Arrow Research search

Author name cluster

Mor Vered

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers
2 author rows

Possible papers

17

AAMAS Conference 2026 Conference Paper

Neurosymbolic Active Goal Recognition in Partially Observable Environments

  • Chenyuan Zhang
  • Sukai Huang
  • Hamid Rezatofighi
  • Mor Vered
  • Buser Say

Active goal recognition, despite its importance for human–AI interaction and autonomous systems, has received relatively limited attention. Unlike passive goal recognition, which infers an actor’s intent from observations alone, active goal recognition allows an observer to select informative actions to reduce uncertainty about the actor’s goal. Building upon prior work in symbolic active goal recognition under POMDP settings, this paper introduces a neurosymbolic framework that addresses two key limitations. First, we extend the modeling capacity to account for heterogeneous actor behaviors, moving beyond the hand-crafted actor behaviour assumption. Second, weintegrateneuralmodelsintotheactivegoal recognition framework in two complementary ways: (i) by replacingactormodelswithVisionLanguageModels(VLMs)trainedfrom data, and (ii) by employing reinforcement learning to train the observer over belief maps, thereby enabling adaptive decision-making beyond symbolic observer policy. Experiments on the grid-world domain show that our neurosymbolic approach achieves comparative performance over state-of-the-art symbolic methods. These results highlight the promise of neurosymbolic methods for robust active goal recognition in complex, uncertain environments.

PDF

AAMAS Conference 2025 Conference Paper

A Hypothesis-Driven Approach to Explainable Goal Recognition

  • Abeer Alshehri
  • Hissah Alotaibi
  • Tim Miller
  • Mor Vered

In this paper, we introduce an explainable goal-recognition (XGR) approach for decision support that instantiates the evaluative AI paradigm. Current explainable AI (XAI) approaches focus on providing recommendations and justifying those recommendations. However, a shift toward evaluative AI has been proposed, focusing on generating evidence to support or refute human judgments and explaining trade-offs among hypotheses, rather than merely justifying AI recommendations. We introduce such a method for goal recognition tasks by leveraging the Weight of Evidence (WoE) framework. Through a human study in a maritime surveillance task, we demonstrate that our model improves decision accuracy, efficiency, and reliance in complex scenarios, outperforming two baseline models and demonstrating its potential in real-world decision-making.

PDF

AAMAS Conference 2025 Conference Paper

Explaining Facial Expression Recognition

  • Sanjeev Nahulanthran
  • Leimin Tian
  • Dana Kulic
  • Mor Vered

Facial expression recognition (FER) has emerged as a promising approach to the development of emotion-aware intelligent agents and systems. However, key challenges remain in utilizing FER in real-world contexts, including ensuring user understanding and establishing a suitable level of user trust. We developed a novel explanation method utilizing Facial Action Units (FAUs) to explain the output of a FER model through both textual and visual modalities. We conducted an empirical user study evaluating user understanding and trust, comparing our approach to stateof-the-art eXplainable AI (XAI) methods. Our results indicate that visual AND textual as well as textual-only FAU-based explanations resulted in better user understanding of the FER model. We also show that all modalities of FAU-based methods improved appropriate trust of the users towards the FER model.

PDF

KR Conference 2025 Conference Paper

Probabilistic Active Goal Recognition

  • Chenyuan Zhang
  • Cristian Rojas Cardenas
  • Hamid Rezatofighi
  • Mor Vered
  • Buser Say

In multi-agent environments, effective interaction hinges on understanding the beliefs and intentions of other agents. While prior work on goal recognition has largely treated the observer as a passive reasoner, Active Goal Recognition (AGR) focuses on strategically gathering information to reduce uncertainty. We adopt a probabilistic framework for AGR and propose an integrated solution that combines a joint belief update mechanism with a Monte Carlo Tree Search (MCTS) algorithm, allowing the observer to plan efficiently and infer the actor's hidden goal without requiring domain-specific knowledge. Through comprehensive empirical evaluation in a grid-based domain, we show that our joint belief update significantly outperforms passive goal recognition, and that our domain-independent MCTS performs comparably to our strong domain-specific greedy baseline. These results establish our solution as a practical and robust framework for goal inference, advancing the field toward more interactive and adaptive multi-agent systems.

