Liz Sonenberg's research while affiliated with University of Melbourne and other places

Publications (145)

Article
In this paper, we show that explanations of decisions made by machine learning systems can be improved by not only explaining why a decision was made but also by explaining how an individual could obtain their desired outcome. We formally define the concept of directive explanations (those that offer specific actions an individual could take to ach...
Preprint
In this paper, we show that counterfactual explanations of confidence scores help users better understand and better trust an AI model's prediction in human-subject studies. Showing confidence scores in human-agent interaction systems can help build trust between humans and AI systems. However, most existing research only used the confidence score...
Article
Many AI applications involve the interaction of multiple autonomous agents, requiring those agents to reason about their own beliefs, as well as those of other agents. However, planning involving nested beliefs is known to be computationally challenging. In this work, we address the task of synthesizing plans that necessitate reasoning about the be...
Preprint
Full-text available
Many AI applications involve the interaction of multiple autonomous agents, requiring those agents to reason about their own beliefs, as well as those of other agents. However, planning involving nested beliefs is known to be computationally challenging. In this work, we address the task of synthesizing plans that necessitate reasoning about the be...
Article
Full-text available
In most multiagent applications, communication is essential among agents to coordinate their actions and achieve their goals. However, communication often has a related cost that affects overall system performance. In this paper, we draw inspiration from epistemic planning studies to develop a communication model for agents that allows them to coop...
Preprint
Full-text available
This paper investigates the prospects of using directive explanations to assist people in achieving recourse of machine learning decisions. Directive explanations list which specific actions an individual needs to take to achieve their desired outcome. If a machine learning model makes a decision that is detrimental to an individual (e.g. denying a...
Chapter
In 2000, it was predicted that artificially intelligent agents would inevitably become deceptive. Today, in a world seemingly awash with fake news and in which we hand over control of our home environments to faux-human smart devices, it is timely to review the types of deception that have actually emerged. By reference to examples from diverse bra...
Chapter
Drawing on an ecological perspective, we contend that research into deception in AI needs to consider not only the cognitive structures of would-be deceptive agents but also the nature of the environments in which they act. To illustrate this approach, we report work-in-progress to design a game called MindTrails, played between a software agent an...
Article
Full-text available
We address the challenge of multi-agent system (MAS) design for organisations of agents acting in dynamic and uncertain environments where runtime flexibility is required to enable improvisation through sharing knowledge and adapting behaviour. We identify behavioural features that correspond to runtime improvisation by agents in a MAS organisation...
Article
In autonomous multiagent or multirobotic systems, the ability to quickly and accurately respond to threats and uncertainties is important for both mission outcomes and survivability. Such systems are never truly autonomous, often operating as part of a human-agent team. Artificial intelligent agents (IAs) have been proposed as tools to help manage...
Article
Prominent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen by referring to counterfactuals — things that did not...
Article
Intention recognition is the process of using behavioural cues, such as deliberative actions, eye gaze, and gestures, to infer an agent's goals or future behaviour. In artificial intelligence, one approach for intention recognition is to use a model of possible behaviour to rate intentions as more likely if they are a better ‘fit’ to actions observ...
Preprint
Full-text available
Causal explanations present an intuitive way to understand the course of events through causal chains, and are widely accepted in cognitive science as the prominent model humans use for explanation. Importantly, causal models can generate opportunity chains, which take the form of `A enables B and B causes C'. We ground the notion of opportunity ch...
Preprint
Full-text available
In most multiagent applications, communication is essential among agents to coordinate their actions, and thus achieve their goal. However, communication often has a related cost that affects overall system performance. In this paper, we draw inspiration from studies of epistemic planning to develop a communication model for agents that allows them...
Preprint
Full-text available
Prevalent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen. In this paper, we use causal models to derive causal...
Article
Full-text available
A concept of capability in multi-agent systems that incorporates a notion of tools that are available to an agent in the environment is formalised. Using tools as the realisation of external capability requires less theoretical apparatus than modelling the interaction between agents. The contribution of this paper is a formal BDI logic for expressi...
Preprint
Full-text available
Explainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee a...
Conference Paper
Full-text available
Intention recognition is the process of using behavioural cues to infer an agent's goals or future behaviour. People use many behavioural cues to infer others' intentions, such as deliberative actions, facial expressions, eye gaze, and gestures. In artificial intelligence, two approaches for intention recognition, among others, are gaze-based and m...
Preprint
Full-text available
To generate trust with their users, Explainable Artificial Intelligence (XAI) systems need to include an explanation model that can communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interacti...
