People
doc. Ing. Stanislav Novotný, Ph.D.

2024, Neural Network World, 34 (5), p. 279-291), ISSN 1210-0552

This study explores the development and evaluation of external human-machine interfaces (eHMI) for communication between autonomous vehicles (AVs) and pedestrians. By employing advanced virtual reality (VR) simulations and leveraging behavioral data from 600 survey respondents, the research examines the intelligibility and effectiveness of seven eHMI prototypes. The experiments utilized eye-tracking and spatial analysis to measure pedestrian response to AV signals in realistic virtual environments. The findings emphasize the potential of LED strip-based communication interfaces, demonstrating their superiority in terms of visibility, clarity, and implementation cost. This research contributes to the broader field of artificial intelligence applications in transportation, with a focus on ensuring safety and trust in autonomous systems interacting with vulnerable road users.

2024

ČVUT usiluje o pozici lídra v oblasti vzdělávání, výzkumu a inovací, který inspiruje studenty, akademiky a širší komunitu k aktivnímu zapojení do budování udržitelné společnosti. Univerzita chce být institucí, která vytváří podmínky pro inovativní přístupy, podporuje ochranu planety a zároveň poskytuje prostor pro profesní i osobní rozvoj jednotlivců. Každá z patnácti tematických oblasti obsahuje 3–6 cílů, které byly definovány na základě analýzy a diskusí v rámci pracovních skupin napříč ČVUT. Pro stanovení jejich důležitosti byla využita Fullerova metoda párového srovnání. Tato metoda umožňuje systematické zhodnocení významnosti jednotlivých cílů porovnáním každého cíle s ostatními v rámci dané oblasti. Na základě výsledků párového srovnání jsou cíle seřazeny podle priority a získávají váhy, které odpovídají jejich významu pro danou oblast. Toto váhování je vizualizováno pomocí grafických výsečí, které obklopují ikonu každé klíčové oblasti. Výseče znázorňují relativní důležitost jednotlivých cílů, ale také pomáhají uživatelům dokumentu rychle pochopit klíčové priority každé oblasti. Tento přístup usnadňuje další kroky při implementaci opatření.

2023, Sensors, 23 (12), p. 1-16), ISSN 1424-8220

The present paper focuses on vehicle simulator fidelity, particularly the effect of motion cues intensity on driver performance. The 6-DOF motion platform was used in the experiment; however, we mainly focused on one characteristic of driving behavior. The braking performance of 24 participants in a car simulator was recorded and analyzed. The experiment scenario was composed of acceleration to 120 km/h followed by smooth deceleration to a stop line with prior warning signs at distances of 240, 160, and 80 m to the finish line. To assess the effect of the motion cues, each driver performed the run three times with different motion platform settings-no motion, moderate motion, and maximal possible response and range. The results from the driving simulator were compared with data acquired in an equivalent driving scenario performed in real conditions on a polygon track and taken as reference data. The driving simulator and real car accelerations were recorded using the Xsens MTi-G sensor. The outcomes confirmed the hypothesis that driving with a higher level of motion cues in the driving simulator brought more natural braking behavior of the experimental drivers, better correlated with the real car driving test data, although exceptions were found.

2021, 2021 3rd IEEE Middle East and North Africa COMMunications Conference (MENACOMM), Piscataway, NJ, IEEE), p. 147-151), ISBN 978-1-6654-3443-0

Autonomous Traffic Management (ATM) systems empowered with Machine Learning (ML) technics are a promising solution for eliminating traffic light and decreasing traffic congestion in the future. However, few efforts have focused on integrating pedestrians in ATM, namely the static programming-based cooperative protocol called Autonomous Pedestrian Crossing (APC). In this paper, we model a Markov Decision Process (MDP) to enable a Deep Reinforcement Learning (DRL)-based version of APC protocol that is able to dynamically achieve the same objectives (i.e. decreasing traffic delay at the crossing area). Using concrete state space, action set and reward functions, our model forces the Autonomous Vehicle (AV) to "think"and behave according to APC architecture. Compared to the traditional programming APC system, our approach permits the AV to learn from its previous experiences in non-signalized crossing and optimize the distance and the velocity parameters accordingly.

2020

Hlavním cílem studie bylo vytvoření systému měření HMI různých vozidel za použití objektivní a subjektivních metrik a analyzačních nástrojů, který je kompatibilní se systémy měření ve Škoda Auto. Stávající metodika byla obohacena o metody vyhodnocování pohledu a vizuální zátěže uživatele (eye tracking). Funkce systému byly ověřeny na reálném experimentu se zaměřením na řidičovu distrakci. Z výsledku vyplynou doporučení pro budoucí podobu uživatelských rozhraní HMI.

2020

Využití sofistikovaných modelů jednotlivých agregátů vozidla (HIL) a jejich zapojení do simulace při provádění experimentů (HMI).

2020

In the scope of the Motostudent competition there was created complex project of the whole motorcycle in the category of Electro bikes. Report contains conceptual design, detailed design, prototyping and development.

2019, 54th INTERNATIONAL SCIENTIFIC CONFERENCE ON INFORMATION, COMMUNICATION AND ENERGY SYSTEMS AND TECHNOLOGIES, Sofia, Technical University of Sofia), p. 321-324), ISSN 2603-3267

The paper provides overview of challenges of drivercar interaction in modern electric vehicles. Different aspects of human-machine interaction are reviewed. Analysis of method of driver-vehicle interaction through in-vehicle display and its influence on using eco driving modes is provided on the example of experimental studies in the field.

2017, Proceedings of the Human Factors and Ergonomics Society Europe Chapter 2016 Annual Conference. ISSN 2333-4959 (online), Groningen, The Human Factors and Ergonomics Society, Europe Chapter), ISSN 2333-4959

The article provides a study of driver fatigue experimental research on interactive driver simulator. Visually available face features, movements of eyes and facial expression are followed with the help of distant eye tracker. The driver behaviour of sleep deprived participants is observed and compared to that of the rested drivers. This research targets sparing the key features of driver behaviour for further implementation in detection methods of driver fatigue in the human-machine interface of modern and future cars.