In this paper, we highlight the field of explainable sequential decision making. We discuss how the problem of explaining sequential decisions gives rise to problems and challenges that are absent from scenarios that focus on explaining single-shot decision making. We provide a short survey of some of the more prominent subareas within explainable sequential decision-making and their unique focuses and blind spots. Here, we argue that we need to go beyond simply focusing on individual subareas like explainable planning, reinforcement learning, or robotics, and move towards studying and tackling the more general problem of explainable sequential decision-making. Such a holistic approach will not only allow us to identify previously ignored problems, but also provide us with the ability to transfer ideas and intuitions from one subarea of explainable sequential decision-making to another. We end the paper with a discussion on future directions and some of the most pressing open questions.

It is well understood that mental modeling forms the foundation of many everyday interactions between humans. This includes both collaborative and deceptive interactions. One could argue that the modeling and manipulation of mental states lies at the heart of effective deception. In this paper, we examine the security problem of insider threat attacks. In this case, an adversary has already infiltrated an organization. The primary challenge for this attacker is to avoid suspicion until their true goal can be achieved. We see how existing model-based explanatory methods can be leveraged to generate lies that explain away potentially suspicious activities. We also propose a novel planning formulation which generates plans that appear to achieve an assigned goal while getting close enough to reach an alternative, covert goal. We evaluate our method through computational experiments and a user study.

Generating behaviors that align with human expectations is a key requirement for human-robot collaboration. Potential behavior misalignment could lead to the robot performing actions with unanticipated, potentially dangerous side effects even while pursuing human goals. In this paper, we introduce a novel metric called Goal State Divergence (GSD) which quantifies the difference between the state a robot achieved in response to a human-specified goal and what the human expected. In cases where GSD cannot be directly calculated, we show how it can be approximated using maximal and minimal bounds. We then leverage GSD in our novel human-robot goal alignment design (HRGAD) problem, which identifies a minimal set of environment modifications that can reduce such mismatches. We show the effectiveness of our method in reducing the goal state divergence by empirically evaluating our approach on several planning benchmarks.

One of the significant challenges to generating value-aligned behavior is to not only account for the specified user objectives but also any implicit or unspecified user requirements. The existence of such implicit requirements could be particularly common in settings where the user's understanding of the task model may differ from the agent's estimate of the model. Under this scenario, the user may incorrectly expect some agent behavior to be inevitable or guaranteed. This paper addresses such expectation mismatch in the presence of differing models by capturing the possibility of unspecified user subgoal in the context of a task captured as a Markov Decision Process (MDP) and querying for it as required. Our method identifies bottleneck states and uses them as candidates for potential implicit subgoals. We then introduce a querying strategy that will generate the minimal number of queries required to identify a policy guaranteed to achieve the underlying goal. Our empirical evaluations demonstrate the effectiveness of our approach in inferring and achieving unstated goals across various tasks.

The ability to provide useful and intuitive explanations remains one of the major hurdles to creating robotic systems capable of working effectively with everyday users. In this paper, we consider a popular explanation generation framework for robot task plans, namely model reconciliation, and try to address one of its main drawbacks, namely its inability to generate actionable explanations. The current methods for generating model reconciliation focus on generating information that explains why the robot chose a certain behavior over one that was expected by the human. However, the user might also want to understand how they can influence the robot's behavior so it follows the one that was expected from it. Explanations that provide such information are called actionable, and we extend traditional model reconciliation explanations to be actionable by combining them with the existing notion of excuses. We will refer to the resulting explanations as Actionable Reconciliation Explanations (ARE), which explains the robot's decision-making process and suggests how its model might be modified for improved alignment with human expectations. However, as we will see, the generation of ARE requires methods that are distinct from existing model reconciliation and excuse generation methods, and ARE also exhibits properties that are distinct from these earlier methods. We assess our method through computational experiments and user studies and, in the process, also compare it against traditional forms of excuses and model reconciliation explanations.

In this late-breaking report, we look at two popular objective specification mechanisms for sequential decision-making problems, namely goals and rewards, and investigate how easy it would be for non-AI experts to use them effectively. Specifically, we propose a user study that allows us to test a user's ability to ($a$) use these mechanisms to direct a robot to generate some desired behavior and (b) predict the behavior resulting from a given objective specification. We conducted a small pilot study to test the study design and report some preliminary observations made regarding the two specification mechanisms.