Chapter
Full-text available
In this chapter, we describe social planning mechanisms for constructing and representing explainable plans in human-agent interactions, addressing one aspect of what it will take to meet the requirements of a trusted autonomous system. Social planning is automated planning in which the planning agent maintains and reasons with an explicit model of...
Article
Full-text available
In his seminal book `The Inmates are Running the Asylum: Why High-Tech Products Drive Us Crazy And How To Restore The Sanity' [2004, Sams Indianapolis, IN, USA], Alan Cooper argues that a major reason why software is often poorly designed (from a user perspective) is that programmers are in charge of design decisions, rather than interaction design...
Article
Full-text available
According to Clark's seminal work on common ground and grounding, participants collaborating in a joint activity rely on their shared information, known as common ground, to perform that activity successfully, and continually align and augment this information during their collaboration. Similarly, teams of human and artificial agents require commo...
Conference Paper
Cooperative problem solving involves four key phases: (1) finding potential members to form a team, (2) forming the team, (3) formulating a plan for the team, and (4) executing the plan. We extend recent work on multi-agent epistemic planning and apply it to the problem of team formation in a blocksworld scenario. We provide an encoding of the firs...
Article
Full-text available
Psychologists and cognitive scientists have long drawn insights and evidence from stage magic about human perceptual and attentional errors. We present a complementary analysis of conjuring tricks that seeks to understand the experience of impossibility that they produce. Our account is first motivated by insights about the constructional aspects o...
Conference Paper
Full-text available
Research shows that performance of human teams improves when members have a shared understanding of their task; that is, when teams develop and use a shared mental model (SMM). An SMM can contain different types of information or components and this paper investigates the influence on team performance of sharing different components. We consider tw...
Article
Objective: We investigated implicit communication strategies for anticipatory information sharing during team performance of tasks with varying degrees of complexity. We compared the strategies used by teams with the highest level of performance to those used by the lowest-performing teams to evaluate the frequency and methods of communications us...
Article
Proper epistemic knowledge bases (PEKBs) are syntactic knowledge bases that use multi-agent epistemic logic to represent nested multi-agent knowledge and belief. PEKBs have certain syntactic restrictions that lead to desirable computational properties; primarily, a PEKB is a conjunction of modal literals, and therefore contains no disjunction. Soun...
Article
Full-text available
Making a computational agent 'social' has implications for how it perceives itself and the environment in which it is situated, including the ability to recognise the behaviours of others. We point to recent work on social planning, i.e. planning in settings where the social context is relevant in the assessment of the beliefs and capabilities of o...
Article
Full-text available
People Oriented Programming (POP) is a new paradigm for developing individual-oriented software applications and associated devices that entails four defining elements. The first three elements call upon, respectively, the individual user: 1. As the central focus of a customised software artefact addressing their heterogeneous needs, described as ‘...
Conference Paper
We present an approach for designing organization-oriented multi-agent systems (MASs) to allow improvisation at run time when agents are not available to exactly match the original organizational design structure. Working with system components from an existing MAS organizational meta-model, OJAzzIC, the approach sets out five stages for the design...
Article
Many AI applications involve the interaction of multiple autonomous agents, requiring those agents to reason about their own beliefs, as well as those of other agents. However, planning involving nested beliefs is known to be computationally challenging. In this work, we address the task of synthesizing plans that necessitate reasoning about the be...
Article
Full-text available
Reasoning about the nested beliefs or knowledge of other agents is essential for many collaborative and competitive tasks. However, reasoning with nested belief (for example through epistemic logics) is computationally expensive. Proper Epistemic Knowledge Bases (PEKBs) address this by enforcing syntactic restrictions on the knowledge base. By comp...
Conference Paper
Full-text available
Designers of human-agent systems use the term “interdependence,” drawing on the work of organisational theorists and sociologists that is set in a human context. In this paper, we extend the agent systems analysis by semi-formally defining several types of task and agent interdependence that are introduced in the organisation theory literature. We...
Conference Paper
With a view to supporting expressive, but tractable, collaborative interactions between humans and agents, we propose an approach for representing heterogeneous agent models, i.e., with potentially diverse mental abilities and holding stereotypical characteristics as members of a social reference group. We build a computationally grounded mechanism...
Article
Full-text available
Purpose – The purpose of this paper is to examine how pregnant women with type 1 diabetes integrate new information technology (IT) into their health management activities, using activity theory as an analytical framework. Design/methodology/approach – The research is a multiple case design, based on interviews with 15 women with type 1 diabetes w...
Chapter
We analyze from a semi-formal perspective the grounding model of cultural transmission, a social psychological theory that emphasizes the role of everyday joint activities in the transmission of cultural information. The model postulates that cultural transmission during joint activities depends on the context of the activity and the common ground...
