found in using clothoid curves. The curvature of the clothoid is a linear function of the distance, which resolves the biggest disadvantage of circle conjunction: the discontinuity of the lateral acceleration. Clothoids have constant lateral jerk profile. In our work an Extended Kalman Filter is used with a clothoid model to consolidate inaccuracies of the lane detection system. The paper is presented as the first part of a research process. The algorithm introduced in this paper is planned to be continued with research on its automatized calibration procedures.

Open Access: Yes

DOI: 10.1109/SAMI54271.2022.9780857

Real‐time lidar‐based urban road and sidewalk detection for autonomous vehicles

R. C. Pozna Ernö Horváth Miklos Unger

Publication Name: Sensors

Publication Date: 2022-01-01

Volume: 22

Issue: 1

Page Range: Unknown

Description:

Road and sidewalk detection in urban scenarios is a challenging task because of the road imperfections and high sensor data bandwidth. Traditional free space and ground filter algorithms are not sensitive enough for small height differences. Camera‐based or sensor‐fusion solutions are widely used to classify drivable road from sidewalk or pavement. A LIDAR sensor contains all the necessary information from which the feature extraction can be done. Therefore, this paper focuses on LIDAR‐based feature extraction. For road and sidewalk detection, the current paper presents a real‐time (20 Hz+) solution. This solution can also be used for local path planning. Sidewalk edge detection is the combination of three algorithms working parallelly. To validate the result, the de facto standard benchmark dataset, KITTI, was used alongside our measurements. The data and the source code to reproduce the results are shared publicly on our GitHub repository.

Open Access: Yes

DOI: 10.3390/s22010194

Case study on the tactical level of an autonomous vehicle control

R. C. Pozna Csaba Antonya Ernö Horváth

Publication Name: International Conference on Electrical Computer Communications and Mechatronics Engineering Iceccme 2021

Publication Date: 2021-10-07

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In this paper, a case study is presented on the tactical level of autonomous vehicle control. Inspired by the human driver behavior, vehicle control is structured in a hierarchy on three levels: the strategic, the tactical, and the operational level. These are connected by specific links, and based on prior information and models, are transforming the input data from the environment into actuator commands on the various degree of freedom of the vehicle. The case study is presenting a simulation of a scenario, detailing the vehicle models with sensors, the collection of behavior, and the behavior selector.

Open Access: Yes

DOI: 10.1109/ICECCME52200.2021.9590868

Clothoid-based Trajectory following Approach for Self-driving vehicles

R. C. Pozna Ernö Horváth

Publication Name: Sami 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics Proceedings

Publication Date: 2021-01-21

Volume: Unknown

Issue: Unknown

Page Range: 251-254

Description:

Lately self-driving navigation and control have obtained significant attention in many fields, such as mobile robotics or autonomous driving. Although sensing, perception, planning and following subtasks associated with autonomous vehicles persist with open challenges. In this paper the autonomous following subtask is targeted. The paper proposes trajectory following approach which is designed for self-driving vehicles.

Open Access: Yes

DOI: 10.1109/SAMI50585.2021.9378664

Self-Driving Vehicle Sensors from One-Seated Experimental to Road-legal Vehicle

Ernö Horváth Zoltan Szeli Peter Koros Gábor Szakállas Peter Gulyas Zoltan Pusztai

Publication Name: Ines 2020 IEEE 24th International Conference on Intelligent Engineering Systems Proceedings

Publication Date: 2020-07-01

Volume: Unknown

Issue: Unknown

Page Range: 97-101

Description:

Our university is determined to research and educate self-driving and autonomous technology. These two field require different necessities and attitude. In his paper we would like to summarize the migration from a road-legal vehicle to a self-developed, one-seated vehicle. We will describe the challenges of the migration process and of course how to overcome these challenges. The current paper also proposes recommendations and use-cases regarding self-driving vehicle sensory system.

Open Access: Yes

DOI: 10.1109/INES49302.2020.9147181

Development of Point-cloud Processing Algorithm for Self-Driving Challenges

Ernö Horváth Peter Koros Miklos Unger

Publication Name: Ines 2020 IEEE 24th International Conference on Intelligent Engineering Systems Proceedings

Publication Date: 2020-07-01

Volume: Unknown

Issue: Unknown

Page Range: 91-95

Description:

The paper proposes an own-developed point-cloud processing algorithm which was developed for the Autonomous Urban Concept competition organized by Shell. The approach does not intend to solve general-purpose object recognition and tracking, although the methodologies presented can be used as general solutions. Our approach will be presented in comprehensive manner, the challenges and solutions will be detailed. Also, the dysfunctional ideas will be listed, and alternative workarounds will be presented as recommendations too. As verification of the algorithm, both simulation and real-world measurements will be presented. For the sake of research and open source, we share datasets and necessary information publicly.

