Plan Recognition Algorithm Research Articles

Probabilistic Plan Recognition for Multi-Agent Systems under Temporal Logic Tasks

This paper studies the plan recognition problem of multi-agent systems with temporal logic tasks. The high-level temporal tasks are represented as linear temporal logic (LTL). We present a probabilistic plan recognition algorithm to predict the future goals and identify the temporal logic tasks of the agent based on the observations of their states and actions. We subsequently build a plan library composed of Nondeterministic Bu¨chi Automation to model the temporal logic tasks. We also propose a Boolean matrix generation algorithm to map the plan library to multi-agent trajectories and a task recognition algorithm to parse the Boolean matrix. Then, the probability calculation formula is proposed to calculate the posterior goal probability distribution, and the cold start situation of the plan recognition is solved using the Bayes formula. Finally, we validate the proposed algorithm via extensive comparative simulations.

Models of Intervention: Helping Agents and Human Users Avoid Undesirable Outcomes.

When working in an unfamiliar online environment, it can be helpful to have an observer that can intervene and guide a user toward a desirable outcome while avoiding undesirable outcomes or frustration. The Intervention Problem is deciding when to intervene in order to help a user. The Intervention Problem is similar to, but distinct from, Plan Recognition because the observer must not only recognize the intended goals of a user but also when to intervene to help the user when necessary. We formalize a family of Intervention Problems and show that how these problems can be solved using a combination of Plan Recognition methods and classification algorithms to decide whether to intervene. For our benchmarks, the classification algorithms dominate three recent Plan Recognition approaches. We then generalize these results to Human-Aware Intervention, where the observer must decide in real time whether to intervene human users solving a cognitively engaging puzzle. Using a revised feature set more appropriate to human behavior, we produce a learned model to recognize when a human user is about to trigger an undesirable outcome. We perform a human-subject study to evaluate the Human-Aware Intervention. We find that the revised model also dominates existing Plan Recognition algorithms in predicting Human-Aware Intervention.

Comparing Plan Recognition Algorithms Through Standard Plan Libraries

Plan recognition deals with reasoning about the goals and execution process of an actor, given observations of its actions. It is one of the fundamental problems of AI, applicable to many domains, from user interfaces to cyber-security. Despite the prevalence of these approaches, they lack a standard representation, and have not been compared using a common testbed. This paper provides a first step towards bridging this gap by providing a standard plan library representation that can be used by hierarchical, discrete-space plan recognition and evaluation criteria to consider when comparing plan recognition algorithms. This representation is comprehensive enough to describe a variety of known plan recognition problems and can be easily used by existing algorithms in this class. We use this common representation to thoroughly compare two known approaches, represented by two algorithms, SBR and Probabilistic Hostile Agent Task Tracker (PHATT). We provide meaningful insights about the differences and abilities of these algorithms, and evaluate these insights both theoretically and empirically. We show a tradeoff between expressiveness and efficiency: SBR is usually superior to PHATT in terms of computation time and space, but at the expense of functionality and representational compactness. We also show how different properties of the plan library affect the complexity of the recognition process, regardless of the concrete algorithm used. Lastly, we show how these insights can be used to form a new algorithm that outperforms existing approaches both in terms of expressiveness and efficiency.

An event-driven plan recognition algorithm based on intuitionistic fuzzy theory

Plan recognition is a process of the observers inferring agents’ goal and planning by observing the agents’ behavior sequences. It is applied to image processing, network security and military domain. But the most prior work about plan recognition could not deal with fragmentary and small quantity of event information effectively and accurately. In this paper, we put forward an event-driven plan recognition method based on intuitionistic fuzzy theory. The algorithm based on recognizing the fuzzy event sequences is presented to forecast the future action about object. First, by analyzing the process and feature of plan recognition, we bring the master plan into sub-tasks which are a sequence of events, and then we create an algorithm about predicting the goal of the plan by recognizing the series of events. At the same time, thinking about the uncertainty of event, intuitionistic fuzzy theory is put into this model to eliminate the ambiguity of data. Finally, an experiment in military domain is testified for our approach.

A Novel Parsimonious Cause-Effect Reasoning Algorithm for Robot Imitation and Plan Recognition

Manually programming robots is difficult, impeding more widespread use of robotic systems. In response, efforts are being made to develop robots that use imitation learning. With such systems a robot learns by watching humans perform tasks. However, most imitation learning systems replicate a demonstrator’s actions rather than obtaining a deeper understanding of why those actions occurred. Here we introduce an imitation learning framework based on causal reasoning that infers a demonstrator’s intentions. As with imitation learning in people, our approach constructs an explanation for a demonstrator’s actions, and generates a plan based on this explanation to carry out the same goals rather than trying to faithfully reproduce the demonstrator’s precise motor actions. This enables generalization to new situations. We present novel causal inference algorithms for imitation learning and establish their soundness, completeness and complexity characteristics. Our approach is validated using a physical robot, which successfully learns and generalizes skills involving bimanual manipulation. Human performance on similar skills is reported. Computer experiments using the Monroe Plan Corpus further validate our approach. These results suggest that causal reasoning is an effective unifying principle for imitation learning. Our system provides a platform for exploring neural implementations of this principle in future work.

