An avionics full-duplex switched ethernet data network that includes multiple hosts, with each of the multiple hosts having at least one communication port and with an End System establishing communication protocol between the multiple hosts.

Avionics full-duplex switched ethernet network

Electrification turned over a new leaf in aviation by introducing new types of aerial vehicles along with new means of transportation. Addressing a plethora of use cases, drones are gaining attention in the industry and increasingly appear in the sky. Emerging concepts of flying taxi enable passengers to be transported over several tens of kilometers. Therefore, unmanned traffic management systems are under development to cope with the complexity of future airspace, thereby resulting in unprecedented communication needs. Moreover, the long-term increase in the number of commercial airplanes pushes the limits of voice-oriented communications, and future options such as single-pilot operations demand robust connectivity. In this survey, we provide a comprehensive review and vision for enabling the connectivity applications of aerial vehicles utilizing current and future communication technologies. We begin by categorizing the connectivity use cases per aerial vehicle and analyzing their connectivity requirements. By reviewing more than 500 related studies, we aim for a comprehensive approach to cover wireless communication technologies, and provide an overview of recent findings from the literature toward the possibilities and challenges of employing the wireless communication standards. After analyzing the proposed network architectures, we list the open-source testbed platforms to facilitate future investigations by researchers. This study helped us observe that while numerous works focused on cellular technologies to enable connectivity for aerial platforms, a single wireless technology is not sufficient to meet the stringent connectivity demands of the aerial use cases, especially for the piloting operations. We identified the need of further investigations on multi-technology heterogeneous network architectures to enable robust and real-time connectivity in the sky. Future works should consider suitable technology combinations to develop unified aerial networks that can meet the diverse quality of service demands of the aerial use cases.

A Survey of Wireless Networks for Future Aerial Communications (FACOM)

Artificial intelligence needs big data to develop reliable predictions. Therefore, storing and processing health data is essential for the new diagnostic and decisional technologies but, at the same time, represents a risk for privacy protection. This scoping review is aimed at underlying the medico-legal and ethical implications of the main artificial intelligence applications to healthcare, also focusing on the issues of the COVID-19 era. Starting from a summary of the United States (US) and European Union (EU) regulatory frameworks, the current medico-legal and ethical challenges are discussed in general terms before focusing on the specific issues regarding informed consent, medical malpractice/cognitive biases, automation and interconnectedness of medical devices, diagnostic algorithms and telemedicine. We aim at underlying that education of physicians on the management of this (new) kind of clinical risks can enhance compliance with regulations and avoid legal risks for the healthcare professionals and institutions.

Management of Medico-Legal Risks in Digital Health Era: A Scoping Review

In the last decade, a growing number of electronic devices have been designed to be deployed in safety-critical autonomous systems. Many application domains, such as autonomous vehicles, robots, nano-drones, are exploring artificial intelligence solutions to handle the increasing computation requirements. Besides, due to their safety-critical application scenarios, they are demanding for even more reliable and advanced systems. These requirements clearly entail a growing complexity in modern processors and System-on-a-Chip design, leading to new efforts in verification and testing phases. These new devices must be also compliant with emerging functional safety standards that regulate their usage during the entire lifetime. The main intent of this work is to improve the reliability of autonomous systems, providing a strategy to link the verification methodology with the testing one. Starting from an almost exhaustive verification set, it is possible to derive a different set of patterns intended for on-line testing. This achievement is gained by taking into account the constraints due to the final system application and the common requirements of the embedded devices used in autonomous systems. Experimental results are provided on an open-source RISC-V processor assembled on an autonomous nano-drone.

On-line Testing for Autonomous Systems driven by RISC-V Processor Design Verification

Architectures used in safety critical systems have to pass certain certification standards, which require sufficient proof that they will behave as expected Multi-core processors make this challenging by featuring complex interactions between the tasks they run A lot of these interactions are made without explicit instructions from the program designers Furthermore, they can have strong negative impacts on performance (and potentially affect correctness) One important such source of interactions is cache coherence, which speeds up operations in most cases, but can also lead to unexpected variations in execution time if not fully understood Architecture documentations often lack details on the implementation of cache coherence We thus propose a strategy to ascertain that the platform does indeed implement the cache coherence protocol its user believes it to We also apply this strategy to the NXP QorIQ T4240, resulting in the identification of a protocol (MESIF) other than the one this architecture’s documentation led us to believe it was using (MESI)

https://drops.dagstuhl.de/opus/volltexte/2020/12376/pdf/LIPIcs-ECRTS-2020-13.pdf/

