Adaptive monitoring for autonomous vehicles using the HAFLoop architecture

Zavala, Edith; Franch, Xavier; Marco, Jordi; Berger, Christian

doi:10.1080/17517575.2020.1844305

Cited by 7 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a single vehicle can produce more than a terabyte of data per hour of operation, and it is not plausible to store the continuously generating large-scale INS data and output insightful indicators on the vehicle setting itself. It has been pointed out that static feedbacks are not able to respond to unanticipated driving situations (Zavala et al , 2021). In addition, a micro-computer on vehicle cannot provide enough computation and storage resources, which is not compatible with the requirement of a real-time indicator calculation and reporting, leading to the following questions: how can we manage such a torrent of data and where could we store and process INS data sets to extract the indicators for driving behaviour and road smoothness?…”

Section: Implementations and Discussionmentioning

confidence: 99%

Driving performance grading and analytics: learning internal indicators and external factors from multi-source data

Zhou

Zhao

et al. 2021

IMDS

View full text Add to dashboard Cite

PurposeThe purpose of this paper is to deal with the practical challenge faced by modern logistics enterprises to accurately evaluate driving performance with high computational efficiency under the disturbance of road smoothness and to identify significantly associated performance influence factors.Design/methodology/approachThe authors cooperate with a logistics server (G7) and establish a driving grading system by constructing real-time inertial navigation data-enabled indicators for both driving behaviour (times of aggressive speed change and times of lane change) and road smoothness (average speed and average vibration times of the vehicle body).FindingsThe developed driving grading system demonstrates highly accurate evaluations in practical use. Data analytics on the constructed indicators prove the significances of both driving behaviour heterogeneity and the road smoothness effect on objective driving grading. The methodologies are validated with real-life tests on different types of vehicles, and are confirmed to be quite effective in practical tests with 95% accuracy according to prior benchmarks. Data analytics based on the grading system validate the hypotheses of the driving fatigue effect, daily traffic periods impact and transition effect. In addition, the authors empirically distinguish the impact strength of external factors (driving time, rainfall and humidity, wind speed, and air quality) on driving performance.Practical implicationsThis study has good potential for providing objective driving grading as required by the modern logistics industry to improve transparent management efficiency with real-time vehicle data.Originality/valueThis study contributes to the existing research by comprehensively measuring both road smoothness and driving performance in the driving grading system in the modern logistics industry.

show abstract

Section: Implementations and Discussionmentioning

confidence: 99%

Driving performance grading and analytics: learning internal indicators and external factors from multi-source data

Zhou

Zhao

et al. 2021

IMDS

View full text Add to dashboard Cite

show abstract

“…Hence, software engineers do not only face today's challenges from (a) growing functional complexities motivated by the trend to include AI/ML-components to tackle an ODD's unstructuredness, (b) continuous pressure to embrace adaptability in software and system architectures (cf. Zavala et al, [4]) motivated by scalability expectations for large software stacks that shall exploit silicon-powered computation accelerators, and (c) traceable, data-driven validation and verification from code changes to explanations for unexpected behavioral patterns in a system's ODD. Software engineers who operate with these aforementioned growingly software and system architectures, as well as their underlying artifact transformation processes face knowingly and unknowingly design decision that may impact and constrain future design possibilities in the on-going society's digitalization transformation.…”

Section: Upcoming Challenges and Responsibilities Formentioning

confidence: 99%

“…Encyclopedia Britannica, https://www.britannica.com/topic/sovereignty 3 Cf. https://ec.europa.eu/newsroom/dae/document.cfm?doc_id=759844 Cf. https://choosealicense.com…”

mentioning

confidence: 99%

Digital Sovereignty and Software Engineering for the IoT-laden, AI/ML-driven Era

Berger¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Today's software engineering already needs to deal with challenges originating from the multidisciplinarity that is required to realize IoT products: Many variants consist of sensor/actuator-powered systems that already today use AI/ML systems to better cope with the unstructuredness of their intended operational design domain (ODD), while, at the same time, such systems need to be monitored, diagnosed, maintained, and evolved using cloud-powered dashboards and data analytics pipelines that process, aggregate, and analyze countless data points preferably in real-time. This position paper discusses selected aspects related to Digital Sovereignty from a software engineering's perspective for the IoT-laden, AI/ML-driven era: While we can undeniably expect more and more benefits from such solutions, a specific light shall be shed in particular on challenges and responsibilities at designand operation-time that, at minimum, prepare for and enable or, even better, preserve and extend digital sovereignty from a software engineering's perspective.

show abstract

“… three deliverables of the SUPERSEDE H2020 European project [23]- [25],  a report of the SALI Swedish project (openresearch@astazero program) [26],  the tutorials and poster abstracts session of the BSR winter school -Big Software on the Run: Where Software meets Data [27],…”

Section: Contributions Of Rq3mentioning

confidence: 99%

“…The first ideas were published in the applicant's Master thesis [21] and a demo tool session of the 23 rd IEEE International Requirements Engineering Conference (CORE2018: A) [22]. Later, during the development of this thesis, contributions were published in: three deliverables of the SUPERSEDE H2020 European project [23]- [25], a report of the SALI Swedish project (openresearch@astazero program) [26], the tutorials and poster abstracts session of the BSR winter school -Big Software on the Run: Where Software meets Data [27], the PhD symposium of the International Conference on Service-Oriented Computing (CORE2018: A) [28] and the SCI-indexed journal Expert Systems with Applications (I.F.2017: 3.768) [7] 4…”