Open Access: Yes

DOI: 10.1109/INES49302.2020.9147201

Enhancement of pure-pursuit path-tracking algorithm with multi-goal selection

Csaba Hajdu Ernö Horváth Peter Koros

Publication Name: Gpmc 2019 1st IEEE International Conference on Gridding and Polytope Based Modeling and Control Proceedings

Publication Date: 2019-11-01

Volume: Unknown

Issue: Unknown

Page Range: 13-18

Description:

In this paper, we present an enhancement to the popular pure-pursuit algorithm, widely used in robotics and automotive applications. The original algorithm is simple and straightforward as it depends only on the very basic attributes of the kinematic model of the target mechanical system. The algorithm is usually tuned by choosing a look-ahead distance of points from the reference trajectory. On the other hand, pure-pursuit suffers from considerable tuning weaknesses highly attributed to improper selection of look-ahead distance, resulting in poor tracking performance. Our method proposes the dynamic change of lookahead distance based on selecting multiple-goal points, thus aiming a curvature fitting more the reference trajectory. Our work was motivated by an ongoing robotics and autonomous vehicle research project at our university.

Open Access: Yes

DOI: 10.1109/GPMC48183.2019.9106958

Novel Pure-Pursuit Trajectory Following Approaches and their Practical Applications

Csaba Hajdu Ernö Horváth Peter Koros

Publication Name: 10th IEEE International Conference on Cognitive Infocommunications Coginfocom 2019 Proceedings

Publication Date: 2019-10-01

Volume: Unknown

Issue: Unknown

Page Range: 597-602

Description:

Pure-pursuit algorithm is a popular trajectory tracking algorithm, widely used in mobile robotics and vehicular control for numerous reasons. The operation is simple and straightforward as it depends only on the kinematic model of the target mechanical system. The algorithm can be tuned by choosing look-Ahead distance of points of the reference trajectory. On the other hand, pure-pursuit suffers from weaknesses highly attributed to improper selection of look-Ahead distance, resulting in poor tracking performance. Recent developments focused on overcoming this drawback by dynamical change of this parameter. In this paper, we propose three enhancements to the original pure-pursuit algorithm, aiming to handle dynamic selection of look-Ahead distance by selecting multiple goals, modifying look-Ahead distance according to the curvatures and adjusting lateral deviation. Our work was motivated by an ongoing autonomous vehicle research at our university.

Open Access: Yes

DOI: 10.1109/CogInfoCom47531.2019.9089927

Range sensor-based occupancy grid mapping with signatures

Á Ballagi Csaba Hajdu Ernö Horváth Claudiu Radu

Publication Name: Proceedings of the 2019 20th International Carpathian Control Conference Iccc 2019

Publication Date: 2019-05-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Recently autonomous navigation technologies have received huge attention in many fields, such as autonomous driving or mobile robotics. Simultaneous localization and mapping (SLAM) [1] is a key problem in this field and the current paper targets the mapping part of it. Mapping means to construct accurate static or even dynamic representation of the observable environment. There are of course solutions for range sensor-based mapping, but the current paper proposes a new approach, which involves signatures. Signature is a mathematical data representation, which handles well uncertainty in complex systems.

Open Access: Yes

DOI: 10.1109/CarpathianCC.2019.8765684

A Mobile Robot and Vehicle Occupancy Map Construction Model

R. C. Pozna Á Ballagi Ernö Horváth

Publication Name: Ines 2019 IEEE 23rd International Conference on Intelligent Engineering Systems Proceedings

Publication Date: 2019-04-01

Volume: Unknown

Issue: Unknown

Page Range: 59-64

Description:

Occupancy gird map is a popular way of representing the environment regarding robots and vehicles. It consists of discrete cells, where each occupancy grid cell is valued independently. Because the represented grid structure is rigid it requires priori known memory resource concerning the size of the environment to obtain. Since their introduction, occupancy grid maps are still researched intensively [1] [2] [3]. In the current paper we propose the mathematical description of the computational simplification via alternative methods for occupancy map.