On How to Identify Cache Coherence: Case of the NXP QorIQ T4240

Safety-critical autonomous systems are becoming more powerful and more integrated to enable higher-level functionality. Modern multi-core SOCs are often the computing backbone in such systems for which safety and associated certification tasks are one of the key challenges, which can become more costly and difficult to achieve. Hence, modeling and assessment of these systems can be a formidable task. In addition, Artificial Intelligence (AI) is already being deployed in safety critical autonomous systems and Machine Learning (ML) enables the achievement of tasks in a cost-effective way.Compliance to Soft Error Rate (SER) requirements is an important element to be successful in these markets. When considering SER performance for functional safety, we need to focus on accurately modeling vulnerability factors for transient analysis based on AI and Deep Learning workloads. We also need to consider the reliability implications due to long mission times leading to high utilization factors for autonomous transport. The reliability risks due to these new use cases also need to be comprehended for modeling and mitigation and would directly impact the safety analysis for these systems. Finally, the need for telemetry for reliability, including capabilities for anomaly detection and prognostics techniques to minimize field failures is of paramount importance.

AI and Reliability Trends in Safety-Critical Autonomous Systems on Ground and Air

Weight, energy consumption and performance are critical drivers in future mass-produced eVTOLs (electrically powered Vertical Take-Off and Landing aircraft) worldwide. The quest to rapidly integrate and certify modern COTS compute and communications technology will be a central goal of modern avionics OEMs combining new technologies, such as cloud-center integration and acceleration of AI, create the new functionality necessary for the Urban Air Mobility (UAM) revolution. The cost savings in COTS, to be fully recognized, will require a new perspective on how functionality is partitioned, how power-efficient and safe/secure performance is facilitated by multicore processors (MCP) and how the HW/SW certification processes can be streamlined to allow the industry to easily absorb the latest innovations. In this paper we describe some current and future trends that affect air traffic control systems and UAM avionics. We describe impact on Air Traffic Control (ATC), present new ATC and UAM avionics architectures, technology enablers in general and how UAM can profit from the latest technology advancements.

Chip-Level Considerations to Enable Dependability for eVTOL and Urban Air Mobility Systems

This paper encompasses three contributions by industry professionals and university researchers. The contributions describe different trends in automotive products, including both manufacturing test and run-time reliability strategies. The subjects considered in this session deal with critical factors, from optimizing the final test before shipment to market to in-field reliability during operative life.

Test, Reliability and Functional Safety Trends for Automotive System-on-Chip

Assessing the reliability of modern devices running CNN algorithms is a very difficult task. Actually, the complexity of the state-of-the-art devices makes exhaustive Fault Injection (FI) campaigns impractical and typically out of the computational capabilities. A possible solution consists of resorting to statistical FI campaigns that allow a reduction in the number of needed experiments by injecting only a carefully selected small part of it. Under specific hypothesis, statistical FIs guarantee an accurate picture of the problem, albeit selecting a reduced sample size. The main problems today are related to the choice of the sample size, the location of the faults, and the correct understanding of the statistical assumptions. The intent of this paper is twofold: first, we describe how to correctly specify statistical FIs for Convolutional Neural Networks; second, we propose a data analysis on the CNN parameters that drastically reduces the number of FIs needed to achieve statistically significant results without compromising the validity of the proposed method. The methodology is experimentally validated on two CNNs, ResNet-20 and MobileNetV2, and the results show that a statistical FI campaign on about 1.21% and 0.55% of the possible faults, provides very precise information of the CNN reliability. The statistical results have been confirmed by the exhaustive FI campaigns on the same cases of study.

Assessing Convolutional Neural Networks Reliability through Statistical Fault Injections

The railway market is changing quickly to enable optimizations for future efficiency and environmental improvements like automated operations, infrastructure utilization, advanced analytics, system-level optimized energy-efficient driving. Additionally, consolidation at different levels (operation centers, hardware virtualization, cloud compute usage) push cost efficiency. Increased system-level connectivity pushes the needs for reliable high-speed communication. In this paper, we present the trends in modern mainline railway and possible implications on safety, differentiate from associated improvements like advanced analytics, and show how these trends can be supported from an IT technology perspective with associated safety needs. We also present elements beneficial for automated transportation.

Jyotika Athavale

Papers

AI and Reliability Trends in Safety-Critical Autonomous Systems on Ground and Air

Chip-Level Considerations to Enable Dependability for eVTOL and Urban Air Mobility Systems

Test, Reliability and Functional Safety Trends for Automotive System-on-Chip

Assessing Convolutional Neural Networks Reliability through Statistical Fault Injections

Trends and Functional Safety Certification Strategies for Advanced Railway Automation Systems