PDF Details DOI

AAMAS Conference 2025 Conference Paper

Rethinking Explainable AI: Explanations can be Deceiving

  • Peta Masters
  • Daniel Gallagher
  • Luc Moreau
  • Mor Vered

The propensity to overtrust explanations and over-rely on systems that seem transparent makes humans vulnerable to output that conforms to explainable AI (XAI) best practice. Human-centred XAI research seeks to determine the type of explanation most appropriate in any particular context. Other disciplines, meanwhile, provide insights into the way deception has tended to arise in relation to AI systems. Examining XAI research in this context, we find it a perfect melting pot for the generation of deceptive explanations. We demonstrate the problem in a user study and provide and evaluate recommendations for stakeholders.

PDF

JAIR Journal 2025 Journal Article

Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach

  • Abeer Alshehri
  • Amal Abdulrahman
  • Hajar Alamri
  • Tim Miller
  • Mor Vered

Goal recognition (GR) involves inferring an agent's unobserved goal from a sequence of observations. This is a critical problem in AI with diverse applications. Traditionally, GR has been addressed using 'inference to the best explanation' or abduction, where hypotheses about the agent's goals are generated as the most plausible explanations for observed behavior. Alternatively, some approaches enhance interpretability by ensuring that an agent's behavior aligns with an observer's expectations or by making the reasoning behind decisions more transparent. In this work, we tackle a different challenge: explaining the GR process in a way that is comprehensible to humans. We introduce and evaluate an explainable model for goal recognition (GR) agents, grounded in the theoretical framework and cognitive processes underlying human behavior explanation. Drawing on insights from two human-agent studies, we propose a conceptual framework for human-centered explanations of GR. Using this framework, we develop the eXplainable Goal Recognition (XGR) model, which generates explanations for both why and why not questions. We evaluate the model computationally across eight GR benchmarks and through three user studies. The first study assesses the efficiency of generating human-like explanations within the Sokoban game domain, the second examines perceived explainability in the same domain, and the third evaluates the model's effectiveness in aiding decision-making in illegal fishing detection. Results demonstrate that the XGR model significantly enhances user understanding, trust, and decision-making compared to baseline models, underscoring its potential to improve human-agent collaboration.

PDF Details DOI

AAMAS Conference 2025 Conference Paper

Who Am I Dealing With? Explaining the Designer's Hidden Intentions

  • Turgay Caglar
  • Sarath Sreedharan
  • Mor Vered

Explainable AI (XAI) methods are generally seen as tools that allow users a greater level of visibility into why certain decisions were made by an AI system or agent. However, by the very choice of current works to focus on merely explaining why the AI system chose to perform an action in their environment, the explanation is withholding any information about the role played by the designer of said system and environment in determining the final behavior. This information could be particularly significant when the underlying designer objectives may differ from those of the user. In this paper we propose a new explanation generation paradigm, built on the concept of model reconciliation, and show how it can support the generation of explanations that include the designer’s goals. We define and study the formal properties of this new form of explanation and introduce an algorithm to generate it over a classical planning domain. We evaluate how this new explanation influences user performance, understanding and trust in an AI agent and further instantiate the new algorithm on standard planning benchmarks to evaluate its computational characteristics.

PDF

AAMAS Conference 2023 Conference Paper

Domain-Independent Deceptive Planning

  • Adrian Price
  • Ramon Fraga Pereira
  • Peta Masters
  • Mor Vered

We investigate deceptive planning, the problem of generating a plan such that an observer is unable to determine its ultimate goal. Most work in this area has focused on path and/or motion planning. However planning problems can be quite varied and challenging. We present domain-independent approaches for deceptive plan generation utilising the concepts of landmarks, centroids, and minimum covering states. We introduce new, domain-independent metrics to evaluate a plan’s deceptivity as a ratio between its deceptive quantity and cost; and we extensively evaluate the performance of our proposed approaches over widely different planning domains providing guidelines as to when to use each approach.

