Subbarao Kambhampati's research while affiliated with Arizona State University and other places

Publications (448)

Conference Paper
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...
Article
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...
Preprint
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...
Preprint
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...
Preprint
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Article
In this paper, we show that popular Generative Adversarial Network (GAN) variants exacerbate biases along the axes of gender and skin tone in the generated data. The use of synthetic data generated by GANs is widely used for a variety of tasks ranging from data augmentation to stylizing images. While practitioners celebrate this method as an econom...
Preprint
Full-text available
Dealing with planning problems with both discrete logical relations and continuous numeric changes in real-world dynamic environments is challenging. Existing numeric planning systems for the problem often discretize numeric variables or impose convex quadratic constraints on numeric variables, which harms the performance when solving the problem....
Preprint
Full-text available
Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the RL-Agent from learning stably and efficiently. Since an optimal demonstration may also suffer from being ambiguous, previous work...
Preprint
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...
Preprint
When humans are given a policy to execute, there can be pol-icy execution errors and deviations in execution if there is un-certainty in identifying a state. So an algorithm that computesa policy for a human to execute ought to consider these effectsin its computations. An optimal MDP policy that is poorly ex-ecuted (because of a human agent) maybe...
Conference Paper
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...
Preprint
Full-text available
The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of properties, and developing them. There is also a lot of randomness from dice rolls, card-draws, and adversaries' strategies. This unpredictability is made worse when unk...
Article
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...
Article
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...
Preprint
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...
Preprint
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...
Preprint
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...
Preprint
Full-text available
This paper addresses the problem of synthesizing the behavior of an AI agent that provides proactive task assistance to a human in settings like factory floors where they may coexist in a common environment. Unlike in the case of requested assistance, the human may not be expecting proactive assistance and hence it is crucial for the agent to ensur...
Preprint
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...
Preprint
In this paper, we aim at providing a comprehensive outline of the different threads of work in human-AI collaboration. By highlighting various aspects of works on the human-AI team such as the flow of complementing, task horizon, model representation, knowledge level, and teaming goal, we make a taxonomy of recent works according to these dimension...
Chapter
Electric power grid components, such as high voltage transformers (HVTs), generating stations, substations, etc. are expensive to maintain and, in the event of failure, replace. Thus, regularly monitoring the behavior of such components is of utmost importance. Furthermore, the recent increase in the number of cyberattacks on such systems demands t...
Preprint
Full-text available
The future will be replete with scenarios where humans are robots will be working together in complex environments. Teammates interact, and the robot's interaction has to be about getting useful information about the human's (teammate's) model. There are many challenges before a robot can interact, such as incorporating the structural differences i...
Preprint
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...
Preprint
Full-text available
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...
Preprint
For humans in a teaming scenario, context switching between reasoning about a teammate's behavior and thinking about thier own task can slow us down, especially if the cognitive cost of predicting the teammate's actions is high. So if we can make the prediction of a robot-teammate's actions quicker, then the human can be more productive. In this pa...
Preprint
Electric power grid components, such as high voltage transformers (HVTs), generating stations, substations, etc. are expensive to maintain and, in the event of failure, replace. Thus, regularly monitoring the behavior of such components is of utmost importance. Furthermore, the recent increase in the number of cyberattacks on such systems demands t...
Preprint
The field of cybersecurity has mostly been a cat-and-mouse game with the discovery of new attacks leading the way. To take away an attacker's advantage of reconnaissance, researchers have proposed proactive defense methods such as Moving Target Defense (MTD). To find good movement strategies, researchers have modeled MTD as leader-follower games be...
Preprint
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...
Conference Paper
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...
Conference Paper
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...
Preprint
Deep Neural Networks are often brittle on image classification tasks and known to misclassify inputs. While these misclassifications may be inevitable, all failure modes cannot be considered equal. Certain misclassifications (eg. classifying the image of a dog to an airplane) can create surprise and result in the loss of human trust in the system....
Preprint
Full-text available
Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground truth but also some form of explanation. However, this kind of human guidance was only investigated in supervised...
Article
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...
Article
Network defenses based on traditional tools, techniques, and procedures (TTP) fail to account for the attacker’s inherent advantage present due to the static nature of network services and configurations. To take away this asymmetric advantage, Moving Target Defense (MTD) continuously shifts the configuration of the underlying system, in turn reduc...
Preprint
Full-text available
Network defense techniques based on traditional tools, techniques, and procedures fail to account for the attacker's inherent advantage present due to the static nature of network services and configurations. Moving Target Defense (MTD), on the other hand, provides an intelligent countermeasure by dynamically re-configuring the underlying systems,...