Sequential plan recognition: An iterative approach to disambiguating between hypotheses

Plan recognition algorithms output hypotheses about an agent's plans from its observed actions. Due to imperfect knowledge about the agent's behavior and the environment, it is often the case that there are multiple hypotheses about an agent's plans that are consistent with the observations, though only one of these hypotheses is correct. This paper addresses the problem of how to disambiguate between hypotheses during the recognition process, by querying the acting agent about whether a given plan is part of the correct hypothesis. The main contribution is a sound and complete process for reducing the set of possible hypotheses called Sequential Plan Recognition (SPR). SPR iteratively queries the user and revises the set of possible hypotheses according to the outcome of the query. Several policies are provided for choosing which plans to query the agent. These policies address the problem of how to reduce the number of hypotheses during the recognition process using a minimal number of queries. The proposed policies include policies that use maximum likelihood and information gain measures.The paper provides a complexity analysis of the SPR process and the proposed query policies. It demonstrate its efficiency on two known domains from the literature, describing how performance and runtime are affected by features in the domain. Our results can inform the design of future plan recognition systems that interleave the recognition process with intelligent interventions of their users.

Predicting Plan Failure by Monitoring Action Sequences and Duration

Anticipating failures in agent plan execution is important to enable an agent to develop strategies to avoid or circumvent such failures, allowing the agent to achieve its goal. Plan recognition can be used to infer which plans are being executed from observations of sequences of activities being performed by an agent. In this work, we use this symbolic plan recognition algorithm to find out which plan the agent is performing and develop a failure prediction system, based on plan library information and in a simplified calendar that manages the goals the agent has to achieve. This failure predictor is able to monitor the sequence of agent actions and detects if an action is taking too long or does not match the plan that the agent was expected to perform. We showcase this approach successfully in a health-care prototype system.

CRADLE

In exploratory domains, agents’ behaviors include switching between activities, extraneous actions, and mistakes. Such settings are prevalent in real world applications such as interaction with open-ended software, collaborative office assistants, and integrated development environments. Despite the prevalence of such settings in the real world, there is scarce work in formalizing the connection between high-level goals and low-level behavior and inferring the former from the latter in these settings. We present a formal grammar for describing users’ activities in such domains. We describe a new top-down plan recognition algorithm called CRADLE (Cumulative Recognition of Activities and Decreasing Load of Explanations) that uses this grammar to recognize agents’ interactions in exploratory domains. We compare the performance of CRADLE with state-of-the-art plan recognition algorithms in several experimental settings consisting of real and simulated data. Our results show that CRADLE was able to output plans exponentially more quickly than the state-of-the-art without compromising its correctness, as determined by domain experts. Our approach can form the basis of future systems that use plan recognition to provide real-time support to users in a growing class of interesting and challenging domains.

Plan Recognition for Exploratory Learning Environments Using Interleaved Temporal Search

This article presents new algorithms for inferring users' activities in a class of flexible and open‐ended educational software called exploratory learning environments (ELEs). Such settings provide a rich educational environment for students, but challenge teachers to keep track of students' progress and to assess their performance. This article presents techniques for recognizing students' activities in ELEs and visualizing these activities to students. It describes a new plan‐recognition algorithm that takes into account repetition and interleaving of activities. This algorithm was evaluated empirically using two ELEs for teaching chemistry and statistics used by thousands of students in several countries. It was able to outperform the state‐of‐the‐art plan‐recognition algorithms when compared to a gold standard that was obtained by a domain expert. We also show that visualizing students' plans improves their performance on new problems when compared to an alternative visualization that consists of a step‐by‐step list of actions.

Parallelizing Plan Recognition

Modern multicore computers provide an opportunity to parallelize plan recognition algorithms to decrease runtime. Viewing plan recognition as parsing based on a complete breadth first search, makes ELEXIR (engine for lexicalized intent recognition) (Geib 2009; Geib and Goldman 2011) particularly suited for parallelization. This article documents the extension of ELEXIR to utilize such modern computing platforms. We will discuss multiple possible algorithms for distributing work between parallel threads and the associated performance wins. We will show, that the best of these algorithms provides close to linear speedup (up to a maximum number of processors), and that features of the problem domain have an impact on the achieved speedup.

Research on Plan Recognition Based on Misleading Action Processing

As the application field of plan recognition expands continuously, the traditional plan recognition methods have hindered the application of plan recognition in hostile environment, which ignored the defects of misleading action. In this paper, a plan recognition algorithm based on the process of misleading action is proposed under the framework of plan knowledge graph. The method makes it possible to infer the action that is not observed by introducing the concept of the original reliability into the plan knowledge graph, and makes it possible to process the misleading action and wrong operation of the hostile agent by introducing the recognition process of the misleading action, which the method based on plan knowledge graph cannot achieved. The experimental results showed the algorithm in this paper greatly improved the accuracy of plan recognition by the process of the misleading action and it was with good performance. The algorithm has great significance for the application of plan recognition in the adversarial environment such as the intrusion detection, tactical planning, intelligence games etc.