PDF

AIJ Journal 2023 Journal Article

The effects of explanations on automation bias

  • Mor Vered
  • Tali Livni
  • Piers Douglas Lionel Howe
  • Tim Miller
  • Liz Sonenberg

In this paper we explore the effect of explanations on reducing errors in the human decision making process caused by placing excessive reliance on automated decision support systems. We develop and implement different forms of explanations based on cognitive principles and evaluate their effect over two different domains: our new version of the Coloured Trails game, and over a simulated radiological task. We found that explanations did not reduce this aspect of automation bias and sometimes increased it. However, they reduced completion time and often increased user decision accuracy, despite not altering the perceived task load. Overall, explanations were beneficial though the benefits were highly context dependent. This work contributes to the complex interplay between automation bias, performance and explanations.

Details DOI

IJCAI Conference 2021 Conference Paper

What’s the Context? Implicit and Explicit Assumptions in Model-Based Goal Recognition

  • Peta Masters
  • Mor Vered

Every model involves assumptions. While some are standard to all models that simulate intelligent decision-making (e. g. , discrete/continuous, static/dynamic), goal recognition is well known also to involve choices about the observed agent: is it aware of being observed? cooperative or adversarial? In this paper, we examine not only these but the many other assumptions made in the context of model-based goal recognition. By exploring their meaning, the relationships between them and the confusions that can arise, we demonstrate their importance, shed light on the way trends emerge in AI, and suggest a novel means for researchers to uncover suitable avenues for future work.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Online Probabilistic Goal Recognition over Nominal Models

  • Ramon Fraga Pereira
  • Mor Vered
  • Felipe Meneguzzi
  • Miquel Ramírez

This paper revisits probabilistic, model-based goal recognition to study the implications of the use of nominal models to estimate the posterior probability distribution over a finite set of hypothetical goals. Existing model-based approaches rely on expert knowledge to produce symbolic descriptions of the dynamic constraints domain objects are subject to, and these are assumed to produce correct predictions. We abandon this assumption to consider the use of nominal models that are learnt from observations on transitions of systems with unknown dynamics. Leveraging existing work on the acquisition of domain models via learning for Hybrid Planning we adapt and evaluate existing goal recognition approaches to analyze how prediction errors, inherent to system dynamics identification and model learning techniques have an impact over recognition error rates.

PDF Details

AAAI Conference 2018 Conference Paper

Plan Recognition in Continuous Domains

  • Gal Kaminka
  • Mor Vered
  • Noa Agmon

Plan recognition is the task of inferring the plan of an agent, based on an incomplete sequence of its observed actions. Previous formulations of plan recognition commit early to discretizations of the environment and the observed agent’s actions. This leads to reduced recognition accuracy. To address this, we first provide a formalization of recognition problems which admits continuous environments, as well as discrete domains. We then show that through mirroring— generalizing plan-recognition by planning—we can apply continuous-world motion planners in plan recognition. We provide formal arguments for the usefulness of mirroring, and empirically evaluate mirroring in more than a thousand recognition problems in three continuous domains and six classical planning domains.

PDF Details

IJCAI Conference 2017 Conference Paper

Heuristic Online Goal Recognition in Continuous Domains

  • Mor Vered
  • Gal A. Kaminka

Goal recognition is the problem of inferring the goal of an agent, based on its observed actions. An inspiring approach—plan recognition by planning (PRP)—uses off-the-shelf planners to dynamically generate plans for given goals, eliminating the need for the traditional plan library. However, existing PRP formulation is inherently inefficient in online recognition, and cannot be used with motion planners for continuous spaces. In this paper, we utilize a different PRP formulation which allows for online goal recognition, and for application in continuous spaces. We present an online recognition algorithm, where two heuristic decision points may be used to improve run-time significantly over existing work. We specify heuristics for continuous domains, prove guarantees on their use, and empirically evaluate the algorithm over hundreds of experiments in both a 3D navigational environment and a cooperative robotic team task.

PDF Details
v2026.09.13