Accurate planning models are a prerequisite for the appropriate functioning of AI planning applications. Creating these models is, however, a tedious and error-prone task -- even for planning experts. This makes the provision of automated modeling support essential. In this work, we differentiate between approaches that learn models from scratch (called domain model acquisition) and those that repair flawed or incomplete ones. We survey approaches for the latter, including those that can be used for domain repair but have been developed for other applications, discuss possible optimization metrics (i.e., which repaired model to aim at), and conclude with lines of research we believe deserve more attention.

One of the core challenges of explaining decisions made by modern AI systems is the need to address the potential gap in the inferential capabilities of the system generating the decision and the user trying to make sense of it. This inferential capability gap becomes even more critical when it comes to explaining sequential decisions. While there have been some isolated efforts at developing explanation methods suited for complex decision-making settings, most of these current efforts are limited in scope. In this paper, we introduce a general framework for generating explanations in the presence of inferential capability gaps. A framework that is grounded in the generation of simplified representations of the agent model through the application of a sequence of model simplifying transformations. This framework not only allows us to develop an extremely general explanation generation algorithm, but we see that many of the existing works in this direction could be seen as specific instantiations of our more general method. While the ideas presented in this paper are general enough to be applied to any decision-making framework, we will focus on instantiating the framework in the context of stochastic planning problems. As a part of this instantiation, we will also provide an exhaustive characterization of explanatory queries and an analysis of various classes of applicable transformations. We will evaluate the effectiveness of transformation-based explanations through both synthetic experiments and user studies.

Graph-based frameworks are often used in network hardening to help a cyber defender understand how a network can be attacked and how the best defenses can be deployed. However, incorporating network connectivity parameters in the attack graph, reasoning about the attack graph when we do not have access to complete information, providing system administrator suggestions in an understandable format, and allowing them to do what-if analysis on various scenarios and attacker motives is still missing. We fill this gap by presenting SPEAR, a formal framework with tool support for security posture evaluation and analysis that keeps human-in-the-loop. SPEAR uses the causal formalism of AI planning to model vulnerabilities and configurations in a networked system. It automatically converts network configurations and vulnerability descriptions into planning models expressed in the Planning Domain Definition Language (PDDL). SPEAR identifies a set of diverse security hardening strategies that can be presented in a manner understandable to the domain expert. These allow the administrator to explore the network hardening solution space in a systematic fashion and help evaluate the impact and compare the different solutions.

This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this union, we explore two different flavors of model space problems that have been studied in the AI planning literature and explore the effect of an LLM on those tasks. We empirically demonstrate how the performance of an LLM contrasts with combinatorial search (CS) – an approach that has been traditionally used to solve model space tasks in planning, both with the LLM in the role of a standalone model space reasoner as well as in the role of a statistical signal in concert with the CS approach as part of a two-stage process. Our experiments show promising results suggesting further forays of LLMs into the exciting world of model space reasoning for planning tasks in the future.

While the question of misspecified objectives has gotten much attention in recent years, most works in this area primarily focus on the challenges related to the complexity of the objective specification mechanism (for example, the use of reward functions). However, the complexity of the objective specification mechanism is just one of many reasons why the user may have misspecified their objective. A foundational cause for misspecification that is being overlooked by these works is the inherent asymmetry in human expectations about the agent's behavior and the behavior generated by the agent for the specified objective. To address this, we propose a novel formulation for the objective misspecification problem that builds on the human-aware planning literature, which was originally introduced to support explanation and explicable behavioral generation. Additionally, we propose a first-of-its-kind interactive algorithm that is capable of using information generated under incorrect beliefs about the agent to determine the true underlying goal of the user.

We describe our methodology for classifying ASL (American Sign Language) gestures. Rather than operate directly on raw images of hand gestures, we extract coor-dinates and render wireframes from individual images to construct a curated training dataset. This dataset is then used in a classifier that is memory efficient and provides effective performance (94% accuracy). Because we con-struct wireframes that contain information about several angles in the joints that comprise hands, our methodolo-gy is amenable to training those interested in learning ASL by identifying targeted errors in their hand gestures.

