2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)最新文献

{"title":"Unmanned Systems Health Analysis through Evidential Reasoning Networks","authors":"J. Dunham, Eric N. Johnson, E. Feron, Brian J. German","doi":"10.1109/DASC50938.2020.9256593","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256593","url":null,"abstract":"Evidential reasoning, developed by Glenn Shafer and Arthur Dempster in the 1960s and 1970s, has been extensively applied to risk analysis, sensor fusion, and system failure analysis. Use in real-time systems for health analysis has been more limited due to computational complexity requiring less either comprehensive analysis or significant computing power. Evidential reasoning networks, also known as valuation networks, reduce computational requirements by eliminating hypothesis combinations which are infeasible. Recent extensions enable these networks to learn the relationships between nodes based on evidence inputs, enabling these networks to adapt without the need of subject matter experts defining each relationship update. This system is applied to unmanned system health analysis, demonstrating the capability to run complex belief analyses in real-time on autopilot systems with low computational power using the GUST autopilot system developed at the Georgia Institute of Technology. Comparisons are made between the evidential combination approach and more traditional contingency management that uses time delays and worst-case scenario assumptions for contingency responses. Simulation training is used as a surrogate for high volumes of flight testing, and operational results are primarily tested through GUST simulation of a representative mission. Results show that evidential reasoning networks are an effective approach to real-time health analysis of unmanned systems, using the novel update rules to understand relationships based on operational outcomes. Flight demonstration is included to show the capability to run this system in real operations. This work has implications on integration of unmanned systems into the national airspace as well as on Urban Air Mobility. Results from the network are explainable, enabling human oversight of operational decisions. Real-time implementation enables integration into avionics systems. Further, the data-driven approach to learning relationships enables this system to adapt as information concerning unmanned systems steadily changes.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131763039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-Power ADS-B for GA Operating in Low Altitude Airspace","authors":"Marketa Palenska, S. L. Brázdilová, P. Casek, Lubos Korenciak","doi":"10.1109/DASC50938.2020.9256553","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256553","url":null,"abstract":"Complete and reliable awareness about surrounding traffic is a key pre-requisite of safe operations in any airspace. Performance of such traffic surveillance functions is usually much higher when directly supported by on-board systems of the monitored aircraft, and the term cooperative surveillance is then used for such capability. Nevertheless, operational benefits associated with the latter are directly depending on the amount of fleet equipped with such systems. This paper describes the situation associated with the latest deployment of Automatic Dependent Surveillance - Broadcast (ADS-B) and discusses the possible ways how to extend the ratio of aircraft equipped with such capability in Europe (beyond the current mandate taking effect after June 2020) while mitigating the risk of spectrum congestion, namely considering 1090 MHz frequency.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131233670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Human-system interaction issues and proposed solutions to promote successful maturation of the UTM system","authors":"Cynthia Wolter, Lynne Martin, Kimberly K. Jobe","doi":"10.1109/DASC50938.2020.9256805","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256805","url":null,"abstract":"Over five years, NASA, together with partnering organizations, has been developing and successfully demonstrating the maturing capabilities of the Unmanned Aircraft Systems (UAS) Traffic Management (UTM) system and its ability to support communication and coordination among small UAS operations through a series of flight tests. During these flight tests, human-system interaction (HSI) elements were also explored in order to identify the barriers to implementation as human operators transitionally fulfill roles that will be ultimately tasked to future automation. Throughout the tests, similar issues were regularly documented and are expected to persist if not formally addressed by consistent procedures, intuitive design, or regulation. Documented here, along with suggested mitigations, are the most frequently noted HSI items, which include operator training, data standardization, and information quality.