Article
Proactive Decision Support aims at improving the decision making experience of human decision-makers by enhancing the quality of the decisions and the ease of making them. Given that AI techniques are efficient in searching over a potentially large solution space (of decision) and finding good solutions, it can be used for human-in-the-loop scenari...
Preprint
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...
Preprint
The problem of multi-agent task allocation arises in a variety of scenarios involving human teams. In many such settings, human teammates may act with selfish motives and try to minimize their cost metrics. In the absence of (1) complete knowledge about the reward of other agents and (2) the team's overall cost associated with a particular allocati...
Preprint
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...
Preprint
Full-text available
Recently, the use of synthetic data generated by GANs has become a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to obtain synthetic data for training data-hungry machine learning models, it is not clear that they recognize the perils of such an augmentation technique when appl...
Chapter
Full-text available
The processing and storage of critical data in large-scale cloud networks necessitate the need for scalable security solutions. It has been shown that deploying all possible detection measures incur a cost on performance by using up valuable computing and networking resources, thereby resulting in Service Level Agreement (SLA) violations promised t...
Chapter
Present attack methods can make state-of-the-art classification systems based on deep neural networks mis-classify every adversarially modified test example. The design of general defense strategies against a wide range of such attacks still remains a challenging problem. In this paper, we draw inspiration from the fields of cybersecurity and multi...
Preprint
Full-text available
There is increasing awareness in the planning community that the burden of specifying complete domain models is too high, which impedes the applicability of planning technology in many real-world domains. Although there have many learning systems that help automatically learning domain models, most existing work assumes that the input traces are co...
Conference Paper
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...
Conference Paper
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...
Conference Paper
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...
Article
Users of AI systems may rely upon them to produce plans for achieving desired objectives. Such AI systems should be able to compute obfuscated plans whose execution in adversarial situations protects privacy, as well as legible plans which are easy for team members to understand in cooperative situations. We develop a unified framework that address...
Preprint
In order to be useful in the real world, AI agents need to plan and act in the presence of others, who may include adversarial and cooperative entities. In this paper, we consider the problem where an autonomous agent needs to act in a manner that clarifies its objectives to cooperative entities while preventing adversarial entities from inferring...
Preprint
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...
Preprint
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...
Preprint
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...
Preprint
Full-text available
In scenarios where a robot generates and executes a plan, there may be instances where this generated plan is less costly for the robot to execute but incomprehensible to the human. When the human acts as a supervisor and is held accountable for the robot's plan, the human may be at a higher risk if the incomprehensible behavior is deemed to be uns...
Conference Paper
The ability of an AI agent to build mental models can open up pathways for manipulating and exploiting the human in the hopes of achieving some greater good. In fact, such behavior does not necessarily require any malicious intent but can rather be borne out of cooperative scenarios. It is also beyond the scope of misinterpretation of intents, as i...
Conference Paper
The recent breakthroughs in Artificial Intelligence (AI) have allowed individuals to rely on automated systems for a variety of reasons. Some of these systems are the currently popular voice-enabled systems like Echo by Amazon and Home by Google that are also called as Intelligent Personal Assistants (IPAs). Though there are rising concerns about p...
Preprint
Full-text available
The processing and storage of critical data in large-scale cloud networks necessitate the need for scalable security solutions. It has been shown that deploying all possible security measures incurs a cost on performance by using up valuable computing and networking resources which are the primary selling points for cloud service providers. Thus, t...
Preprint
Human visual recognition of activities or external agents involves an interplay between high-level plan recognition and low-level perception. Given that, a natural question to ask is: can low-level perception be improved by high-level plan recognition? We formulate the problem of leveraging recognized plans to generate better top-down attention map...
Preprint
Full-text available
Existing work for plan trace visualization in automated planning uses pipeline-style visualizations, similar to plans in Gantt charts. Such visualization do not capture the domain structure or dependencies between the various fluents and actions. Additionally, plan traces in such visualizations cannot be easily compared with one another without par...
Preprint
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,...
Preprint
Full-text available
The use of synthetic data generated by Generative Adversarial Networks (GANs) has become quite a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to get more synthetic data that can be used to train downstream classifiers, it is not clear that they recognize the inherent pitfalls...
Conference Paper
Full-text available
A lot of software systems are deployed in the cloud. Owing to realistic demands for an early product launch, oftentimes there are vulnerabilities that are present in these deployed systems (or eventually found out). The cloud service provider can find and leverage this knowledge about known vulnerabilities and the underlying communication network t...
Conference Paper
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...
Conference Paper
Extracting action sequences from texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require either the set of candidate actions be provided in advance, or action descriptions are restricted to a specific form, e...