No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
The IDEA of Us: An Identity-Aware Architecture for Autonomous Systems
Abstract
Autonomous systems, such as drones and rescue robots, are increasingly used during emergencies. They deliver services and provide situational awareness that facilitate emergency management and response. To do so, they need to interact and cooperate with humans in their environment. Human behaviour is uncertain and complex, so it can be difficult to reason about it formally. In this paper, we propose IDEA: an adaptive software architecture that enables cooperation between humans and autonomous systems, by leveraging in the social identity approach. This approach establishes that group membership drives human behaviour. Identity and group membership are crucial during emergencies, as they influence cooperation among survivors. IDEA systems infer the social identity of surrounding humans, thereby establishing their group membership. By reasoning about groups, we limit the number of cooperation strategies the system needs to explore. IDEA systems select a strategy from the equilibrium analysis of game-theoretic models, that represent interactions between group members and the IDEA system. We demonstrate our approach using a search-and-rescue scenario, in which an IDEA rescue robot optimises evacuation by collaborating with survivors. Using an empirically validated agent-based model, we show that the deployment of the IDEA system can reduce median evacuation time by .
ResearchGate has not been able to resolve any citations for this publication.
Autonomous systems, such as drones, are critical for emergency mitigation, management, and recovery. They provide situational awareness and deliver communication services which effectively guide emergency responders’ decision making. This combination of technology and people comprises a socio-technical system. Yet, focusing on the use of drone technology as a solely operational tool, underplays its potential to enhance coordination between the different agents involved in mass emergencies, both human and non-human. This paper proposes a new methodological approach that capitalizes on social identity principles to enable this coordination in an evacuation operation. In the proposed approach, an adaptive drone uses sensor data to infer the group membership of the survivors it encounters during the operation. A corpus of 200 interactions of survivors’ talk during real-life emergencies was computationally classified as being indicative of a shared identity or personal/no identity. This classification model, then, informed a game-theoretic model of human-robot interactions. Bayesian Nash Equilibrium analysis determined the predicted behavior for the human agent and the strategy that the drone needs to adopt to help with survivor evacuation. Using linguistic and synthetic data, we show that the identity-adaptive architecture outperformed two non-adaptive architectures in the number of successful evacuations. The identity-adaptive drone can infer which victims are likely to be helped by survivors and where help from emergency teams is needed. This facilitates effective coordination and adaptive performance. This study shows decision-making can be an emergent capacity that arises from the interactions of both human and non-human agents in a socio-technical system.
The human-machine teaming paradigm is increasingly widespread in critical domains, such as healthcare and domestic assistance. The paradigm goes beyond human-on-the-loop and human-in-the-loop systems by promoting tight teamwork between humans and autonomous machines that collaborate in the same physical space. These systems are expected to build a certain level of trust by enforcing dependability and exhibiting interpretable behavior. We present emerging results in this direction, with a novel framework aiming at achieving better trust in human-machine teaming leveraging formal analysis, as well as eXplainable AI. We illustrate our approach and the emerging results with an example from the healthcare domain.
Thinking and reasoning, long the academic province of philosophy, have emerged over the past century as core topics of empirical investigation and theoretical analysis in the modern fields of cognitive psychology, cognitive science, and cognitive neuroscience. Formerly seen as too complicated and amorphous to be included in early textbooks on the science of cognition, the study of thinking and reasoning has since taken off, branching off in a distinct direction from the field from which it originated. This comprehensive publication covers all the core topics of the field of thinking and reasoning. Written by the foremost experts from cognitive psychology, cognitive science, and cognitive neuroscience, individual articles summarize basic concepts and findings for a major topic, sketch its history, and give a sense of the directions in which research is currently heading. The authors provide introductions to foundational issues and methods of study in the field, as well as treatment of specific types of thinking and reasoning and their application in a broad range of fields including business, education, law, medicine, music, and science.
