Representative Safety Assessment of Autonomous Vehicle for Public Transportation

Adedjouma, Morayo; Pedroza, Gabriel; Bannour, Boutheina

doi:10.1109/isorc.2018.00025

Cited by 8 publications

(16 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…derive test cases from safety and performance requirements [197]. The last paper focuses on the elicitation of safety requirements in automotive systems using a risk-based approach [1].…”

Section: Discussionmentioning

confidence: 99%

Software Engineering for AI-Based Systems: A Survey

Martínez-Fernández,

Bogner,

Franch

et al. 2021

Preprint

View full text Add to dashboard Cite

AI-based systems are software systems with functionalities enabled by at least one AI component (e.g., for image-and speechrecognition, and autonomous driving). AI-based systems are becoming pervasive in society due to advances in AI. However, there is limited synthesized knowledge on Software Engineering (SE) approaches for building, operating, and maintaining AI-based systems.To collect and analyze state-of-the-art knowledge about SE for AI-based systems, we conducted a systematic mapping study. We considered 248 studies published between January 2010 and March 2020. SE for AI-based systems is an emerging research area, where more than 2/3 of the studies have been published since 2018. The most studied properties of AI-based systems are dependability and safety. We identified multiple SE approaches for AI-based systems, which we classified according to the SWEBOK areas. Studies related to software testing and software quality are very prevalent, while areas like software maintenance seem neglected. Data-related issues are the most recurrent challenges. Our results are valuable for: researchers, to quickly understand the state of the art and learn which topics need more research; practitioners, to learn about the approaches and challenges that SE entails for AI-based systems; and, educators, to bridge the gap among SE and AI in their curricula. CCS Concepts: • Software and its engineering → Software creation and management; • Computing methodologies → Machine learning;

show abstract

“…derive test cases from safety and performance requirements [197]. The last paper focuses on the elicitation of safety requirements in automotive systems using a risk-based approach [1].…”

Section: Discussionmentioning

confidence: 99%

Software Engineering for AI-Based Systems: A Survey

Martínez-Fernández,

Bogner,

Franch

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Sophia uses Papyrus extension mechanisms to support safety and reliability analyses like HARA, FMEA, FTA. We evaluate the OGI method on an ongoing industry-academy experimentation of autonomous shuttles deployment on a sensitive site, as described in [12]. Due to lack of space, the evaluation only focus on selected method phases.…”

Section: Ogi Methods Tool Support and Evaluationmentioning

confidence: 99%

“…The evaluation of the hazardous scenario is conducted based upon our proposed safety assessment method. To do so, an existing hazard analysis of the shuttle [12] is considered which covers the phases a, b, c, d of the OGI cycle (see Figure 3). The concerning fault in the scenario is the non recognition of a person as a such.…”

Section: Ogi Methods Tool Support and Evaluationmentioning

confidence: 99%

“…Referred safety aspects are integrated into the OGI cycle (see Figure 3) as follows: a) Situations analysis. This activity corresponds to a typical operational situation analysis as in hazard analysis [12]. However, special attention is given to situations in which autonomous functions operate and are at stake.…”

Section: B Integration Of Safety Aspects Into the Ogi Cyclementioning

confidence: 99%

See 1 more Smart Citation

Safe-by-Design Development Method for Artificial Intelligent Based Systems

Pedroza¹,

Adedjouma²

2019

International Conferences on Software Engineering and Knowledge Engineering

Self Cite

View full text Add to dashboard Cite

Albeit Artificial Intelligent (AI) based systems are nowadays deployed in a variety of safety critical domains, current engineering methods and standards are barely applicable for their development and assurance. The lack of common criteria to assess safety levels as well as the dependency of certain development phases w.r.t. the chosen technology (e.g., machine learning modules) are among the identified drawbacks. In addition, the development of such engineering methods has been hampered by the emerging challenges in AI-based systems design mainly regarding autonomy, correctness and prevention of catastrophic risks. In this paper we propose an approach to conduct a safeby-design development process for AI based systems. The approach relies upon a method which benefits from a reference AI architecture and safety principles. This contribution helps to address safety concerns and to comprehend current AI architectures diversity and particularities.

show abstract

“…Meantime, the state-ofthe-art ADAS functionalities are usually Quality Management (QM) and subject to the driver control and responsibility. Wherefore, autonomous driving transfers this responsibility to complex ADAS multicore critical systems depending on the autonomy level that results in producing highly safety-critical functions with high-performance requirements, as they have been introduced in the literature [8, 13,14]. Moreover, traditional safety-critical mechanical features, such as antilock braking, have moved towards new autonomous driving solutions, such as the electronic stability program with the help of networked layered architecture systems.…”

Section: Figure 1 Multicore Architecture Block Diagrammentioning

confidence: 99%

ISO-26262 Compliant Safety-Critical Autonomous Driving Applications: Real-Time Interference-Aware Multicore Architectures

El-Bayoumi¹

2021

IJSSE

View full text Add to dashboard Cite

Over the decades, autonomous vehicles have been developed and qualified using variant single-core architectures. With the evolutionary trend of safety critical applications, innovative safety design methodologies have raised present requirements constraints and limitations to mitigate such design complexity deviations. The main objectives of this work are to investigate, evaluate and introduce an efficient safety-critical multi-cache multicore architecture, that is fully compliant with methods and principles of ISO 26262. Moreover, this paper presents new safety design choices applied to timing monitoring, temporal protection, runtime monitoring and services protection to overcome multicore processor challenges in runtime that eventually decay the worst case execution time and the interconnections (symmetric and asymmetric processors, critical timing, data coherency and synchronization predictability, core interconnects, etc.), as well as to tolerate real-time interference faults.

show abstract

Representative Safety Assessment of Autonomous Vehicle for Public Transportation

Cited by 8 publications

References 9 publications

Software Engineering for AI-Based Systems: A Survey

Software Engineering for AI-Based Systems: A Survey

Safe-by-Design Development Method for Artificial Intelligent Based Systems

ISO-26262 Compliant Safety-Critical Autonomous Driving Applications: Real-Time Interference-Aware Multicore Architectures

Contact Info

Product

Resources

About