Detecting and handling misspecified objectives, such as reward functions, has been widely recognized as one of the central challenges within the domain of Artificial Intelligence (AI) safety research. However, even with the recognition of the importance of this problem, we are unaware of any works that attempt to provide a clear definition for what constitutes (a) misspecified objectives and (b) successfully resolving such misspecifications. In this work, we use the theory of mind, i.e., the human user's beliefs about the AI agent, as a basis to develop a formal explanatory framework, called Expectation Alignment (EAL), to understand the objective misspecification and its causes. Our EAL framework not only acts as an explanatory framework for existing works but also provides us with concrete insights into the limitations of existing methods to handle reward misspecification and novel solution strategies. We use these insights to propose a new interactive algorithm that uses the specified reward to infer potential user expectations about the system behavior. We show how one can efficiently implement this algorithm by mapping the inference problem into linear programs. We evaluate our method on a set of standard Markov Decision Process (MDP) benchmarks.

We are living through a revolutionary moment in AI history. We are seeing the development of impressive new AI systems at a rate that was unimaginable just a few years ago. However, AI's true potential to transform society remains unrealized, in no small part due to the inability of current systems to work effectively with people. A major hurdle to achieving such coordination is the inherent asymmetry between the AI system and its users. In this talk, I will discuss how the framework of Human-Aware AI (HAAI) provides us with the tools required to bridge this gap and support fluent and intuitive coordination between the AI system and its users.

Trust between team members is an essential requirement for any successful cooperation. Thus, engendering and maintaining the fellow team members' trust becomes a central responsibility for any member trying to not only successfully participate in the task but to ensure the team achieves its goals. The problem of trust management is particularly challenging in mixed human-robot teams where the human and the robot may have different models about the task at hand and thus may have different expectations regarding the current course of action, thereby forcing the robot to focus on the costly explicable behavior. We propose a computational model for capturing and modulating trust in such iterated human-robot interaction settings, where the human adopts a supervisory role. In our model, the robot integrates human's trust and their expectations about the robot into its planning process to build and maintain trust over the interaction horizon. By establishing the required level of trust, the robot can focus on maximizing the team goal by eschewing explicit explanatory or explicable behavior without worrying about the human supervisor monitoring and intervening to stop behaviors they may not necessarily understand. We model this reasoning about trust levels as a meta reasoning process over individual planning tasks. We additionally validate our model through a human subject experiment.

Recent prolific advances in artificial intelligence through the incorporation of domain knowledge have constituted a new paradigm for AI and data mining communities. For example, the human feedback-based language generation in ChatGPT (a large language model (LLM)), the use of Protein Bank in DeepMind's AlphaFold, and the use of 23 rules of safety in DeepMind's Sparrow have demonstrated the success of teaming human knowledge and AI. In addition, the knowledge retrieval-guided language modeling methods have strengthened the association between knowledge and AI. However, translating research methods and resources into practice presents a new challenge for the machine learning and data/knowledge mining communities. For example, in DARPA's Explainable AI seminar, the need for explainable contextual adaptation is seen as the 3rd phase of AI, facilitating the interplay between data and knowledge for explainability, safety, and, eventually, trust. However, policymakers and practitioners assert serious usability and privacy concerns that constrain adoption, notably in high-consequence domains, such as cybersecurity, healthcare, and other social good domains. In addition, limitations in output quality, measurement, and interactive ability, including both the provision of explanations and the acceptance of user preferences, result in low adoption rates in such domains. This workshop aims to accelerate our pace towards creating innovative methods for integrating knowledge into contemporary AI and data science methods and develop metrics for assessing performance in various applications.