In emergency response scenarios, autonomous small Unmanned Aerial Systems (sUAS) must be configured and deployed quickly and safely to perform mission-specific tasks. In this paper, we present Drone Response, a Software Product Line for rapidly configuring and deploying a multi-role, multi-sUAS mission whilst guaranteeing a set of safety properties related to the sequencing of tasks within the mission. Individual sUAS behavior is governed by an onboard state machine, combined with coordination handlers which are configured dynamically within seconds of launch and ultimately determine the sUAS’ behaviors, transition decisions, and interactions with other sUAS, as well as human operators. The just-in-time manner in which missions are configured precludes robust upfront testing of all conceivable combinations of features – both within individual sUAS and across cohorts of collaborating ones. To ensure the absence of common types of configuration failures and to promote safe deployments, we check vital properties of the dynamically generated sUAS specifications and coordination handlers before sUAS are assigned their missions. We evaluate our approach in two ways. First, we perform validation tests to show that the end-to-end configuration process results in correctly executed missions, and second, we apply fault-based mutation testing to show that our safety checks successfully detect incorrect task sequences.
With the ever-increasing number of domains in which we encounter robots - be it in industry, airports, or the home - the opportunity to interact and collaborate with these grows. And while an abundance of Human-Robot Interaction (HRI) literature has investigated dyadic interaction, non-dyadic HRI research, i.e., more than one human and one robot, has just recently begun to receive increasing attention. In this dissertation, I investigate characteristics of non-dyadic Human-Robot Interaction and collaboration. Specifically, I investigate two research questions focusing on i) the identification of existing characteristics of non-dyadic Human-Robot Interaction research and ii) the influence robots have on non-dyadic collaborative efforts.
This dissertation's contribution is based on five research papers. Paper I presents an empirical investigation of existing research on non-dyadic HRI over the last 15 years. Paper II to IV present qualitative field studies in the domestic and industrial contexts. Lastly, Paper V presents a mixed-methods lab-based study investigating human group collaboration and identifies design considerations to improve non-dyadic human-robot collaboration. Based on these five papers, this dissertation presents two primary contributions.
Firstly, I identify characteristics of non-dyadic HRI through an investigation of 164 research papers. These characteristics include the ongoing paradigm shift from a dyadic focus towards a non-dyadic focus, three non-dyadic configurations within HRI (one-to-many, many-to-one, and many-to-many) and an imbalance emphasising research involving one human interacting with multiple digital artefacts (one-to-many), a classification framework for non-dyadic Human-Robot Interaction, as well as empirical evidence showing the focus of non-dyadic HRI research on simultaneous over sequential interaction.
Secondly, I present several ways in which robots influence collaboration during non-dyadic Human-Robot Interaction. I highlight how introducing robots in both the domestic and industrial contexts into non-dyadic settings can lead to a fragmentation of previously coherent tasks while only some of the sub-tasks are automated. Furthermore, I show how the robot's presence, as previously hypothesised---can lead to a spatial restructuring resulting in a positive change in interpersonal relationships amongst collaborators. Lastly, I argue for the robot's capacity to alter, remove, and create roles and responsibilities within the non-dyadic collaborative Human-Robot Interaction.
Future work includes the investigation of i) robots as pro-active collaborators, ii) increase of transparency during robot introduction to counter unintended negative side-effects, and iii) a reconsideration of what a collaborative robot and collaboration with robots means.
The COVID-19 pandemic is worsening loneliness for many older people through the challenges it poses in engaging with their social worlds. Digital technology has been offered as a potential aid, however, many popular digital tools have not been designed to address the needs of older adults during times of limited contact. We propose that the Social Identity Model of Identity Change (SIMIC) could be a foundation for digital loneliness interventions. While SIMIC is a well-established approach for maintaining wellbeing during life transitions, it has not been rigorously applied to digital interventions. There are known challenges to integrating psychological theory in the design of digital technology to enable efficacy, technology acceptance, and continued use. The interdisciplinary field of Human Computer Interaction has a history of drawing on models originating from psychology to improve the design of digital technology and to design technologies in an appropriate manner. Drawing on key lessons from this literature, we consolidate research and design guidelines for multidisciplinary research applying psychological theory such as SIMIC to digital social interventions for loneliness.
