Article
Engineering, Civil
Szilard Aradi
Summary: Academic research in the field of autonomous vehicles has gained popularity in recent years, covering various topics such as sensor technologies, communication, safety, decision making, and control. Artificial Intelligence and Machine Learning methods have become integral parts of this research. Motion planning, with a focus on strategic decision-making, trajectory planning, and control, has also been studied. This article specifically explores Deep Reinforcement Learning (DRL) as a field within Machine Learning. The paper provides insights into hierarchical motion planning and the basics of DRL, including environment modeling, state representation, perception models, reward mechanisms, and neural network implementation. It also discusses vehicle models, simulation possibilities, and computational requirements. The paper surveys state-of-the-art solutions, categorized by different tasks and levels of autonomous driving, such as car-following, lane-keeping, trajectory following, merging, and driving in dense traffic. Lastly, it raises open questions and future challenges.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Daniel Omeiza, Helena Webb, Marina Jirotka, Lars Kunze
Summary: This paper provides a comprehensive survey of explainable autonomous driving, emphasizing the importance of transparency, accountability, and trust in autonomous vehicles. It argues that AVs should be able to explain their behavior, providing researchers with the necessary knowledge and framework.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Gueltoum Bendiab, Amina Hameurlaine, Georgios Germanos, Nicholas Kolokotronis, Stavros Shiaeles
Summary: The arrival of autonomous vehicles brings many benefits, but also security and privacy issues that could undermine these benefits. Combining Blockchain and AI can provide strong protection against malicious attacks. This paper explores the application of Blockchain and AI for securing AVs and suggests potential future directions for research in this field.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Review
Materials Science, Multidisciplinary
Yunchao Xie, Kianoosh Sattari, Chi Zhang, Jian Lin
Summary: The increasing demand for novel materials has led to the retrofitting of traditional research paradigms with artificial intelligence and automation. An autonomous experimental platform (AEP) has emerged as a research frontier that integrates data-driven algorithms and experimental automation for material development. This review provides insights into developing data-driven algorithms, recent progress in automated material synthesis, ML-enabled data analysis, and decision-making, and the challenges and opportunities in developing the next-generation AEP for autonomous laboratories.
PROGRESS IN MATERIALS SCIENCE
(2023)
Article
Computer Science, Hardware & Architecture
Moayad Aloqaily, Rasheed Hussain, Deena Khalaf, Dana Slehat, Alma Oracevic
Summary: Unmanned aerial vehicles (UAVs) and autonomous vehicle (AV) technologies complement each other by providing support and addressing each other's limitations at the service and application level. This article focuses on the role of futuristic technologies, such as blockchain and artificial intelligence, in securing critical environments and discusses the challenges and opportunities for research and development.
IEEE CONSUMER ELECTRONICS MAGAZINE
(2022)
Article
Chemistry, Multidisciplinary
Justin Nakama, Ricky Parada, Joao P. Matos-Carvalho, Fabio Azevedo, Dario Pedro, Luis Campos
Summary: This paper introduces a new testing platform that utilizes machine learning algorithms to generate realistic environments, based on satellite images and providing examples of real-world UAV deployment.
APPLIED SCIENCES-BASEL
(2021)
Article
Social Issues
Angel Swastik Duggal, Rajesh Singh, Anita Gehlot, Lovi Raj Gupta, Sheik Vaseem Akram, Chander Prakash, Sunpreet Singh, Raman Kumar
Summary: This study highlights the importance of modernization in road-based technologies for enhancing mobility and ensuring safer transportation. Recommendations include utilizing AI/ML to improve road environment, adopting electric vehicles, and integrating low power computing units in vehicular networks. By integrating modern technology into traditional transportation elements, the ecosystem surrounding road safety and mobility can be further enhanced.