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127243833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Average Exploration in Multi-Agent Reinforcement Learning","authors":"Garrett Hall, K. Holladay","doi":"10.1109/DASC50938.2020.9256721","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256721","url":null,"abstract":"The objective of this research project was to improve Multi-Agent Reinforcement Learning performance in the StarCraft II environment with respect to faster training times, greater stability, and higher win ratios by 1) creating an adaptive action selector we call Adaptive Average Exploration, 2) using experiences previously learned by a neural network via Transfer Learning, and 3) updating the network simultaneously with its random action selector epsilon. We describe how agents interact with the StarCraft II environment and the QMIX algorithm used to test our approaches. We compare our AAE action selection approach with the default epsilon greedy method used by QMIX. These approaches are used to train Transfer Learning (TL) agents under a variety of test cases. We evaluate our TL agents using a predefined set of metrics. Finally, we demonstrate the effects of updating the neural networks and epsilon together more frequently on network performance.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126809327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of Onboard System State and Path Awareness Technologies During Transport Operations","authors":"T. Etherington, L. Kramer, Renee C. Lake, T. Schnell, R. Mumaw, L. Sherry, Matthew B. Cover, Tom Evans","doi":"10.1109/DASC50938.2020.9256588","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256588","url":null,"abstract":"Even after decades of continuous use, automation surprise and mode confusion are still prevalent in commercial airline operations. Without increased awareness of the aircraft and automation future state, crews have difficulty monitoring and managing flight path leading to clearance violations and the potential for loss of separation. A pilot-in-the-loop flight simulation study was conducted at NASA Langley Research Center to evaluate a path awareness display technology concept called “Automation Does What?” and an automation configuration display technology concept called “Automation Function Configuration Display”. The two technologies were evaluated and contrasted with a current state-of-the-art flight deck modeled from the Boeing B-787 using guided discussion and pilot comments. Objective and subjective data were collected from aircraft parameters, questionnaires, audio/video recordings, head/eye tracking data, and subject matter expert observations.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123746306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Verifying Autonomous Air Traffic Algorithms in the Presence of Sensor Error and Flight Perturbations","authors":"A. L. White","doi":"10.1109/DASC50938.2020.9256610","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256610","url":null,"abstract":"We offer a method to verify algorithms for air traffic control in the presence of sensor errors and flight perturbations. Since errors and perturbations are described by stochastic processes, verification by analytical methods is difficult. We turn to Monte Carlo simulation, but there are two major obstacles. Since air traffic algorithms are safety-critical, the algorithm must be established at a very high confidence level which requires an enormous number of trials. Another is that a simulation attempts to show that an algorithm correctly handles a hazard that might appear, but there is a lack of information about the frequency of occurrence of hazards in the airspace. This paper offers a solution to these and other obstacles. It recognizes there may be a number of algorithms that address different hazards, and the results of the different simulations must be combined to satisfy a global reliability requirement at a high confidence level. To demonstrate the feasibility of the approach, we apply it to an example, an initial effort in collision avoidance.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126716655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Challenges in Using Neural Networks in Safety-Critical Applications","authors":"H. Forsberg, J. Lindén, J. Hjorth, T. Manefjord, M. Daneshtalab","doi":"10.1109/DASC50938.2020.9256519","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256519","url":null,"abstract":"In this paper, we discuss challenges when using neural networks (NNs) in safety-critical applications. We address the challenges one by one, with aviation safety in mind. We then introduce a possible implementation to overcome the challenges. Only a small portion of the solution has been implemented physically and much work is considered as future work. Our current understanding is that a real implementation in a safety-critical system would be extremely difficult. Firstly, to design the intended function of the NN, and secondly, designing monitors needed to achieve a deterministic and fail-safe behavior of the system. We conclude that only the most valuable implementations of NNs should be considered as meaningful to implement in safety-critical systems.