Going beyond dyadic (one-to-one) interaction has been increasingly explored in HRI. Yet we lack a comprehensive view on non-dyadic interaction research in HRI. To map out 15 years of works investigating non-dyadic interaction, and thereby identifying the trend of the field and future research areas, we performed a literature review containing all 164 publications (2006-2020) from the HRI conference investigating non-dyadic interaction. Our approach is inspired by the 4C framework, an interaction framework focusing on understanding and categorising different types of interaction between humans and digital artefacts. The 4C framework consists of eight interaction principles for multi-user/multi-artefact interaction categorised into four broader themes. We modified the 4C framework to increase applicability and relevance in the context of non-dyadic human-robot interaction. We identify an increasing tendency towards non-dyadic research (36% in 2020), as well as a focus on simultaneous studies (85% from 2006-2020) over sequential. We also articulate seven interaction principles utilised in non-dyadic HRI and provide specific examples. Last, based on our findings, we discuss several salient points of non-dyadic HRI, the applicability of the modified 4C framework to HRI and potential future topics of interest as well as open-questions for non-dyadic research.
Disasters often occur without warning and despite extensive preparation, disaster managers must take action to respond to changes critical resource allocations to support existing health-care facilities and emergency triages. A key challenge is to devise sound and verifiable resourcing plans within an evolving disaster scenario. Our main contribution is the development of a conceptual self-adaptive system featuring a monitor-analyse-plan-execute (MAPE) feedback loop to continually adapt resourcing within the disaster-affected region in response to changing usage and requirements. We illustrate the system’s use on a case study based on Auckland city (New Zealand). Uncertainty arising from partial knowledge of infrastructure conditions and outcomes of human participant’s actions are modelled and automatically analysed using formal verification techniques. The analysis inform plans for routing resources to where they are needed in the region. Our approach is shown to readily support multiple model and verification techniques applicable to a range of disaster scenarios.
How do people behave in the seconds after they become aware they have been caught up in a real-life transport emergency? This paper presents the first micro-behavioral, video-based analysis of the behavior of passengers during a small explosion and subsequent fire on a subway train. We analyzed the behavior of 40 passengers present in the same carriage as the explosion. We documented the first action of the passengers following the onset of the emergency and described evidence of pro- and anti-social behavior. Passengers’ first actions varied widely. Moreover, anti-social behavior was rare and displays of pro-sociality were more common. In a quantitative analysis, we examined spatial clustering of running behavior and patterns in passenger exit choices. We found both homogeneity and heterogeneity in the running behavior and exiting choices of passengers. We discuss the implications of these findings for the mass emergency literature and for evacuation modeling.
To improve communication during emergencies, this research introduces an agent-based modeling (ABM) method to test the effect of psychological emergency communication strategies on evacuation performance. We follow a generative social science approach in which agent-based simulations allow for testing different candidate solutions. Unlike traditional methods, such as laboratory experiments and field observations, ABM simulation allows high-risk and infrequent scenarios to be empirically examined before applying the lessons in the real world. This is essential, as emergency communication with diverse crowds can be challenging due to language barriers, conflicting social identities, different cultural mindsets, and crowd demographics. Improving emergency communication could therefore improve evacuations, reduce injuries, and ultimately save lives. We demonstrate this ABM method by determining the effectiveness of three communication strategies for different crowd compositions in transport terminals: (1) dynamic emergency exit floor lighting directing people to exits, (2) staff guiding people to exits with verbal and physical instructions, and (3) public announcements in English. The simulation results indicated that dynamic emergency exit floor lighting and staff guiding people to exits were only beneficial for high-density crowds and those unfamiliar with the environment. Furthermore, English public announcements actually slowed the evacuation for mainly English-speaking crowds, due to simultaneous egress causing congestion at exits, but improved evacuation speed in multicultural, multilingual crowds. Based on these results, we make recommendations about which communication strategies to apply in the real world to demonstrate the utility of this ABM simulation approach for risk assessment practice.