There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical due to several factors, including limited correctness of plans, strong reliance on feedback from interactions with simulators or even the actual environment, and the inefficiency in utilizing human feedback. In this work, we introduce a novel alternative paradigm that constructs an explicit world (domain) model in planning domain definition language (PDDL) and then uses it to plan with sound domain-independent planners. To address the fact that LLMs may not generate a fully functional PDDL model initially, we employ LLMs as an interface between PDDL and sources of corrective feedback, such as PDDL validators and humans. For users who lack a background in PDDL, we show that LLMs can translate PDDL into natural language and effectively encode corrective feedback back to the underlying domain model. Our framework not only enjoys the correctness guarantee offered by the external planners but also reduces human involvement by allowing users to correct domain models at the beginning, rather than inspecting and correcting (through interactive prompting) every generated plan as in previous work. On two IPC domains and a Household domain that is more complicated than commonly used benchmarks such as ALFWorld, we demonstrate that GPT-4 can be leveraged to produce high-quality PDDL models for over 40 actions, and the corrected PDDL models are then used to successfully solve 48 challenging planning tasks. Resources, including the source code, are released at: https://guansuns.github.io/pages/llm-dm.

There has been an increasing interest in using symbolic models along with reinforcement learning (RL) problems, where these coarser abstract models are used as a way to provide RL agents with higher level guidance. However, most of these works are inherently limited by their assumption of having an access to a symbolic approximation of the underlying problem. To address this issue, we introduce a new method for learning optimistic symbolic approximations of the underlying world model. We will see how these representations, coupled with fast diverse planners developed by the automated planning community, provide us with a new paradigm for optimistic exploration in sparse reward settings. We investigate the possibility of speeding up the learning process by generalizing learned model dynamics across similar actions with minimal human input. Finally, we evaluate the method, by testing it on multiple benchmark domains and compare it with other RL strategies.

Generating plans of action, and reasoning about change have long been considered a core competence of intelligent agents. It is thus no surprise that evaluating the planning and reasoning capabilities of large language models (LLMs) has become a hot topic of research. Most claims about LLM planning capabilities are however based on common sense tasks–where it becomes hard to tell whether LLMs are planning or merely retrieving from their vast world knowledge. There is a strong need for systematic and extensible planning benchmarks with sufficient diversity to evaluate whether LLMs have innate planning capabilities. Motivated by this, we propose PlanBench, an extensible benchmark suite based on the kinds of domains used in the automated planning community, especially in the International Planning Competition, to test the capabilities of LLMs in planning or reasoning about actions and change. PlanBench provides sufficient diversity in both the task domains and the specific planning capabilities. Our studies also show that on many critical capabilities–including plan generation–LLM performance falls quite short, even with the SOTA models. PlanBench can thus function as a useful marker of progress of LLMs in planning and reasoning.

Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs as a source of heuristic guidance for other agents (AI planners) in their planning tasks. We conduct a systematic study by generating a suite of instances on domains similar to the ones employed in the International Planning Competition and evaluate LLMs in two distinct modes: autonomous and heuristic. Our findings reveal that LLMs’ ability to generate executable plans autonomously is rather limited, with the best model (GPT-4) having an average success rate of ~12% across the domains. However, the results in the heuristic mode show more promise. In the heuristic mode, we demonstrate that LLM-generated plans can improve the search process for underlying sound planners and additionally show that external verifiers can help provide feedback on the generated plans and back-prompt the LLM for better plan generation.

Despite the surprising power of many modern AI systems that often learn their own representations, there is significant discontent about their inscrutability and the attendant problems in their ability to interact with humans. While alternatives such as neuro-symbolic approaches have been proposed, there is a lack of consensus on what they are about. There are often two independent motivations (i) symbols as a lingua franca for human-AI interaction and (ii) symbols as (system-produced) abstractions use in its internal reasoning. The jury is still out on whether AI systems will need to use symbols in their internal reasoning to achieve general intelligence capabilities. Whatever the answer there is, the need for (human-understandable) symbols in human-AI interaction seems quite compelling. Symbols, like emotions, may well not be sine qua non for intelligence per se, but they will be crucial for AI systems to interact with us humans--as we can neither turn off our emotions not get by without our symbols. In particular, in many human-designed domains, humans would be interested in providing explicit (symbolic) knowledge and advice--and expect machine explanations in kind. This alone requires AI systems to at least do their I/O in symbolic terms. In this blue sky paper, we argue this point of view, and discuss research directions that need to be pursued to allow for this type of human-AI interaction.