Conference Paper
We seek to engineer adaptive coordination between agents working in and across dynamic organizations in a complex, distributed setting. Guided by predefined social policies, agents can create social commitments at run time to achieve coordination of knowledge and behaviour. We demonstrate coordination requirements by providing example policies, dra...
Conference Paper
Full-text available
Space operations involve the control of complex technical equipment in highly dynamic and unknown environments. This is a challenging task for human operators. To facili- tate this task, mission-critical software systems need to be able to truly engage in joint activities with their human operators; i.e. these systems need to be designed for inter-...
Article
Full-text available
We present a new technique for interactively mining patterns and generating explanations by harnessing the expertise of domain experts. Key to the approach is the distinction between what is unexpected from the perspective of the computational data mining process and what is surprising to the domain experts and interesting relative to their needs....
Article
Full-text available
Most successful Bayesian network (BN) applications to datehave been built through knowledge elicitation from experts.This is difficult and time consuming, which has lead to recentinterest in automated methods for learning BNs from data. We present a case study in the construction of a BN in anintelligent tutoring application, specifically decimal m...
Article
Full-text available
The articles in this special issue have been specifically commissioned to provide a snapshot of current activity in the autonomous agents and multiagent systems communities.
Article
The articles in this special issue have been specifically commissioned to provide a snapshot of current activity in the autonomous agents and multiagent systems communities.
Conference Paper
Computational models of the transmission of cultural information usually neglect that cultural transmission between individuals occurs mainly as a consequence of complex social interactions. We analyze the requirements for a computational model of a social psychological theory of cultural transmission, a theory which postulates that actors in a joi...
Chapter
We elaborate the rationale and design of OJAzzIC (Organizations Joining Adaptively with Improvised Coordination), a model for agents in (Jazzy) Organizations that need to engage in dynamic adaptation to respond to a dynamic situation. OJAzzIC provides an adaptive data structure and framework for creation of multiple instances of organizations withi...
Conference Paper
Full-text available
Traders that operate in markets with multiple competing marketplaces can use learning to choose in which marketplace they will trade, and how much they will shout in that marketplace. If traders are able to share information with each other about their shout price and market choice over a social network, they can trend towards the market equilibriu...
Conference Paper
A typical thread in research relies on the maturing of ideas through an iterative process of construction, testing and refinement. In this talk I will trace some such trajectories of ideas by illustration from some of my own and others' experiences in agent-based modelling. I draw inspiration from previous commentaries, including from those who gen...
Chapter
Reputation and commitment are important issues for automated contracting. Leveled commitment contracts, i.e. contracts where each party can decommit by paying a predetermined penalty, were introduced to allow self interested agents to accommodate events that unfolded since the contract was entered into. Various approaches to modelling reputation ha...
Article
Full-text available
Exhibits within Cultural Heritage collections such as museums and art galleries are arranged by experts with intimate knowledge of the domain, but there may exist connections between individual exhibits that are not evident in this representation. For example, the visitors to such a space may have their own opinions on how exhibits relate to one an...
Conference Paper
Full-text available
ICT can play a vital role in facilitating quality care and support for people living with chronic illness. Recently, there has been a proliferation of ICT-enabled consumer health devices. These devices can enable individual patients more precise monitoring and control of chronic conditions, and can generate information and statistics for analysis b...
Conference Paper
In this paper we address the design of robots that can be successful partners to humans in joint activity. The paper outlines an approach to achieving adjustable autonomy during execution- and hence to achieve resilient multi-actor joint action - based on both temporal and epistemic situation projection. The approach is based on non-deterministic p...
Chapter
Full-text available
In this paper we develop a comprehensive composite meta-model from Task Analysis models called the Reference Task Meta-model (ReTaMeta model) for the purpose of comparing numerous Agent-Oriented meta-models. The reference model needed to be derived from a field independent of the Agent-oriented paradigm, yet based on Psychology. To arrive at the Re...
Conference Paper
Full-text available
We introduce an architecture for low-cost mobile health (mHealth) applications that run on health-workers' existing devices. Moreover, we envision extending the phone's capabilities with an external to attach ¿sensor¿ modules, such as pulse oximeter, ECG and phonocardiogram. Our design principles are frugality and simplicity. We propose a compreh...
Conference Paper
Creating agents that act reasonably in uncertain environments is a primary goal of agent-based research. In this work we explore the theory that wishful thinking can be an effective strategy in uncertain and competitive decision scenarios. Specifically, we present the constraints necessary for wishful thinking to outperform Expected Utility Maximiz...
Article
Full-text available
Dealing with changing situations is a major issue in building agent systems. When the time is limited, knowledge is unreliable, and resources are scarce, the issue becomes more challenging. The BDI (Belief-Desire-Intention) agent architecture provides a model for building agents that addresses that issue. The model can be used to build intentional...