Search and rescue (SAR) operations can take significant advantage from supporting autonomous or teleoperated robots and multi-robot systems. These can aid in mapping and situational assessment, monitoring and surveillance, establishing communication networks, or searching for victims. This paper provides a review of multi-robot systems supporting SAR operations, with system-level considerations and focusing on the algorithmic perspectives for multi-robot coordination and perception. This is, to the best of our knowledge, the first survey paper to cover (i) heterogeneous SAR robots in different environments, (ii) active perception in multi-robot systems, while (iii) giving two complementary points of view from the multi-agent perception and control perspectives. We also discuss the most significant open research questions: shared autonomy, sim-to-real transferability of existing methods, awareness of victims' conditions, coordination and interoperability in heterogeneous multi-robot systems, and active perception. The different topics in the survey are put in the context of the different challenges and constraints that various types of robots (ground, aerial, surface, or underwater) encounter in different SAR environments (maritime, urban, wilderness, or other post-disaster scenarios). The objective of this survey is to serve as an entry point to the various aspects of multi-robot SAR systems to researchers in both the machine learning and control fields by giving a global overview of the main approaches being taken in the SAR robotics area.
Mass gatherings are routinely viewed as posing risks to physical health. However, social psychological research shows mass gathering participation can also bring benefits to psychological well-being. We describe how both sets of outcomes can be understood as arising from the distinctive forms of behavior that may be found when people—even strangers—come to define themselves and each other in terms of a shared social identity. We show that many of the risks and benefits of participation are products of group processes; that these different outcomes can have their roots in the same core processes; and that knowledge of these process provides a basis for health promotion interventions to mitigate the risks and maximize the benefits of participation. Throughout, we offer practical guidance as to how policy makers and practitioners should tailor such interventions. © 2020 The Authors. Social Issues and Policy Review published by Wiley Periodicals LLC on behalf of Society for the Psychological Study of Social Issues
Development of crowd evacuation systems is a challenge due to involvement of complex interrelated aspects, diversity of involved individuals and/or environment, and lack of direct evidence. Evacuation modeling and simulation is used to analyze various possible outcomes as different scenarios unfold, typically when the complexity of scenario is high. However, incorporation of different aspect categories in a unified modeling space is a challenge. In this paper, we addressed this challenge by combining individual, social and technological models of people during evacuation, while pivoting all these aspects on a common agent-based modeling framework and a grid-based hypothetical environment. By simulating these models, an insight into the effectiveness of several interesting evacuation scenarios is provided. Based on the simulation results, a couple of useful recommendations are also given. The most important recommendation is not to use potential field indicating the exits dynamics as an exit strategy particularly for a spatial complexity environment.
We explore a dataset of app developer reasoning to better understand the reasons that may inadvertently promote or demote app developers' prioritization of security. We identify a number of reasons: caring vs. fear of users, the impact of norms, and notions of 'otherness' and 'self' in terms of belonging to groups. Based on our preliminary ndings, we propose an interdisciplinary research agenda to explore the impact of social identity (a psychological theory) on developers' security rationales, and how this could be leveraged to guide developers towards making more secure choices.
Significance
We present a framework that integrates social psychology tools into controller design for autonomous vehicles. Our key insight utilizes Social Value Orientation (SVO), quantifying an agent’s degree of selfishness or altruism, which allows us to better predict driver behavior. We model interactions between human and autonomous agents with game theory and the principle of best response. Our unified algorithm estimates driver SVOs and incorporates their predicted trajectories into the autonomous vehicle’s control while respecting safety constraints. We study common-yet-difficult traffic scenarios: highway merging and unprotected left turns. Incorporating SVO reduces error in predictions by 25%, validated on 92 human driving merges. Furthermore, we find that merging drivers are more competitive than nonmerging drivers.