In this work, we investigate and model how human trust affects monitoring. We present a web-based human subject study in which the robot is a worker and the human plays the role of a supervisor. First, we evaluate the correlation between the human trust and monitoring by using statistical tests, and then we learn probabilistic models of the behavioral data collected through our user studies. These models can provide us with the likelihood of a human user monitoring a system given their level of trust. Such models can be leveraged in many systems including the ones designed to be resilient to automation bias and complacency.

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for developing scalable approaches for solving long-horizon problems. While previous works have looked at the possibility of using symbolic models along with RL approaches, they tend to assume that the high-level action models are executable at low level and the fluents can exclusively characterize all desirable MDP states. Symbolic models of real world tasks are however often incomplete. To this end, we introduce Approximate Symbolic-Model Guided Reinforcement Learning, wherein we will formalize the relationship between the symbolic model and the underlying MDP that will allow us to characterize the incompleteness of the symbolic model. We will use these models to extract high-level landmarks that will be used to decompose the task. At the low level, we learn a set of diverse policies for each possible task subgoal identified by the landmark, which are then stitched together. We evaluate our system by testing on three different benchmark domains and show how even with incomplete symbolic model information, our approach is able to discover the task structure and efficiently guide the RL agent towards the goal.

Model-reconciliation explanation is a popular framework for generating explanations for planning problems. While the framework has been extended to multiple settings since its introduction for classical planning problems, there is little agreement on the computational complexity of generating minimal model reconciliation explanations in the basic setting. In this paper, we address this lacuna by introducing a decision-version of the model-reconciliation explanation generation problem and we show that it is Sigma-2-P Complete.

Automated Planning techniques can be leveraged to build effective decision support systems that assist the human-in-the-loop. Such systems must provide intuitive explanations when the suggestions made by these systems seem inexplicable to the human. In this regard, we consider scenarios where the user questions the system's suggestion by providing alternatives (referred to as foils). In response, we empower existing decision support technologies to engage in an interactive explanatory dialogue with the user and provide contrastive explanations based on user-specified foils to reach a consensus on proposed decisions. To provide contrastive explanations, we adapt existing techniques in Explainable AI Planning (XAIP). Furthermore, we use this dialog to elicit the user's latent preferences and propose three modes of interaction that use these preferences to provide revised plan suggestions. Finally, we showcase a decision support system that provides all these capabilities.

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under differing assumptions, thus precluding the possibility of designing a single framework that captures these measures under the same assumptions. In this paper, we present a unifying Bayesian framework that models a human observer's evolving beliefs about an agent and thereby define the problem of Generalized Human-Aware Planning. We will show that the definitions of interpretability measures like explicability, legibility and predictability from the prior literature fall out as special cases of our general framework. Through this framework, we also bring a previously ignored fact to light that the human-robot interactions are in effect open-world problems, particularly as a result of modeling the human's beliefs over the agent. Since the human may not only hold beliefs unknown to the agent but may also form new hypotheses about the agent when presented with novel or unexpected behaviors.

There is a growing interest in designing robots that can work alongside humans. Such robots will undoubtedly be expected to explain their behavior and decisions. While generating explanations is an actively researched topic, most works tend to focus on methods that generate explanations that are one size fits all. As in the specifics of the user-model are completely ignored. The handful of works that look at tailoring their explanation to the user’s background rely on having specific models of the users (either analytic models or learned labeling models). The goal of this work is thus to propose an end-to-end adaptive explanation generation system that begins by learning the different types of users that the robot could interact with. Then during the interaction with the target user, it is tasked with identifying the type on the fly and adjust its explanations accordingly. The former is achieved by a data-driven clustering approach while for the latter, we compile our explanation generation problem into a POMDP. We demonstrate the usefulness of our system on two domains using state-of-the-art POMDP solvers. We also report the results of a user study that investigates the benefits of providing personalized explanations in a human-robot interaction setting.