Open Access: Yes

DOI: 10.1109/INES46365.2019.9109531

Evaluation of Neural Network-Based Sensing and Perception in Experimental Vehicles

R. C. Pozna Á Ballagi Ernö Horváth

Publication Name: Ines 2018 IEEE 22nd International Conference on Intelligent Engineering Systems Proceedings

Publication Date: 2018-11-05

Volume: Unknown

Issue: Unknown

Page Range: 000113-000118

Description:

As increasing use of neural networks (NN) and deep-learning (DL) can be observed in various fields, such as voice and image recognition, control, translation, data processing, function approximation, etc. These technologies can also be applied in a specific domain of experimental vehicles. This paper presents and summarizes our recent practical experiences gained during the usage of neural network as sensing and perception subsystem in an experimental vehicle. The paper does not targets general NN problems, only focuses on the narrow subdomain. The current paper also reviews and evaluates the available hyper parameter tunings, optimizers and neural network architectures and proposes tested solutions for enhanced performance. All of the used datasets, source codes and additional materials is available online.

Open Access: Yes

DOI: 10.1109/INES.2018.8523952

Two-stage racetrack segmentation method using color feature filtering and superpixel-based convolutional neural network

R. C. Pozna Ernö Horváth János Hollósi

Publication Name: Saci 2018 IEEE 12th International Symposium on Applied Computational Intelligence and Informatics Proceedings

Publication Date: 2018-08-20

Volume: Unknown

Issue: Unknown

Page Range: 131-135

Description:

The Széchenyi István University race car team is an active and successful participant of the Shell Eco-marathon for long time ago. The Shell introduces the autonomous vehicle category on the Eco-marathon for 2018. Our long-term goal is to make the Szenergy racing team's vehicle suitable for the autonomous category. The first milestone is to make a reliable computer vision based intelligent detection system that understands the environment of the racing car. In this paper we will present a solution for racetrack detection i.e. a fusion of image processing and neural network systems. The two-stage recognition system is at the first phase an image processing algorithm which finds the red-white and blue-white striped edge of the road, and at the second phase, a pre-trained superpixel-based neural network which recognize the road on the filtered image.

Open Access: Yes

DOI: 10.1109/SACI.2018.8440968

Robot coverage path planning based on Iterative Structured Orientation

R. C. Pozna Radu Emil Precup Ernö Horváth

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2018-01-01

Volume: 15

Issue: 2

Page Range: 231-249

Description:

Coverage path planning for mobile robots aims to compute the shortest path that ensures the overlap of a given area, with applications in various domains. This paper proposes a coverage path planning strategy, referred to as Iterative Structured Orientation Coverage, which has two main advantages over the state-of-the-art, namely it is it versatile and it is capable to handle complex environments. The path planning strategy is expressed as three new approaches to coverage path planning. The suggested approaches are validated by simulation and experimental results. The source codes along with the test set are available in a public repository.

Open Access: Yes

DOI: 10.12700/APH.15.1.2018.2.12

Probabilistic occupancy grid map building for Neobotix MP500 robot

R. C. Pozna Ernö Horváth

Publication Name: Proceedings of the 2016 13th Workshop on Positioning Navigation and Communication Wpnc 2016

Publication Date: 2017-01-17

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In vehicle and robot navigation low-level tasks such as path planning, obstacle avoidance and autonomous operation are extensively studied nowadays. Most of these task require map building. In this paper a map representation is discussed with the focus for the singular domain of our Neobotix MP500 mobile robot. Among others the state of the art map building techniques will be introduced such as topological map, line map, landmark-based map and of course in more detail the occupancy grid based map. The probabilistic representation of the occupancy grid will be examined as a map building problem for the given mobile robot.

Open Access: Yes

DOI: 10.1109/WPNC.2016.7822843

Two operating states-based low energy consumption vehicle control

István Lakatos Ernö Horváth Peter Koros Ferenc Szauter

Publication Name: Proceedings of the ASME Design Engineering Technical Conference

Publication Date: 2017-01-01

Volume: 9

Issue: Unknown

Page Range: Unknown

Description:

The current paper presents a realization of a complex vehicle control task. The goal was to consume the lowest possible energy in a less than 100 kg, wheel hub motor-driven vehicle. The realization is based on two distinguishable operating states which states characterizes well the driving cycle of the vehicle. The main contribution of the proposed method is that it reliably estimates the external loads which interacts the vehicle, the controller can adapt to this changes thus it can guarantee the minimal energy consumption. The vehicle described in the paper is a participant at the Shell Eco-marathon Europe competition in Urban Concept - Battery Electric category.