BACKGROUND Despite evidence linking rapid defibrillation to out-of-hospital cardiac arrest (OHCA) survival, bystander use of automatic external defibrillators (AEDs) remains low, due in part to AED placement and accessibility. AED-equipped drones may improve time-to-defibrillation, yet the benefits and costs are unknown.METHODS We designed drone deployment networks for the state of North Carolina using mathematical optimization models to select drone stations from existing infrastructure by specifying the number of stations and the targeted AED arrival time. Expected outcomes were evaluated over the drone's lifespan (4 years). We estimated the following parameters: proportion of OHCAs within a targeted AED delivery time, bystander utilization of AEDs, survival/neurological status, and incremental cost per quality-adjusted life year (QALY).RESULTS Statewide, 16,503 adults aged 18 or older were expected to experience OHCA with an attempted resuscitation over 4 years. Compared to no drone network, all proposed drone networks were expected to improve survival outcomes. For example, assuming 46% of OHCAs have bystanders willing to use an AED, a 500-drone network decreased the median time of defibrillator arrival from 7.7 to 2.7 minutes compared to no drone network. Expected survival rates doubled (24.5% versus 12.3%), resulting in an additional 30,267 QALYs ($858/incremental QALY). If just 4.5% of OHCAs had willing bystanders, 13.8% of victims would have survived. Sensitivity analysis demonstrated that an AED drone network remained cost-effective over a wide range of assumptions.CONCLUSIONS With proper integration into existing systems, large-scale networks for drone AED delivery have the potential to substantially improve OHCA survival rates while remaining cost-effective. Public health researchers should consider advocating for feasibility studies and policy development surrounding drones.
Accumulated evidence demonstrates the centrality of social psychology to the behavior of members of the public as immediate responders in emergencies. Such public behavior is a function of social psychological processes—in particular identities and norms. In addition, what the authorities and relevant professional groups assume about the social psychology of people in emergencies shapes policy and practice in preparedness, response, and recovery. These assumptions therefore have consequences for the public's ability to act as immediate responders. In this Policy and Practice Review, we will do three things. First, we will overview research on the behavior of survivors of emergencies and disasters, drawing out key factors known to explain the extent to which survivors cooperate in these events and contribute to safe collective outcomes. We will demonstrate the utility of the social identity approach as an overarching framework for explaining the major mechanisms of collective supportive behavior among survivors in emergencies. Second, we will critically review recent and current UK government agency guidance on emergency response, focusing particularly on what is stated about the role of survivors in emergencies and disasters. This review will suggest that the “community resilience” agenda has only been partly realized in practice, but that the social identity approach is progressing this. Third, we will derive from the research literature and from dialogue with groups involved in emergencies a set of 12 recommendations for both emergency managers and members of the public affected by emergencies and disasters. These focus on the crucial need to build shared identity and to communicate, and the connection between these two aims. Including our recommendations within emergency guidance and training will facilitate collective psychosocial resilience, which refers to the way a shared identity allows groups of survivors to express and expect solidarity and cohesion, and thereby to coordinate and draw upon collective sources of support. In sum, this evidence-base and the recommendations we derive from it will help professionals involved in emergency management to support public resilient behaviors and will help the public to develop and maintain their own capacity for such resilience.
The last decades have seen a surge of robots working in contact with humans. However, until now these contact robots have made little use of the opportunities offered by physical interaction and lack a systematic methodology to produce versatile behaviors. Here we develop the first interactive robot controller able to understand the control strategy of the human user and react optimally to their movements. We demonstrate that combining an observer with a differential game theory controller can: induce a stable interaction between the two partners; precisely identify each other's control law; and allow them to successfully perform the task with minimum effort. Simulations and experiments with human subjects demonstrate these properties and illustrate how the new controller can induce different representative interaction strategies.
Crowd dynamics have important applications in evacuation management systems relevant to organizing safer large scale gatherings. For crowd safety, it is very important to study the evolution of potential crowd behaviours by simulating the crowd evacuation process. Planning crowd control tasks via studying the impact of crowd behavioural evolution towards evacuation simulation could mitigate the possibility of crowd disasters that may happen. During a typical emergency evacuation scenario, conflict among agents occurs when agents intend to move to the same location as a result of the interaction of agents within their nearest neighbours. The effect of the agent response towards their neighbourhood is vital in order to understand the effect of variation of crowd behaviours towards the whole environment. In this work, we model crowd motion subject to exit congestion under uncertainty conditions in a continuous space via computer simulations. We model best-response, risk-seeking, risk-averse and risk-neutral behaviours of agents via certain game theory notions. We perform computer simulations with heterogeneous populations in order to study the effect of the evolution of agent behaviours towards egress flow under threat conditions. Our simulation results show the relation between the local crowd pressure and the number of injured agents. We observe that when the proportion of agents in a population of risk-seeking agents is increased, the average crowd pressure, average local density and the number of injured agents get increased. Besides that, based on our simulation results, we can infer that crowd disaster could be prevented if the agent population are full of risk-averse and risk-neutral agents despite circumstances that lead to threat consequences.