In this work, we present a new planning formalism called Expectation-Aware planning for decision making with humans in the loop where the human's expectations about an agent may differ from the agent's own model. We show how this formulation allows agents to not only leverage existing strategies for handling model differences like explanations (Chakraborti et al. 2017) and explicability (Kulkarni et al. 2019), but can also exhibit novel behaviors that are generated through the combination of these different strategies. Our formulation also reveals a deep connection to existing approaches in epistemic planning. Specifically, we show how we can leverage classical planning compilations for epistemic planning to solve Expectation-Aware planning problems. To the best of our knowledge, the proposed formulation is the first complete solution to planning with diverging user expectations that is amenable to a classical planning compilation while successfully combining previous works on explanation and explicability. We empirically show how our approach provides a computational advantage over our earlier approaches that rely on search in the space of models.

In this paper, we provide a comprehensive outline of the different threads of work in Explainable AI Planning (XAIP) that has emerged as a focus area in the last couple of years and contrast that with earlier efforts in the field in terms of techniques, target users, and delivery mechanisms. We hope that the survey will provide guidance to new researchers in automated planning towards the role of explanations in the effective design of human-in-the-loop systems, as well as provide the established researcher with some perspective on the evolution of the exciting world of explainable planning.

Designing robots capable of generating interpretable behavior is essential for effective human-robot collaboration. This requires robots to be able to generate behavior that aligns with human expectations but exhibiting such behavior in arbitrary environments could be quite expensive for robots, and in some cases, the robot may not even be able to exhibit expected behavior. However, in structured environments (like warehouses, restaurants, etc.), it may be possible to design the environment so as to boost the interpretability of a robot's behavior or to shape the human's expectations of the robot's behavior. In this paper, we investigate the opportunities and limitations of environment design as a tool to promote a particular type of interpretable behavior - known in the literature as explicable behavior. We formulate a novel environment design framework that considers design over multiple tasks and over a time horizon. In addition, we explore the longitudinal effect of explicable behavior and the trade-off that arises between the cost of design and the cost of generating explicable behavior over an extended time horizon.

Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same, and how the explanation process as a result of this mismatch can be then seen as a process of reconciliation of these models. Existing algorithms in such settings, while having been built on contrastive, selective and social properties of explanations as studied extensively in the psychology literature, have not, to the best of our knowledge, been evaluated in settings with actual humans in the loop. As such, the applicability of such explanations to human-AI and human-robot interactions remains suspect. In this paper, we set out to evaluate these explanation generation algorithms in a series of studies in a mock search and rescue scenario with an internal semi-autonomous robot and an external human commander. During that process, we hope to demonstrate to what extent the properties of these algorithms hold as they are evaluated by humans.

Recent work has formalized the explanation process in the context of automated planning as one of model reconciliation - i.e. a process by which the planning agent can bring the explainee's (possibly faulty) model of a planning problem closer to its understanding of the ground truth until both agree that its plan is the best possible. The content of explanations can thus range from misunderstandings about the agent's beliefs (state), desires (goals) and capabilities (action model). Though existing literature has considered different kinds of these model differences to be equivalent, literature on the explanations in social sciences has suggested that explanations with similar logical properties may often be perceived differently by humans. In this brief report, we explore to what extent humans attribute importance to different kinds of model differences that have been traditionally considered equivalent in the model reconciliation setting. Our results suggest that people prefer the explanations which are related to the effects of actions.

Human-aware planning involves generating plans that are explicable as well as providing explanations when such plans cannot be found. In this paper, we bring these two concepts together and show how an agent can achieve a trade-off between these two competing characteristics of a plan. In order to achieve this, we conceive a first of its kind planner MEGA that can augment the possibility of explaining a plan in the plan generation process itself. We situate our discussion in the context of recent work on explicable planning and explanation generation and illustrate these concepts in two well-known planning domains, as well as in a demonstration of a robot in a typical search and reconnaissance task. Human factor studies in the latter highlight the usefulness of the proposed approach.

Designing agents capable of explaining complex sequential decisions remains a significant open problem in human-AI interaction. Recently, there has been a lot of interest in developing approaches for generating such explanations for various decision-making paradigms. One such approach has been the idea of explanation as model-reconciliation. The framework hypothesizes that one of the common reasons for a user's confusion could be the mismatch between the user's model of the agent's task model and the model used by the agent to generate the decisions. While this is a general framework, most works that have been explicitly built on this explanatory philosophy have focused on classical planning settings where the model of user's knowledge is available in a declarative form. Our goal in this paper is to adapt the model reconciliation approach to a more general planning paradigm and discuss how such methods could be used when user models are no longer explicitly available. Specifically, we present a simple and easy to learn labeling model that can help an explainer decide what information could help achieve model reconciliation between the user and the agent with in the context of planning with MDPs.

