Sarath Sreedharan

• Doctor of Philosophy
• Professor (Assistant) at Colorado State University

From its inception, AI has had a rather ambivalent relationship with humans -- swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever increasing pace, there is a greater need for AI systems to work synergistically with humans. One critical requirement for such synergistic human-AI interactio...

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...

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 empiric...

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 perfor...

We are living through a revolutionary moment in AI history. Users from diverse walks of life are adopting and using AI systems for their everyday use cases at a pace that has never been seen before. However, with this proliferation, there is also a growing recognition that many of the central open problems within AI are connected to how the user in...

In this paper, we propose a planning framework to generate a defense strategy against an attacker who is working in an environment where the defender can operate covertly. Here the objective of the defender is to covertly guide the attacker to a trap state from which the attacker cannot achieve their goal. Further, the defender is constrained to ac...

We revisit two concepts popularly used within the context of classical planning, namely action justification and causal links. While these concepts have come to underpin some of the most popular notions of explanations in classical planning, these notions are restricted to sequential plans. To address this shortcoming, we propose a generalization o...

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...

This paper describes TOBY, a visualization tool that helps a user explore the contents of an academic survey paper. The visualization consists of four components: a hierarchical view of taxonomic data in the survey, a document similarity view in the space of taxonomic classes, a network view of citations, and a new paper recommendation tool. In thi...

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 o...

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 ine...

In this paper, we propose a planning framework to generate a defense strategy against an attacker who is working in an environment where a defender can operate without the attacker's knowledge. The objective of the defender is to covertly guide the attacker to a trap state from which the attacker cannot achieve their goal. Further, the defender is...

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) how good LLMs are by themselves in generating and validating simple plans in commonsense planning tasks (of the type that humans are generally quite good at)...

Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI. Unfortunately, most existing works in value alignment tend to focus on issues that are primarily related to the fact that...

Handling trust is one of the core requirements for facilitating effective interaction between the human and the AI agent. Thus, any decision-making framework designed to work with humans must possess the ability to estimate and leverage human trust. In this paper, we propose a mental model based theory of trust that not only can be used to infer tr...

There is a growing interest in developing automated agents that can work alongside humans. In addition to completing the assigned task, such an agent will undoubtedly be expected to behave in a manner that is preferred by the human. This requires the human to communicate their preferences to the agent. To achieve this, the current approaches either...

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 s...

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 abou...

The recent advances in large language models (LLMs) have transformed the field of natural language processing (NLP). From GPT-3 to PaLM, the state-of-the-art performance on natural language tasks is being pushed forward with every new large language model. Along with natural language abilities, there has been a significant interest in understanding...

Decision support systems seek to enable informed decision-making. In the recent years, automated planning techniques have been leveraged to empower such systems to better aid the human-in-the-loop. The central idea for such decision support systems is to augment the capabilities of the human-in-the-loop with automated planning techniques and enhanc...

There has been significant recent interest in developing AI agents capable of effectively interacting and teaming with humans. While each of these works try to tackle a problem quite central to the problem of human-AI interaction, they tend to rely on myopic formulations that obscure the possible inter-relatedness and complementarity of many of the...

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...

In the previous sections, we considered how in human-robot teaming scenarios, the robot behavior influences and is influenced by the human’s mental model of the robot. We have been quantifying some of the interaction between the behavior and human’s model in terms of three interpretability scores, each of which corresponds to some desirable propert...

In this chapter, the discussion will focus on another type of interpretable behavior, namely legibility. The notion of legibility allows the robot to implicitly communicate information about its goals, plans (or model, in general) to a human observer. For instance, consider a human robot cohabitation scenario consisting of a multi-tasking robot wit...

This book presents a concise introduction to recent research on human-aware decision-making, particularly ones focused on the generation of behavior that a human would find explainable or deceptive. Human-aware AI or HAAI techniques are characterized by the acknowledgment that for automated agents to successfully interact with humans, they need to...

In this chapter, we will focus the discussion on some of the behavioral and communication strategies that a robot can employ in adversarial environments. So far in this book, we have looked at how the robot can be interpretable to the human in the loop while it is interacting with her either through its behavior or through explicit communication. H...

All previous discussions on model-reconciliation explanations implicitly assume that the robot can communicate information about the model to the user. This suggests that the human and the robot share a common vocabulary that can be used to describe the model. However, this cannot be guaranteed unless the robots are using models that are specified...

In this section, we will look at four different applications that leverage the ideas discussed in this book. In particular, all the systems discussed in this chapter will explicitly model the human’s mental model of the task and among other things use it to generate explanations. In particular, we will look at two broad application domains. One whe...

In this chapter, we revisit the explicability score and investigate an alternate strategy to improve the explicability of the robot behavior, namely explanations. Rather than force the robot to choose behaviors that are inherently explicable in the human model, here we will let the robot choose a behavior optimal in its model and use communication...

In Chapter 2, among other things, we defined the notion of explicability of a plan and laid out an informal description of explicable planning. In this chapter, we will take a closer look at explicability and discuss some practical methods to facilitate explicable planning. This would include discussion on both planning algorithms specifically desi...