As autonomous systems increasingly become part of our lives, it is crucial to foster trust between humans and these systems, to ensure positive outcomes and mitigate harmful ones.
Despite considerable research efforts on handling uncertainty in self-adaptive systems, a comprehensive understanding of the precise nature of uncertainty is still lacking. This paper summarises the findings of the 2023 Bertinoro Seminar on Uncertainty in Self- Adaptive Systems, which aimed at thoroughly investigating the notion of uncertainty, and outlining open challenges associated with its handling in self-adaptive systems. The seminar discussions were centered around five core topics: (1) agile end-toend handling of uncertainties in goal-oriented self-adaptive systems, (2) managing uncertainty risks for self-adaptive systems, (3) uncertainty propagation and interaction, (4) uncertainty in self-adaptive machine learning systems, and (5) human empowerment under uncertainty. Building on the insights from these discussions, we propose a research agenda listing key open challenges, and a possible way forward for addressing them in the coming years.
The Human Machine Teaming (HMT) paradigm focuses on supporting partnerships between humans and autonomous machines. HMT describes requirements for transparency, augmented cognition, and coordination that enable far richer partnerships than those found in typical human-on-the-loop and human-in-the-loop systems. Autonomous, self-adaptive systems in domains such as autonomous driving, robotics, and Cyber-Physical Systems, are often implemented using the MAPE-K feedback loop as the primary reference model. However, while MAPE-K enables fully autonomous behavior, it does not explicitly address the interactions that occur between humans and autonomous machines as intended by HMT. In this paper, we, therefore, present the MAPE-K HMT framework which utilizes runtime models to augment the monitoring, analysis, planning, and execution phases of the MAPE-K loop in order to support HMT despite the different operational cadences of humans and machines. We draw on examples from our own emergency response system of interactive, autonomous, small unmanned aerial systems to illustrate the application of MAPE-K HMT in both a simulated and physical environment, and discuss how the various HMT models are connected and can be integrated into a MAPE-K solution.
Society is characterized by the presence of a variety of social norms: collective patterns of sanctioning that can prevent miscoordination and free-riding. Inspired by this, we aim to construct learning dynamics where potentially beneficial social norms can emerge. Since social norms are underpinned by sanctioning, we introduce a training regime where agents can access all sanctioning events but learning is otherwise decentralized. This setting is technologically interesting because sanctioning events may be the only available public signal in decentralized multi-agent systems where reward or policy-sharing is infeasible or undesirable. To achieve collective action in this setting, we construct an agent architecture containing a classifier module that categorizes observed behaviors as approved or disapproved, and a motivation to punish in accord with the group. We show that social norms emerge in multi-agent systems containing this agent and investigate the conditions under which this helps them achieve socially beneficial outcomes.
Designing for the social, cultural, and ethical implications of ML are just as important as its technical advances.
Most real-world games and many recreational games are games of incomplete information. Over the last dozen years, abstraction has emerged as a key enabler for solving large incomplete-information games. First, the game is abstracted to generate a smaller, abstract game that is strategically similar to the original game. Second, an approximate equilibrium is computed in the abstract game. Third, the strategy from the abstract game is mapped back to the original game. In this paper, I will review key developments in the field. I present reasons for abstracting games, and point out the issue of abstraction pathology. I then review the practical algorithms for information abstraction and action abstraction. I then cover recent theoretical breakthroughs that beget bounds on the quality of the strategy from the abstract game, when measured in the original game. I then discuss how to reverse map the opponent's action into the abstraction if the opponent makes a move that is not in the abstraction. Finally, I discuss other topics of current and future research.