Open Access: Yes

DOI: 10.1115/DETC2017-67978

A use case of the simulation-based approach to mobile robot algorithm development

R. C. Pozna Ernö Horváth János Hollósi Csaba Hajdu

Publication Name: Sami 2016 IEEE 14th International Symposium on Applied Machine Intelligence and Informatics Proceedings

Publication Date: 2016-03-01

Volume: Unknown

Issue: Unknown

Page Range: 311-314

Description:

A complex algorithm development progress for mobile robot (MR) usually requires a priori simulation of the whole dynamic environment before it is applied on a real-world robot. In order to reduce the development time and avoid programming mistakes it is recommended to use the same language for both simulation and real-word testing. The paper presents a certain use case for the simulation-based approach. In this use case V-REP is used for simulation, ROS for the real-world robot application and MATLAB or C# for algorithm development. Note that the source code of the work is available on a public GitHub repository.

Open Access: Yes

DOI: 10.1109/SAMI.2016.7423026

The inverse kinematics problem, a heuristical approach

R. C. Pozna Ernö Horváth János Hollósi

Publication Name: Sami 2016 IEEE 14th International Symposium on Applied Machine Intelligence and Informatics Proceedings

Publication Date: 2016-03-01

Volume: Unknown

Issue: Unknown

Page Range: 299-304

Description:

This paper presents a heuristic solution for the inverse kinematics problem. The heuristic consists on combining the distance between the actual position and the desired position of the gripper with the direction of the best manipulability of the robot. Theoretical results are validated by digital simulations resolute.

Open Access: Yes

DOI: 10.1109/SAMI.2016.7423024

Systematic approach to software related tasks in electric fuel-efficiency vehicle development

Ernö Horváth Peter Koros

Publication Name: Ines 2015 IEEE 19th International Conference on Intelligent Engineering Systems Proceedings

Publication Date: 2015-11-13

Volume: Unknown

Issue: Unknown

Page Range: 375-378

Description:

Nowadays software related tasks in experimental vehicle development are getting more and more attention. These tasks not only include the final product related software solutions such as the motor and the vehicle control algorithm or the telemetry system but even in the development process, applications are needed - for example on the motor test bench. The paper presents our ideas and solutions to software related tasks in vehicles for the whole development and validation process.

Open Access: Yes

DOI: 10.1109/INES.2015.7329737

Development of individual information technology systems of experimental vehicles

Peter Dely István Lakatos Ernö Horváth Peter Koros

Publication Name: Saci 2015 10th Jubilee IEEE International Symposium on Applied Computational Intelligence and Informatics Proceedings

Publication Date: 2015-08-17

Volume: Unknown

Issue: Unknown

Page Range: 489-493

Description:

Two experimental vehicles were developed during the last two years in the Research Center of Vehicle Industry. The vehicles mentioned above are electrically driven and equipped with own developed computational modules. During development of the computational modules it was an important issue for us to create easily extendable systems which are easy-To-use. Different applications are realized in the two vehicles, consequently, different requirements were set up concerning our applications.

Open Access: Yes

DOI: 10.1109/SACI.2015.7208253

An abstraction of the Lidar measurements

R. C. Pozna Ernö Horváth Janos Kovacs

Publication Name: Saci 2015 10th Jubilee IEEE International Symposium on Applied Computational Intelligence and Informatics Proceedings

Publication Date: 2015-08-17

Volume: Unknown

Issue: Unknown

Page Range: 381-385

Description:

The laser scanner seems to be one of the favorite sensors used in mobile robots (autonomous car) localization. The Lidar is similar to the radar except radio signals are substituted with laser beams. Measurements are a collection of n lengths obtained for different firing angles. The paper presents an abstraction of this collection. The abstraction reduce the dimensions of data from n to 3 and can be used in obstacles avoiding or in localization. The paper presents the abstraction definition and a simulation scenario where the abstraction is used.

Open Access: Yes

DOI: 10.1109/SACI.2015.7208234

Developing rapid prototype-capable applications for industrial mobile robot platforms

R. C. Pozna Ernö Horváth Janos Kovacs

Publication Name: Ines 2014 IEEE 18th International Conference on Intelligent Engineering Systems Proceedings

Publication Date: 2014-09-24

Volume: Unknown

Issue: Unknown

Page Range: 203-207

Description:

The paper summarizes our ideas and solutions in the subject of developing a rapid prototype-capable robot platform. Constructing a robotic platform for scientific researches means to find a robust electrical and mechanical system which is connected to a high computational device and it is easily programmable. Usually the first two features can be funded in industrial robots which unfortunately do not possess the last two. The presented solution refers to a mobile robot (Neobotix MP500) tuned with an extra computer and programmed with LabVIEW.

Open Access: Yes

DOI: 10.1109/INES.2014.6909369