Modelling the ZalaZONE Proving Ground: a benchmark of State-of-the-art Automotive Simulators PreScan, IPG CarMaker, and VTD Vires

Gangel, Kálmán; Hamar, Zoltán; Háry, András; Horváth, Ágnes; Jandó, Gábor; Könyves, Balázs; Panker, Dániel; Pinter, Krisztian; Pataki, Márton; Szalai, Mátyás; Szalay, Zsolt; Tettamanti, Tamás; Tihanyi, Viktor; Tóth, Bence; Varga, Balázs; Viharos, Zsolt János

doi:10.14513/actatechjaur.00606

Cited by 11 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The next steps of this research include evaluating more RL algorithms on this problem (e.g., discrete Q-learning, DQN) to find the most beneficial solution in practice. In the future, the goal is to test this approach in real conditions on a commercial test car on the ZalaZONE proving ground preceded by a validation on the freely available ZalaZONE simulated environment [17]. Also, this research will set its focus on more complex problems and situations later, like adding noise to the environment (e.g., varying road surfaces) and performing more challenging maneuvers in form of trajectory following problems.…”

Section: Discussionmentioning

confidence: 99%

Initiation and Stabilization of Drifting Motion of a Self-driving Vehicle with a Reinforcement Learning Agent

Tóth¹,

Bárdos²,

Viharos³

2022

Proceedings of the First Conference on ZalaZONE Related R&I Activities of Budapest University of Technology and Economics 2

Self Cite

View full text Add to dashboard Cite

Performing special driving techniques like drifting can be challenging even for professional human drivers. However, such maneuvers can be essential for avoiding accidents in critical road scenarios like evasive maneuvers. This paper reports novel research results whose main goal is to develop a self-driving agent for drift motion control based on vehicle simulation in MATLAB/Simulink. The state representation of the vehicle includes the longitudinal and lateral velocities with the yaw rate. The agent action space consists of two actuators: the throttle position and the roadwheel angle. The goal of the agent is twofold: first, it needs to jump into a drifting state; second, it has to keep the vehicle in drift. The simulation results show that the proposed RL agent is capable of learning to approach a predetermined drift equilibrium from cornering and staying in this drift situation as well. For the training, the solution excluded using any prior data. It only works with information gained from the simulation model, which is a remarkable difference from the actual state-of-the-art RL-based solutions.

show abstract

Section: Discussionmentioning

confidence: 99%

Initiation and Stabilization of Drifting Motion of a Self-driving Vehicle with a Reinforcement Learning Agent

Tóth¹,

Bárdos²,

Viharos³

2022

Proceedings of the First Conference on ZalaZONE Related R&I Activities of Budapest University of Technology and Economics 2

Self Cite

View full text Add to dashboard Cite

show abstract

“…To ensure the right cooperation between the two software, the OpenDRIVE ® virtual environment of the ZalaZONE Smart City was imported into the vehicle simulation tools. The model was generated using laser scanning, but manually built environments can also be used in both software [48].…”

Section: Applied Simulation Sofware and Their Application In The Simu...mentioning

confidence: 99%

Development and Functional Validation Method of the Scenario-in-the-Loop Simulation Control Model Using Co-Simulation Techniques

Toth,

Szalay

2023

Machines

Self Cite

View full text Add to dashboard Cite

With the facilitated development of highly automated driving functions and automated vehicles, the need for advanced testing techniques also arose. With a near-infinite number of potential traffic scenarios, vehicles have to drive an increased number of test kilometers during development, which would be very difficult to achieve with currently utilized conventional testing methods. State-of-the-Art testing technologies such as Vehicle-in-the-Loop (ViL) or Scenario-in-the-Loop (SciL) can provide a long-term solution; however, validation of these complex systems should also be addressed. ViL and SciL technologies provide real-time control and measurement with multiple participants; however, they require enormous computational capacity and low-latency communication to provide comparable results with real-world testing. 5G (fifth-generation wireless) communication and Edge computing can aid in fulfilling these needs, although appropriate implementation should also be tested. In the current paper, a realized control model based on the SciL architecture was presented that was developed with real-world testing data and validated utilizing co-simulation and digital twin techniques. The model was established in Simcenter Prescan© connected to MATLAB Simulink® and validated using IPG CarMaker®, which was used to feed the simulation with the necessary input data to replace the real-world testing data. The aim of the current paper was to introduce steps of the development process, to present the results of the validation procedure, and to provide an outlook of potential future implementations into the state of the art in proving ground ecosystems.

show abstract

“…The more, the mission of ZalaZONE is not limited to pure commercial use. It is also a major goal to lay the foundation for research and innovation activities in national and international cooperation with universities, research centers, and industrial participants (Szalay et al, 2017;Gangel et al, 2021;Duleba et al, 2021). The braking platform (Fig.…”

Section: A Measurement At Zalazone Proving Groundmentioning

confidence: 99%

OpenCRG Models From Different Data Sources to Support Vehicle Simulations

et al. 2022

Self Cite

View full text Add to dashboard Cite

Digital twins of road surfaces support multiple engineering applications. Remote sensing technologies provide information from the entire surface of the pavement by high accuracy point clouds. Pavement errors and differences from designed geometry can be detected and assessed using such datasets, while OpenCRG models derived from point clouds support transportation applications. High-resolution CRG (Curved Regular Grid) models enable analyzing vehicle suspension systems in vehicle dynamics simulation environments. Furthermore, such models also support creating the digital twins of vehicle suspensions and improve the development and research of models related to vehicle dynamics. The paper presents how the suspension digital twin was obtained applying a genetic algorithm and how it was assessed. The quality of raw data and that of the derived methods are analyzed in the case of multiple mapping technologies (terrestrial, mobile, and aerial laser scanning). CRG models were created from all datasets, and their applicability was investigated to support vehicle simulations with high accuracy demand. Other important vehicle-related use cases are also mentioned in the paper.INDEX TERMS road geometry, point clouds, laser scanning, OpenCRG I. INTRODUCTION

show abstract

Modelling the ZalaZONE Proving Ground: a benchmark of State-of-the-art Automotive Simulators PreScan, IPG CarMaker, and VTD Vires

Cited by 11 publications

References 13 publications

Initiation and Stabilization of Drifting Motion of a Self-driving Vehicle with a Reinforcement Learning Agent

Initiation and Stabilization of Drifting Motion of a Self-driving Vehicle with a Reinforcement Learning Agent

Development and Functional Validation Method of the Scenario-in-the-Loop Simulation Control Model Using Co-Simulation Techniques

OpenCRG Models From Different Data Sources to Support Vehicle Simulations

Contact Info

Product

Resources

About