Section: How To Supportmentioning

confidence: 99%

Towards adaptative monitoring for self-adaptative systems

Zavala Rodríguez

View full text Add to dashboard Cite

Nowadays, most of the approaches supporting self-adaptive systems (SASs) rely on static feedback control loops, for managing their adaptation process. One of the most popular feedback loops is the MAPE-K loop. In this loop, the Monitor element plays a crucial role since the quality of the monitoring data (e.g., timeliness, freshness, accuracy, availability, etc.) affects directly the performance of the rest of the elements of the loop, and in consequence the quality of the resulting adaptation decisions. Assuming static feedback loops implies that the structure and behavior of the elements of the loop should be determined at design-time and cannot change at runtime, i.e., in the case of the Monitor, systems’ owners should know everything to be monitored at design time. If that the case, current self-adaptive systems would not be able to react to unpredictable runtime events such as faults or changing requirements. Motivated by this fact, in this thesis, we address the automatic runtime adaptation of SASs’ feedback control loops, particularly the Monitor element, in order to respond to changes in the systems, the environment and the elements of the loop themselves. Concretely, we have presented HAFLoop, an architectural proposal for supporting the adaptation of the MAPE-K loop at runtime. We have identified open research challenges affecting SASs’ and feedback loops’ adaptation and analyzed whether and how existing approaches address those challenges. We have also studied how state-of-the-art approaches support adaptive monitoring in current monitoring systems. Although great efforts have been done for supporting the adaptation of feedback loops in SASs’, none of the state-of-the-art solutions satisfactorily addresses all the open research challenges. HAFLoop, in conjunction with its implementation in the form of a framework named HAFLoop4J, is a generic and reusable solution that easies the design and development of adaptive feedback loops, from higher to lower levels. Our solution enables loops to support different types of adaptation in a variety of settings. HAFLoop has been evaluated in different scenarios and in both simulation and real environments. The evaluations of HAFLoop have been conducted in the domain of smart vehicles with very promising results. Actualmente, la mayoría de las soluciones que soportan sistemas de software autoadaptativos (SASs) se basan en bucles estáticos de control para administrar el proceso de adaptación. Uno de los bucles más populares es el bucle MAPE-K. En este bucle, el elemento Monitor desempeña un papel crucial ya que la calidad de los datos monitoreados (por ejemplo, su precisión, su disponibilidad, etc.) afecta directamente el rendimiento del resto de los elementos del bucle, y en consecuencia el de la calidad de las decisiones de adaptación resultantes. Asumir que los bucles de los SASs son estáticos, implica que la estructura y comportamiento de sus elementos deben determinarse al momento de su diseño y no pueden cambiarse en tiempo de ejecución. Por ejemplo, en el caso del Monitor, todo lo que se ha de monitorear en tiempo de ejecución y como se ha de obtener, debe conocerse al momento de diseñar el sistema. En este escenario, los sistemas autoadaptativos actuales no serían capaces de reaccionar ante eventos impredecibles en tiempo de ejecución, tales como fallas de sensores o cambios en los requisitos. Motivados por este hecho, en esta tesis, abordamos la adaptación automática en tiempo de ejecución de los bucles de control para los SASs, en particular la adaptación del elemento Monitor, con el fin de responder a cambios en los sistemas, su entorno y cambios en los propios elementos del bucle. Concretamente, presentamos HAFLoop, una propuesta arquitectónica para la adaptación del bucle MAPE-K en tiempo de ejecución. Hemos identificado desafíos de investigación que afectan actualmente la adaptación de los SASs así como de los bucles que conducen su adaptación, también hemos analizado si las propuestas existentes los abordan y como lo hacen. Hemos estudiado también cómo las propuestas actuales abordan el monitoreo adaptativo en los sistemas de monitorización existentes. Si bien se han realizado grandes esfuerzos para habilitar la adaptación de bucles SASs, ninguna de las propuestas que evaluamos aborda satisfactoriamente todos los desafíos que aún afectan este campo de estudio. HAFLoop, junto con su implementación en forma de un marco denominado HAFLoop4J, es una solución genérica y reutilizable que facilita el diseño y el desarrollo de bucles adaptativos para SASs, desde los niveles técnicos más altos, como el diseño de componentes genéricos, a los más bajos, como la implementación de componentes específicos para una aplicación en particular. Nuestra solución permite que los bucles se adapten de diferentes maneras y en una variedad de configuraciones distintas. HAFLoop se ha evaluado en diferentes escenarios y en entornos de simulación así como reales. Las evaluaciones de HAFLoop se han realizado en el dominio de vehículos inteligentes con resultados muy prometedores.

show abstract

Adaptive monitoring for autonomous vehicles using the HAFLoop architecture

Cited by 7 publications

References 35 publications

Driving performance grading and analytics: learning internal indicators and external factors from multi-source data

Driving performance grading and analytics: learning internal indicators and external factors from multi-source data

Digital Sovereignty and Software Engineering for the IoT-laden, AI/ML-driven Era

Towards adaptative monitoring for self-adaptative systems

Contact Info

Product

Resources

About