The previous chapter sketches out some of the central ideas behind generating an explanation as model reconciliation, but it does so while making some strong assumptions. Particularly, the setting assumes that the human’s model of the robot is known exactly upfront. In this chapter, we will look at how we can relax this assumption and see how we ca...

This chapter will act as the introduction to the technical discussions in the book. We will start by establishing some of the basic notations that we will use, including the definitions of deterministic goal-directed planning problems, incomplete planning models, sensor models, etc. With the basic notations in place, we will then focus on establish...

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 abou...

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...

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 users have domain and task models that differ from that used by the AI system. We posit that the explanations are b...

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 u...

There is a growing interest in designing autonomous agents that can work alongside humans. Such agents 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...

Operations in many essential industries including finance and banking are often characterized by the need to perform repetitive sequential tasks. Despite their criticality to the business, workflows are rarely fully automated or even formally specified, though there may exist a number of natural language documents describing these procedures for th...

There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for “explicable”, “legible”, “predictable” and “transparent” planning with overlapping, and sometimes conflicting,...

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...

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 cha...

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...

Existing approaches for the design of interpretable agent behavior consider different measures of interpretability in isolation. In this paper we posit that, in the design and deployment of human-aware agents in the real world, notions of interpretability are just some among many considerations; and the techniques developed in isolation lack two ke...

A new design of an AI assistant that has become increasingly popular is that of an "aggregated assistant" -- realized as an orchestrated composition of several individual skills or agents that can each perform atomic tasks. In this paper, we will talk about the role of planning in the automated composition of such assistants and explore how concept...

Empowering decision support systems with automated planning has received significant recognition in the planning community. The central idea for such systems is to augment the capabilities of the human-in-the-loop with automated planning techniques and provide timely support to enhance the decision-making experience. In addition to this, an effecti...

Designing robots capable of generating interpretable behavior is a prerequisite for achieving effective human-robot collaboration. This means that the robots need to be capable of generating behavior that aligns with human expectations and, when required, provide explanations to the humans in the loop. However, exhibiting such behavior in arbitrary...

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 rese...

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 rese...

As more and more people are expected to work with complex AI-systems, it becomes more important than ever that such systems provide intuitive explanations for their decisions. A prerequisite for holding such explanatory dialogue is the ability of the systems to present their proposed decisions to the user in an easy-to-understand form. Unfortunatel...

Recently, the D3WA system was proposed as a paradigm shift in how complex goal-oriented dialogue agents can be specified by taking a declarative view of design. However, it turns out actual users of the system have a hard time evolving their mental model and grasping the imperative consequences of declarative design. In this paper, we adopt ideas f...

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 (Cha...

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 rese...

As more and more complex AI systems are introduced into our day-to-day lives, it becomes important that everyday users can work and interact with such systems with relative ease. Orchestrating such interactions require the system to be capable of providing explanations and rationale for its decisions and be able to field queries about alternative d...

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 unders...

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 fr...

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 plann...

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 unders...

In this work, we formulate the process of generating explanations as model reconciliation for planning problems as one of planning with explanatory actions. We show that these problems could be better understood within the framework of epistemic planning and that, in fact, most earlier works on explanation as model reconciliation correspond to trac...

Designing agents capable of explaining complex sequential decisions remain a significant open problem in automated decision-making. 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 {\em explanation as model-reconciliatio...

There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for "explicable", "legible", "predictable" and "transparent" planning with overlapping, and sometimes conflicting,...

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 u...

Model reconciliation has been proposed as a way for an agent to explain its decisions to a human who may have a different understanding of the same planning problem by explaining its decisions in terms of these model differences.However, often the human's mental model (and hence the difference) is not known precisely and such explanations cannot be...

There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users. One aspect of the explanation generation problem that has yet to receive much attention is the task of explaining plans to users whose level of expertise differ from that of the explainer. We propose an approach...

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...

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 sc...

Human aware planning requires an agent to be aware of the intentions, capabilities and mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to a human observer as well as the ability to provide explanations when such plans cannot be generated. This has led to the notion "multi-mode...

Ambiguity and noise in natural language instructions create a significant barrier towards adopting autonomous systems into safety critical workflows involving humans and machines. In this paper, we propose to build on recent advances in electrophysiological monitoring methods and augmented reality technologies, to develop alternative modes of commu...

The ability to explain the rationale behind a planner's deliberative process is crucial to the realization of effective human-planner interaction. However, in the context of human-in-the-loop planning, a significant challenge towards providing meaningful explanations arises due to the fact that the actor (planner) and the observer (human) are likel...

Most current planners assume complete domain models and focus on generating correct plans. Unfortunately, domain modeling is a laborious and error-prone task, thus real world agents have to plan with incomplete domain models. While domain experts cannot guarantee completeness, often they are able to circumscribe the incompleteness of the model by p...

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 approximat...

In this paper, we develop a computationally simpler version of the operator count heuristic for a particular class of domains. The contribution of this abstract is threefold, we (1) propose an efficient closed form approximation to the operator count heuristic using the Lagrangian dual; (2) leverage compressed sensing techniques to obtain an intege...

One important challenge for a set of agents to achieve more efficient collaboration is for these agents to maintain proper models of each other. An important aspect of these models of other agents is that they are often not provided, and hence must be learned from plan execution traces. As a result, these models of other agents are inherently parti...