Article
Full-text available
In multi-agent systems (MAS), negotiation provides a powerful metaphor for automating the allocation and reallocation of resources. Methods for automated negotiation in MAS include auction-based protocols and alternating offer bargaining protocols. Recently, argumentation-based negotiation has been accepted as a promising alternative to such approa...
Conference Paper
The main aim of this paper is to motivate extending the formal definition of "capability'' to incorporate the capabilities of external entities, i.e. external capability. The title points to the idea that an external entity may be either a tool or an agent, and only in the latter case does collaboration becomes relevant. This is the starting point...
Conference Paper
We present a novel approach for assisting pattern interpretation by data mining end-users: finding explanations for association rules based on probabilistic dependencies. In the approach, relevant variables are selected from rules and from other data sources to facilitate human-understandable interpretations. An explanation of a rule involves consi...
Conference Paper
Full-text available
The vast amounts of information presented in museums can be overwhelming to a visitor, whose receptivity and time are typically limited. Hence, s/he might have difficulties selecting interesting exhibits to view within the available time. Mobile, context-aware guides offer the opportunity to improve a visitor’s experience by recommending exhibits o...
Conference Paper
Full-text available
Software agents are situated in an environment with which they interact reactively or in a goal-directed fashion. Generally, such environments do not assume a structure, hence are deemed to be unpredictable. Recent approaches adopt an environment model where artifacts form the building blocks. Artifacts represent functional components that an agent...
Conference Paper
Full-text available
Agent-based simulation can be used to investigate behavioural requirements, capabilities and strategies that might be helpful in complex, dynamic and adaptive situations, and can be used in training scenarios. In this paper, we study the requirements of coordination in complex unfolding scenarios in which agents may come and go and where there is a...
Article
Full-text available
Museums offer vast amounts of information, but a visitor's receptivity and time are typically limited, providing the visitor with the challenge of selecting the (subjectively) interesting exhibits to view within the available time. Mobile, electronic handheld guides offer the opportunity to improve a visitor's experience by recommending exhibits of...
Conference Paper
In the research discussed here, in addition to extracting meta-models from numerous existing Agent architectures and frameworks, we looked at several Task meta-models, with the aim of creating a more comprehensive Agent meta-model with respect to the analysis, design and development of computer games. From the agent-oriented perspective gained by e...
Conference Paper
Full-text available
In this paper, we detail recent research on agent meta-models. In par-ticular, we introduce a new agent meta-model called ShaMAN, created with a specific focus on computer game development using agent systems. ShaMAN was derived by applying the concept of Normalisation from Information Analy-sis, against a superset of agent meta-model concepts from...
Article
Full-text available
While the layout of a museum exhibition is largely prescribed by the curator, visitors to museums view connections between exhibits in ways unique to themselves. With the assistance of a large-scale survey of museum visitors we identify that the view taken by museum visitors of a collection of exhibits can be rep- resented by similarity over docume...
Article
We have analysed rich, dynamic data about the behaviour of anaesthetists during the management of a simulated critical incident in the operating theatre. We use a paper based analysis and a partial implementation to further the development of a computational cognitive model for disturbance management in anaesthesia. We suggest that our data analysi...
Conference Paper
Full-text available
Current practices for agent-infrastructure interaction enforce agent designers to hard code the name and the use of the infrastructure components in the agent. Therefore, agents can only function within an environment which is a priori known to the agent designer. Even in these environments, agents are not robust against the modification or failure...
Conference Paper
Full-text available
While argumentation-based negotiation has been accepted as a promising alternative to game-theoretic or heuristic-based negotiation, no evidence has been provided to confirm this theoretical advantage. We propose a model of bilateral negotiation extending a simple monotonic concession protocol by allowing the agents to exchange information about th...
Article
This paper reports a domain ontology-driven approach to data mining on a medical database containing clinical data on patients undergoing treatment for chronic kidney disease. Each record within the dataset is comprised of a large number (up to 96) of quantitative and qualitative metrics which represent the physiological state of a particular patie...
Article
Full-text available
Abstract Automated negotiation is a powerful (and sometimes,essential) means,for allocating resources among,self-interested autonomous,software agents. A key problem in building negotiating agents is the design of the negotiation strategy, which is used by an agent to decide its negotiation behaviour. In complex domains, there is no single, obvious...
Conference Paper
Full-text available
Interest-based negotiation (IBN) is a form of negotiation in which agents exchange information about their underlying goals, with a view to improving the likelihood and quality of a deal. While this in- tuition has been stated informally in much previous literature, there is no formal analysis of the types of deals that can be reached through IBN a...