The vision of populating the world with autonomous systems that reduce human labor and improve safety is gradually becoming a reality. Autonomous systems have changed the way space exploration is conducted and are beginning to transform everyday life with a range of household products. In many areas, however, there are considerable barriers to the deployment of fully autonomous systems. We refer to systems that require some degree of human intervention in order to complete a task as semi-autonomous systems. We examine the broad rationale for semi-autonomy and define basic properties of such systems. Accounting for the human in the loop presents a considerable challenge for current planning techniques. We examine various design choices in the development of semi-autonomous systems and their implications on planning and execution. Finally, we discuss fruitful research directions for advancing the science of semi-autonomy.
Agent-based models of group behaviour often lack evidence-based psychological reasons for the behaviour. Similarly, pedestrian behaviour models focus on modelling physical movement while ignoring the psychological reasons leading to those movements (or other relevant behaviours). To improve realism, we need to be able to reflect behaviour as a consequence of feeling part of a psychological group, so we better understand why collective behaviour occurs under different circumstances. The social identity approach has been recognised as a way of understanding within and between group dynamics, as well as the processes that make an individual act as a group member. However, as promising the social identity approach is, the formalisation is a challenging endeavour since different choices can be made to reflect the core concepts and processes. We therefore in this paper elaborate on a few of these formalisation challenges and the choices we made. To support the formalisation and use of social identity approach and finally for the increased realism in group behaviour models, such as pedestrian models that are so heavily used to manage real world crowds.KeywordsPsychological groupAgent-based modellingSocial identitySelf-categorisation theoryGroup dynamics
As robots begin to interact closely with humans, we need to build systems worthy of trust regarding the safety and quality of the interaction.
Recently, we have been witnessing a rapid increase in the use of machine learning techniques in self-adaptive systems. Machine learning has been used for a variety of reasons, ranging from learning a model of the environment of a system during operation to filtering large sets of possible configurations before analyzing them. While a body of work on the use of machine learning in self-adaptive systems exists, there is currently no systematic overview of this area. Such an overview is important for researchers to understand the state of the art and direct future research efforts. This article reports the results of a systematic literature review that aims at providing such an overview. We focus on self-adaptive systems that are based on a traditional Monitor-Analyze-Plan-Execute (MAPE)-based feedback loop. The research questions are centered on the problems that motivate the use of machine learning in self-adaptive systems, the key engineering aspects of learning in self-adaptation, and open challenges in this area. The search resulted in 6,709 papers, of which 109 were retained for data collection. Analysis of the collected data shows that machine learning is mostly used for updating adaptation rules and policies to improve system qualities, and managing resources to better balance qualities and resources. These problems are primarily solved using supervised and interactive learning with classification, regression, and reinforcement learning as the dominant methods. Surprisingly, unsupervised learning that naturally fits automation is only applied in a small number of studies. Key open challenges in this area include the performance of learning, managing the effects of learning, and dealing with more complex types of goals. From the insights derived from this systematic literature review, we outline an initial design process for applying machine learning in self-adaptive systems that are based on MAPE feedback loops.
In human-robot collaborative frameworks, the maximization of productivity is of paramount importance. However, it is also crucial to mitigate the cognitive workload induced on the operator during cooperation. Indeed, a high level of stress can negatively affect the human capabilities, thus compromising the performance of the working dyad. In this work, we propose a novel paradigm where the robot is enabled to adapt online its behavior to simultaneously optimize in real-time the human physiological stress and productivity. The proposed control strategy exploits a game theoretic approach to model and locally estimate the state of collaboration in terms of human productivity and stress. Based on this estimate, a learning automaton suitably adjusts the production pace of the robot, thus influencing the dynamics of the cooperation. The proposed method was tested on a realistic collaborative assembly task. The results demonstrated that the novel control strategy effectively enhances the productivity of the human-robot team, while significantly mitigating the stress induced in the operator.