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114898817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Value of Design Assurance in Acquisition - Improvements in Cost, Schedule and Quality","authors":"U. Ferrell, Calvin Miles","doi":"10.1109/DASC50938.2020.9256675","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256675","url":null,"abstract":"For quite some time, military and civil aviation acquisition communities have been facing challenges and opportunities in addressing cost, schedule, and quality of safety critical systems. Regulatory guidance and the contract management processes are not adequately nimble to keep up with each other and with the pace of complexity in systems. Aviation is a connected system of systems with shared responsibilities on the ground, space, and airplanes. Even though there are common standards in use for the systems of systems in aviation, there is an uneven focus on how these standards are applied because some systems are put into service using acquisition programs. Acquisition programs generally have different sets of controls with responsibilities for cost, schedule, and system performance. These programs usually do not use safety assurance like the Aircraft Certification Holders although there is a safety budget that is shared by these interconnected systems. To create a more efficient and safer system, the safety oversight in acquisition programs must adapt collaborative risk-based practices in line with the Safety Management System (SMS) that is promoted by the International Civil Aviation Organization (ICAO) and the aviation regulatory authorities throughout the world including the Federal Aviation Administration (FAA). Since the 1935 Cutting Air Crash, the aviation community has recognized that the safety assurance practices used to certify the design of aircraft also need to be used to assure the safety of navigational aids since the aircraft flight safety depends upon Navigational Aid (NAVAID) design and operations. NAVAID technology has evolved from Four Course Radio Ranges and Light Beacons to Instrument Landing Systems (ILSs) and VHF Omnirange (VOR) Distance Measuring Equipment (DME), Tactical Air Navigation (TACAN), and now, Global Positioning System (GPS) augmentations. Likewise, the design techniques for safety have evolved, from failsafe designs implemented in tubes then transistors and TTL logic to the assured software and complex hardware designs of today. Such design assurance practices for software (RTCA/DO-278A) or complex electronic hardware (RTCA/DO-254) have been used in conjunction with the system safety assurance standards SAE ARP 4754A and SAE ARP 4761 on FAA navigation acquisition programs since the standards were first developed. The practices have proven to be useful for extracting early indicators for technical, cost, and schedule risks. Once risk indicators are noted, risk mitigation decisions can be taken, minimizing disruption to the project since the key is to extract early indicators and take prompt actions which are less severe and less drastic than if the risk is allowed to persist until a later stage in the project. Although, acquisition contractors strive to increase maturity in compliance activities, these efforts appear to be ad hoc from an external perspective and are not adequately standardized to be used as m","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115009137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Why CPM is not CPM - Enabling Standardized Safety Mechanisms on Off-the-shelf IMA Modules","authors":"Julian Schoepf, Bastian Luettig, B. Annighoefer, R. Reichel","doi":"10.1109/DASC50938.2020.9256489","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256489","url":null,"abstract":"This paper describes the implementation of standardized mechanisms for safety-critical applications (Flexible-Avionics-Platform) on a state-of-the-art Integrated Modular Avionics (IMA) platform. The major contribution is the virtual promotion of two IMA simplex Core Processing Modules (CPM) to a high-integrity unit by application-level synchronization and cross-lane communication via CAN bus. In order to incorporate Remote Data Concentrators (RDC), the CPMs need to perform additional services for sensor management while maintaining robustness against failures from other components. Automatic artifact generation from an abstract model to loadable units is implemented for all modules within the platform. Verification is finally performed using real IMA hardware.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125351809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assured Integration of Machine Learning-based Autonomy on Aviation Platforms","authors":"Erfan Asaadi, S. Beland, Alexander Chen, E. Denney, D. Margineantu, M. Moser, Ganesh J. Pai, J. Paunicka, D. Stuart, Huafeng Yu","doi":"10.1109/DASC50938.2020.9256475","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256475","url":null,"abstract":"Dynamic assurance cases (DACs) are a novel concept for the provision of assurance—both during development and, subsequently, continuously in operation—that can be usefully applied to machine learning (ML)-based autonomous systems. We describe the application of a DAC for dependability assurance of an aviation system that integrates ML-based perception to provide an autonomous taxiing capability. Specifically, we present how we: i) formulate and capture risk-based safety and performance objectives, ii) model architectural mechanisms for risk reduction, iii) record the rationale that justifies relying upon autonomy, itself underpinned by heterogeneous items of verification and validation evidence, and iv) develop and integrate a computable notion of confidence that enables a run-time risk assessment and, in turn, dynamic assurance. We also describe our evaluation efforts, currently based on a hardware-in-the-loop simulator surrogate of an airworthy flight platform.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126172968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}