TECHNOLOGY IN SOCIETY
(2021)
Article
Business
Jenny van Doorn, Edin Smailhodzic, Stefano Puntoni, Jia Li, Jan Hendrik Schumann, Jana Holthower
Summary: In the digital age, research on the impact of autonomous technology (AT) in organizational frontlines has focused either on the consumer or the worker. To fill this gap, we propose the Consumer-Autonomous Technology-Worker (CAW) framework, which considers the implications of consumer-worker-AT interactions. Based on interviews with workers and consumers in hospitality contexts, we suggest that consumer-worker relations are strengthened when AT augments rather than replaces the worker. Human leadership is crucial for the acceptance of AT by consumers and workers, while the anthropomorphism of AT is less critical when a human worker is present.
JOURNAL OF BUSINESS RESEARCH
(2023)
Article
Computer Science, Information Systems
Dario Rossi, Liang Zhang
Summary: This paper discusses the challenges and opportunities of Autonomous Driving Network (ADN) driven by AI technologies, and clarifies how AI can be fitted in the network architecture. It also mentions a roadmap to avoid issues in the large-scale deployment of AI technologies in networks.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2022)
Article
Engineering, Civil
Chen Sun, Ruihe Zhang, Yukun Lu, Yaodong Cui, Zejian Deng, Dongpu Cao, Amir Khajepour
Summary: This survey analyzes and reviews the current achievements of safety-related standards and definitions, sensory modeling, and metrics for perception tasks in autonomous driving applications. It also summarizes the new safety challenges laid out by the information exchange stage of the connected autonomous vehicle application and outlines the future research questions and directions.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
David Fernandez-Llorca, Emilia Gomez
Summary: We determine the maturity level of various requirements for AI in autonomous driving and highlight the main challenges that need to be tackled in the future to ensure the development of trustworthy automotive AI systems.
Article
Physics, Multidisciplinary
Oleg Illiashenko, Vyacheslav Kharchenko, Ievgen Babeshko, Herman Fesenko, Felicita Di Giandomenico
Summary: Introduced an entropy-oriented approach called security- or cybersecurity-informed safety (SIS or CSIS) for analyzing and evaluating the safety and dependability of autonomous transport systems. This approach extends the FMECA and IMECA techniques and introduces the new SISMECA technique. It suggests an ontology model and templates for SISMECA implementation.
Article
Chemistry, Multidisciplinary
Jacek Caban, Aleksander Nieoczym, Agnieszka Dudziak, Tomasz Krajka, Maria Stopkova
Summary: Transportation is rapidly developing with the emergence of electric and hybrid cars, as well as autonomous or semi-autonomous vehicles. The use of automated guided vehicles (AGV) for logistics and technical tasks, with the application of artificial intelligence (AI) and machine learning, is widely discussed. The IT connection of sensors receiving environmental signals plays a crucial role in the construction of autonomous vehicles.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Palak Dixit, Pronaya Bhattacharya, Sudeep Tanwar, Rajesh Gupta
Summary: The next wave of smart transportation is focused on designing renewable energy sources to fuel autonomous electric vehicles (AEVs), which can reduce carbon footprints and support green transportation. However, AEVs are vulnerable to security and privacy attacks, leading researchers to develop AI techniques for detecting and classifying malicious AEVs exhibiting anomalous behavior.
Article
Engineering, Aerospace
Anirudh Warrier, Saba Al-Rubaye, Gokhan Inalhan, Antonios Tsourdos
Summary: This research proposes a novel deep reinforcement learning algorithm powered by AI to address the interference challenge in integrating autonomous UAVs with 5G networks. The algorithm effectively mitigates interference through power control, leading to improved link performance.
Article
Computer Science, Artificial Intelligence
Andre Ippolito, Jorge Rady de Almeida Junior
JOURNAL OF INTELLIGENT INFORMATION SYSTEMS
(2020)
Article
Computer Science, Information Systems
David F. N. Oliveira, Lucio F. Vismari, Alexandre M. Nascimento, Jorge R. de Almeida Jr, Paulo S. Cugnasca, Joao B. Camargo Jr, Leandro Almeida, Rafael Gripp, Marcelo Neves
Summary: This paper explores the issue of interpretability in deep learning methods and introduces a new interpretability method called RXP. Experimental results demonstrate that RXP outperforms traditional methods in large-scale systems, showing potential for significant impact in supporting decision making.