We don't yet have adequate theories of what the human mind is representing when it represents a social group. Worse still, many people think we do. This mistaken belief is a consequence of the state of play: Until now, researchers have relied on their own intuitions to link up the concept social group on the one hand, and the results of particular studies or models on the other. While necessary, this reliance on intuition has been purchased at considerable cost. When looked at soberly, existing theories of social groups are either (i) literal, but not remotely adequate (such as models built atop economic games), or (ii) simply metaphorical (typically a subsumption or containment metaphor). Intuition is filling in the gaps of an explicit theory. This paper presents a computational theory of what, literally, a group representation is in the context of conflict: it is the assignment of agents to specific roles within a small number of triadic interaction types. This "mental definition" of a group paves the way for a computational theory of social groups-in that it provides a theory of what exactly the information-processing problem of representing and reasoning about a group is. For psychologists, this paper offers a different way to conceptualize and study groups, and suggests that a non-tautological definition of a social group is possible. For cognitive scientists, this paper provides a computational benchmark against which natural and artificial intelligences can be held.
This chapter reviews research on the group identity explanation of social influence, grounded in self-categorization theory, and contrasts it with other group-based explanations, including normative influence, interdependence, and social network approaches, as well as approaches to persuasion and influence that background group (identity) processes. Although the review primarily discusses recent research, its focus also invites reappraisal of some classic research in order to address basic questions about the scope and power of the group identity explanation. The self-categorization explanation of influence grounded in group norms, moderated by group identification, is compared and contrasted to other normative explanations of influence, notably the concept of injunctive norms and the relation to moral conviction. A range of moderating factors relating to individual variation, features of the intragroup and intergroup context, and important contextual variables (i.e., anonymity versus visibility, isolation versus copresence) that are particularly relevant to online influence in the new media are also reviewed.
Expected final online publication date for the Annual Review of Psychology, Volume 72 is January 4, 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.
Priority inflation occurs when a Quality-Assurance (QA) engineer or a project manager requesting a feature inflates the priority of their task so that developers deliver the fix or the new functionality more quickly. We survey developers and show that priority inflation occurs and misallocates developer time. We are the first to apply empirical game-theoretic analysis (EGTA) to a software engineering problem, specifically priority inflation. First, we extract prioritisation strategies from 42,620 issues from Apache's JIRA, then use
TaskAssessor
, our EGTA-based modelling approach, to confirm conventional wisdom and show that the common process of a QA engineer assigning priority labels is susceptible to priority inflation. We then show that the common mitigation strategy of having a bug triage team assigning priorities does not resolve priority inflation and slows development. We then use mechanism design to devise
assessor-throttling
, a new, lightweight prioritization process, immune to priority inflation. We show that assessor-throttling resolves 97 percent of high priority tasks, 69 percent better than simply relying on those filing tasks to assign priorities. Finally, we present The Fed, a browser extension for Chrome that supports assessor-throttling.
Developers continuously invent new practices, usually grounded in hard-won experience, not theory. Game theory studies cooperation and conflict; its use will speed the development of effective
processes. A survey of game theory in software engineering finds highly idealised models that are rarely based on process data. This is because software processes are hard to analyse using traditional game theory since they generate huge game models. We are the first to show how to use game abstractions, developed in artificial intelligence, to produce tractable game-theoretic models of software practices. We present Game-Theoretic Process Improvement (GTPI), built on top of empirical game-theoretic analysis. Some teams fall into the habit of preferring “quick-and-dirty” code to slow-to-write, careful code, incurring technical debt. We showcase GTPI’s ability to diagnose and improve such a development process. Using GTPI, we discover a lightweight intervention that incentivises developers to write careful code: add a single code reviewer who needs to catch only 25% of kludges. This 25% accuracy is key; it means that a reviewer does not
need to examine each commit in depth, making this process intervention cost-effective.
This article presents a conceptual framework for human-robot trust which uses computational representations inspired by game theory to represent a definition of trust, derived from social psychology. This conceptual framework generates several testable hypotheses related to human-robot trust. This article examines these hypotheses and a series of experiments we have conducted which both provide support for and also conflict with our framework for trust. We also discuss the methodological challenges associated with investigating trust. The article concludes with a description of the important areas for future research on the topic of human-robot trust.