Explainable planning is widely accepted as a prerequisite for autonomous agents to successfully work with humans. While there has been a lot of research on generating explanations of solutions to planning problems, explaining the absence of solutions remains an open and under-studied problem, even though such situations can be the hardest to understand or debug. In this paper, we show that hierarchical abstractions can be used to efficiently generate reasons for unsolvability of planning problems. In contrast to related work on computing certificates of unsolvability, we show that these methods can generate compact, human-understandable reasons for unsolvability. Empirical analysis and user studies show the validity of our methods as well as their computational efficacy on a number of benchmark planning domains.

There is a growing interest within the AI research community in developing autonomous systems capable of explaining their behavior to users. However, the problem of computing explanations for users of different levels of expertise has received little research attention. We propose an approach for addressing this problem by representing the user's understanding of the task as an abstraction of the domain model that the planner uses. We present algorithms for generating minimal explanations in cases where this abstract human model is not known. We reduce the problem of generating an explanation to a search over the space of abstract models and show that while the complete problem is NP-hard, a greedy algorithm can provide good approximations of the optimal solution. We also empirically show that our approach can efficiently compute explanations for a variety of problems.

Recent advances in mixed-reality technologies have renewed interest in alternative modes of communication for human-robot interaction. However, most of the work in this direction has been confined to tasks such as teleoperation, simulation or explication of individual actions of a robot. In this paper, we will discuss how the capability to project intentions affect the task planning capabilities of a robot. Specifically, we will start with a discussion on how projection actions can be used to reveal information regarding the future intentions of the robot at the time of task execution. We will then pose a new planning paradigm - projection-aware planning - whereby a robot can trade off its plan cost with its ability to reveal its intentions using its projection actions. We will demonstrate each of these scenarios with the help of a joint human-robot activity using the HoloLens.

Intelligent robots and machines are becoming pervasive in human populated environments. A desirable capability of these agents is to respond to goal-oriented commands by autonomously constructing task plans. However, such autonomy can add significant cognitive load and potentially introduce safety risks to humans when agents behave in unexpected ways. Hence, for such agents to be helpful, one important requirement is for them to synthesize plans that can be easily understood by humans. While there exists previous work that studied socially acceptable robots that interact with humans in “natural ways”, and work that investigated legible motion planning, there is no general solution for high level task planning. To address this issue, we introduce the notions of plan explicability and predictability. To compute these measures, first, we postulate that humans understand agent plans by associating abstract tasks with agent actions, which can be considered as a labeling process. We learn the labeling scheme of humans for agent plans from training examples using conditional random fields (CRFs). Then, we use the learned model to label a new plan to compute its explicability and predictability. These measures can be used by agents to proactively choose or directly synthesize plans that are more explicable and predictable to humans. We provide evaluations on a synthetic domain and with a physical robot to demonstrate the effectiveness of our approach.

When AI systems interact with humans in the loop, they are often called on to provide explanations for their plans and behavior. Past work on plan explanations primarily involved the AI system explaining the correctness of its plan and the rationale for its decision in terms of its own model. Such soliloquy is wholly inadequate in most realistic scenarios where the humans have domain and task models that differ significantly from that used by the AI system. We posit that the explanations are best studied in light of these differing models. In particular, we show how explanation can be seen as a "model reconciliation problem" (MRP), where the AI system in effect suggests changes to the human's model, so as to make its plan be optimal with respect to that changed human model. We will study the properties of such explanations, present algorithms for automatically computing them, and evaluate the performance of the algorithms.

In this brief abstract, we develop a computationally simpler version of the operator count heuristic for a particular class of domains. The contribution of this abstract is thus threefold, we (1) propose an efficient closed form approximation to the operator count heuristic; (2) leverage compressed sensing techniques to obtain an integer approximation in polynomial time; and (3) discuss the relationship of the proposed formulation to existing heuristics and investigate properties of domains where such approaches are useful.