Article
Engineering, Civil
Euclides Carlos Pinto Neto, Derick Moreira Baum, Jorge Rady de Almeida Jr, Joao Batista Camargo Jr, Paulo Sergio Cugnasca
Summary: The demand for optimized services in urban environments is increasing, leading to the proposal of Urban Air Mobility (UAM) concept to enhance urban transportation systems. However, there are many challenges that need to be faced to achieve safe and efficient operations in UAM. This research introduces a simulation platform, Trajectory-Based Urban Air Mobility Simulator (TUS), for trajectory evaluation in urban aerial environment and testing new UAM algorithms.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Review
Computer Science, Information Systems
Antonio V. Silva Neto, Joao B. B. Camargo Jr, Jorge R. R. Almeida Jr, Paulo S. S. Cugnasca
Summary: The objective of this research is to present the latest developments in the safety assurance of AI-based systems and provide guidelines for future work. A systematic literature review was conducted, including 5090 peer-reviewed references related to AI safety, with a focus on a subset of 329 references directly related to the safety assurance of AI-based systems. Since 2016, there has been significant progress in the safety assurance of AI-based systems, with five main approaches emerging: black-box testing, safety envelopes, fail-safe AI design, white-box analyses combined with explainable AI, and a safety assurance process throughout systems' lifecycles. This paper discusses each of these approaches, including their features, advantages, and disadvantages. Finally, guidelines for future research topics are presented, based on an analysis of the reviewed references and the authors' experience. Among the 15 research themes, these guidelines emphasize the need to further enhance guidelines for the safety assurance of AI-based systems, such as analyzing datasets from a safety perspective, designing explainable AI, setting and justifying AI hyperparameters, and assuring the safety of hardware-implemented AI-based systems.
Proceedings Paper
Computer Science, Interdisciplinary Applications
Felipe Desiglo Ferrare, Derick Moreira Baum, Jorge Rady de Almeida Junior, Joao Batista Camargo Junior, Paulo Sergio Cugnasca
Summary: Netlogo is a tool for creating Multi-Agent Simulations in various areas and scenarios, including the study of electric vertical take-off and landing aircraft and Urban Air Mobility concepts. Researchers are challenged with structuring airspace with specific air traffic rules while maintaining aviation safety levels, and simulation serves as an effective way to gather data and define parameters for this new system.
PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON SIMULATION AND MODELING METHODOLOGIES, TECHNOLOGIES AND APPLICATIONS (SIMULTECH)
(2021)
Article
Computer Science, Information Systems
Euclides Carlos Pinto Neto, Derick Moreira Baum, Jorge Rady De Almeida, Joao Batista Camargo, Paulo Sergio Cugnasca
Summary: In recent years, there has been an increase in the number of Unmanned Aircraft Systems (UAS) in segregated airspace, but integrating large UAS into the National Airspace System (NAS) presents safety challenges due to new ways of reaching unsafe states. A parallel swarm-based method has been proposed to optimize final aircraft arrival segment design, taking into account multiple Technology Maturity Levels (TML) of aircraft.
Article
Computer Science, Information Systems
Derick Moreira Baum, Euclides Carlos Pinto Neto, Jorge Rady De Almeida, Joao Batista Camargo, Paulo Sergio Cugnasca
Article
Engineering, Civil
Euclides Carlos Pinto Neto, Derick Moreira Baum, Jorge Rady de Almeida Jr, Joao Batista Camargo Jr, Paulo Sergio Cugnasca
Summary: The demand for optimized services in urban environments has been increasing, leading to challenges in ground transportation in big urban centers. The concept of Urban Air Mobility (UAM) aims to enhance urban transportation systems using manned and unmanned aerial vehicles, but faces numerous challenges in ensuring safe and efficient operations. However, new initiatives for UAM trajectory planning may be accelerated with the support of an automatic what-if platform for evaluating trajectory feasibility and efficiency.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)