Machine learning has made rapid advances in safety-critical applications, such as traffic control, finance, and healthcare. With the criticality of decisions they support potential consequences following their recommendations, it also became critical to provide users with explanations interpret machine models general, black-box particular. However, despite agreement on explainability a necessity, there is little evidence how recent eXplainable Artificial Intelligence literature (XAI) can be...

Abstract Human-AI collaborative decision-making tools are being increasingly applied in critical domains such as healthcare. However, these often seen closed and intransparent for human decision-makers. An essential requirement their success is the ability to provide explanations about themselves that understandable meaningful users. While generally have positive connotations, studies showed assumption behind users interacting engaging with could introduce trust calibration errors...

Formal Modelling is often used as part of the design and testing process software development to ensure that components operate within suitable bounds even in unexpected circumstances. We conducted a user study evaluation predictive formal modelling (PFM) at runtime human-swarm mission determine benefit on performance interaction. 180 participants were recruited perform role aerial swarm operators delivering parcels target locations simulation environment. The PFM model was integrated into...

The increased adoption of collaborative human-artificial intelligence decision-making tools triggered a need to explain recommendations for safe and effective collaboration. We explore how users interact with explanations why trust-calibration errors occur, taking clinical decision-support systems as case study.

Recent advancements in machine learning have spurred an increased integration of AI critical sectors such as healthcare and criminal justice. The ethical legal concerns surrounding fully autonomous highlight the importance combining human oversight with to elevate decision-making quality. However, trust calibration errors human-AI collaboration, encompassing instances over-trust or under-trust recommendations, pose challenges overall performance. Addressing design process is essential,...

Abstract Autonomous vehicles (AV) offer promising benefits to society in terms of safety, environmental impact and increased mobility. However, acute challenges persist with any novel technology, inlcuding the perceived risks trust underlying public acceptance. While research examining current state AV perceptions future related both societal individual barriers risk is emerging, it highly fragmented across disciplines. To address this gap, by using Web Science database, our study undertakes...

Explainability has become an essential requirement for safe and effective collaborative Human-AI environments., especially when generating recommendations through black-box modality. One goal of eXplainable AI (XAI) is to help humans calibrate their trust while working with intelligent systems., i.e., avoid situations where human decision-makers over-trust the it incorrect., or under-trust correct. XAI., in this context., aims understand reasoning decide whether follow reject its...

Autonomous vehicles (AVs) have made significant progress towards large-scale deployment, offering numerous advantages to society. These benefits include enhanced comfort, safety, efficient utilization of resources (such as energy and land), environmental protection. Moreover, the potential positive impact AVs on people's health, such reducing stress during traffic, is often emphasised. Research suggests that driver responsibilities allowing leisure activities like reading or entertainment...

Despite the advantages of having robot swarms, human supervision is required for real-world applications. The performance human-swarm system depends on several factors including data availability operators. In this paper, we study aspect interaction and investigate how access to high-quality can affect system— number tasks completed trust level in operation. We designed an experiment where a operator tasked operate swarm identify casualties area within given time period. One group operators...

Formal Modelling is often used as part of the design and testing process software development to ensure that components operate within suitable bounds even in unexpected circumstances. In this paper, we use predictive formal modelling (PFM) at runtime a human-swarm mission show integration can be improve performance teams. We recruited 60 participants simulated aerial swarm deliver parcels target locations. PFM condition, operators were informed estimated completion times given number drones...

Background: Interest in eHealth has grown since the Coronavirus (COVID-19) pandemic. Use of internet-based technologies (IBTs) and artificial intelligence (AI) potential to transform delivery mental healthcare services, however, trust remains a pivotal factor public acceptance adoption these systems. Aims: We investigated attitudes behaviours towards with focus on health wellbeing provision, general population individuals experience serious illness. Our investigation was underpinned by...

Recent advances in artificial intelligence, specifically machine learning, contributed positively to enhancing the autonomous systems industry, along with introducing social, technical, legal and ethical challenges make them trustworthy. Although Trustworthy Autonomous Systems (TAS) is an established growing research direction that has been discussed multiple disciplines, e.g., Artificial Intelligence, Human-Computer Interaction, Law, Psychology. The impact of TAS on education curricula...

<p class="first" id="d171096e98">The ubiquity of information and communication technology contributed positively in enhancing lives, mainly increasing productivity economic growth, while their impact on life satisfaction wellbeing has been a hidden cost. Digital media shall empower users to maximise digital wellbeing, i.e. healthy regulated relationship with technology. Similar usability, people differ needs achieve maintain wellbeing. A design be inclusive how it helps increase reduce...

One of the challenges human-swarm interaction (HSI) is how to manage operator's workload. In order do this, we propose a novel neurofeedback technique for real-time measurement workload using functional near-infrared spectroscopy (fNIRS). The objective develop baseline in fNIRS and an interface that dynamically adapts proposed method consists device measure brain activity, process this through machine learning algorithm, pass it on HSI interface. By adapting interface, swarm could be reduced...