Exploration of Explainable AI in Context of Human-Machine Interface for the Assistive Driving System

Chaczko, Zenon; Kulbacki, Marek; Gudzbeler, Grzegorz; Alsawwaf, Mohammad; Thai-Chyzhykau, Ilya; Wajs-Chaczko, Peter

doi:10.1007/978-3-030-42058-1_42

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The design of human-centered AI should also be adaptive to CPS applications of different functions, features, requirements, and constraints. For example, it is essential for a driving-assistive system to be explainable to facilitate trust and minimize a driver's decision time to take proper action [6]. Meanwhile, an AI-enabled HMI in the control room of a power grid should feature the following functions [35]:…”

Section: Incorporating Ai Stack Into Mission Stackmentioning

confidence: 99%

An Introduction of System-Scientific Approaches to Cognitive Security

Huang¹,

Zhu²

2023

Preprint

View full text Add to dashboard Cite

Human cognitive capacities and the needs of human-centric solutions for "Industry 5.0" make humans an indispensable component in Cyber-Physical Systems (CPSs), referred to as Human-Cyber-Physical Systems (HCPSs), where AI-powered technologies are incorporated to assist and augment humans. The close integration between humans and technologies in Section 1.1 and cognitive attacks in Section 1.2.4 poses emerging security challenges, where attacks can exploit vulnerabilities of human cognitive processes, affect their behaviors, and ultimately damage the HCPS.Defending HCPSs against cognitive attacks requires a new security paradigm, which we refer to as "cognitive security" in Section 1.2.5. The vulnerabilities of human cognitive systems and the associated methods of exploitation distinguish cognitive security from "cognitive reliability" and give rise to a distinctive CIA triad, as shown in Sections 1.2.5.1 and 1.2.5.2, respectively. Section 1.2.5.3 introduces cognitive and technical defense methods that deter the kill chain of cognitive attacks and achieve cognitive security. System scientific perspectives in Section 1.3 offer a promising direction to address the new challenges of cognitive security by developing quantitative, modular, multi-scale, and transferable solutions. Fig. 1.1 illustrates the structure of Chapter 1.

show abstract

Section: Incorporating Ai Stack Into Mission Stackmentioning

confidence: 99%

An Introduction of System-Scientific Approaches to Cognitive Security

Huang¹,

Zhu²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, Schoner,¨ 2018 showed that simulation supports testing the behavior of autonomous vehicles in a variety of scenarios, environments, system set-ups and driver profiles and, simultaneously, constitutes a vital part of the development and testing of autonomous driving software [32]. Chaczko et al, 2020 presented in their article research on a system assisting a driver in an autonomous vehicle [24]. The task of the system is to prevent situations and scenarios which are unpredictable at the stage of building the embedded AI system from appearing, and to inform the driver about such events (explain such situations) so that the driver could initiate relevant actions to avoid a collision or an accident [23].…”

Section: Is It Safementioning

confidence: 99%

Is it safe to drive a vehicle with a steering equipment positioned on the same side as the direction of the traffic – driving simulation experiments

Gudzbeler¹,

Gromek²,

Urban³

et al. 2023

JoMS

View full text Add to dashboard Cite

Polish road traffic law was amended to reflect the EU legislation concerning the LHT vehicle registration in the RHT member states without repositioning the steering equipment, following complaints by Polish citizens to the EC and the subsequent ECJ judgment. This research was conducted to analyze the implications on the road safety when driving LHT and RHT vehicles in RHT. For the purposes of the study, the main research question was defined: Does driving an LHT vehicle adapted to RHT reduce the level of safety of the driver and other road users. Method: The experiment used a vehicle driving simulator. Research sample was selected by means of a survey

show abstract

“…The literature contains most of the works from the medical and health care domains [28][29][30][31][32][33][34]. However, there are review articles available in the literature from the domains of industry [35], software engineering [36], automotive [37], etc.…”

Section: Related Studiesmentioning

confidence: 99%

A Systematic Review of Explainable Artificial Intelligence in Terms of Different Application Domains and Tasks

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence (AI) and machine learning (ML) have recently been radically improved and are now being employed in almost every application domain to develop automated or semi-automated systems. To facilitate greater human acceptability of these systems, explainable artificial intelligence (XAI) has experienced significant growth over the last couple of years with the development of highly accurate models but with a paucity of explainability and interpretability. The literature shows evidence from numerous studies on the philosophy and methodologies of XAI. Nonetheless, there is an evident scarcity of secondary studies in connection with the application domains and tasks, let alone review studies following prescribed guidelines, that can enable researchers’ understanding of the current trends in XAI, which could lead to future research for domain- and application-specific method development. Therefore, this paper presents a systematic literature review (SLR) on the recent developments of XAI methods and evaluation metrics concerning different application domains and tasks. This study considers 137 articles published in recent years and identified through the prominent bibliographic databases. This systematic synthesis of research articles resulted in several analytical findings: XAI methods are mostly developed for safety-critical domains worldwide, deep learning and ensemble models are being exploited more than other types of AI/ML models, visual explanations are more acceptable to end-users and robust evaluation metrics are being developed to assess the quality of explanations. Research studies have been performed on the addition of explanations to widely used AI/ML models for expert users. However, more attention is required to generate explanations for general users from sensitive domains such as finance and the judicial system.

show abstract

Exploration of Explainable AI in Context of Human-Machine Interface for the Assistive Driving System

Cited by 9 publications

References 12 publications

An Introduction of System-Scientific Approaches to Cognitive Security

An Introduction of System-Scientific Approaches to Cognitive Security

Is it safe to drive a vehicle with a steering equipment positioned on the same side as the direction of the traffic – driving simulation experiments

A Systematic Review of Explainable Artificial Intelligence in Terms of Different Application Domains and Tasks

Contact Info

Product

Resources

About