Plan Recognition and Visualization in Exploratory Learning Environments

Modern pedagogical software is open-ended and flexible, allowing students to solve problems through exploration and trial-and-error. Such exploratory settings provide for a rich educational environment for students, but they challenge teachers to keep track of students’ progress and to assess their performance. This article presents techniques for recognizing students’ activities in such pedagogical software and visualizing these activities to teachers. It describes a new plan recognition algorithm that uses a recursive grammar that takes into account repetition and interleaving of activities. This algorithm was evaluated empirically using an exploratory environment for teaching chemistry used by thousands of students in several countries. It was always able to correctly infer students’ plans when the appropriate grammar was available. We designed two methods for visualizing students’ activities for teachers: one that visualizes students’ inferred plans, and one that visualizes students’ interactions over a timeline. Both of these visualization methods were preferred to and found more helpful than a baseline method which showed a movie of students’ interactions. These results demonstrate the benefit of combining novel AI techniques and visualization methods for the purpose of designing collaborative systems that support students in their problem solving and teachers in their understanding of students’ performance.

A plan classifier based on Chi-square distribution tests

To make good decisions in a social context, humans often need to recognize the plan underlying the behavior of others, and make predictions based on this recognition. This process, when carried out by software agents or robots, is known as plan recognition, or agent modeling. Most existing techniques for plan recognition assume the availability of carefully hand-crafted plan libraries, which encode the a-priori known behavioral repertoire of the observed agents; during run-time, plan recognition algorithms match the observed behavior of the agents against the plan-libraries, and matches are reported as hypotheses. Unfortunately, techniques for automatically acquiring plan-libraries from observations, e.g., by learning or data-mining, are only beginning to emerge. We present an approach for automatically creating the model of an agent behavior based on the observation and analysis of its atomic behaviors. In this approach, observations of an agent behavior are transformed into a sequence of atomic behaviors (events). This stream is analyzed in order to get the corresponding behavior model, represented by a distribution of relevant events. Once the model has been created, the proposed approach presents a method using a statistical test for classifying an observed behavior. Therefore, in this research, the problem of behavior classification is examined as a problem of learning to characterize the behavior of an agent in terms of sequences of atomic behaviors. The experiment results of this paper show that a system based on our approach can efficiently recognize different behaviors in different domains, in particular UNIX command-line data, and RoboCup soccer simulation.

Model and algorithmic framework for detection and correction of cognitive errors

This paper outlines an approach that we are taking for elder-care applications in the smart home, involving cognitive errors and their compensation. Our approach involves high level modeling of daily activities of the elderly by breaking down these activities into smaller units, which can then be automatically recognized at a low level by collections of sensors placed in the homes of the elderly. This separation allows us to employ plan recognition algorithms and systems at a high level, while developing stand-alone activity recognition algorithms and systems at a low level. It also allows the mixing and matching of multi-modality sensors of various kinds that go to support the same high level requirement. Currently our plan recognition algorithms are still at a conceptual stage, whereas a number of low level activity recognition algorithms and systems have been developed. Herein we present our model for plan recognition, providing a brief survey of the background literature. We also present some concrete results that we have achieved for activity recognition, emphasizing how these results are incorporated into the overall plan recognition system.

A probabilistic plan recognition algorithm based on plan tree grammars

We present the PHATT algorithm for plan recognition. Unlike previous approaches to plan recognition, PHATT is based on a model of plan execution. We show that this clarifies several difficult issues in plan recognition including the execution of multiple interleaved root goals, partially ordered plans, and failing to observe actions. We present the PHATT algorithm's theoretical basis, and an implementation based on tree structures. We also investigate the algorithm's complexity, both analytically and empirically. Finally, we present PHATT's integrated constraint reasoning for parametrized actions and temporal constraints.

Policy Recognition in the Abstract Hidden Markov Model

In this paper, we present a method for recognising an agent's behaviour in dynamic, noisy, uncertain domains, and across multiple levels of abstraction. We term this problem on-line plan recognition under uncertainty and view it generally as probabilistic inference on the stochastic process representing the execution of the agent's plan. Our contributions in this paper are twofold. In terms of probabilistic inference, we introduce the Abstract Hidden Markov Model (AHMM), a novel type of stochastic processes, provide its dynamic Bayesian network (DBN) structure and analyse the properties of this network. We then describe an application of the Rao-Blackwellised Particle Filter to the AHMM which allows us to construct an efficient, hybrid inference method for this model. In terms of plan recognition, we propose a novel plan recognition framework based on the AHMM as the plan execution model. The Rao-Blackwellised hybrid inference for AHMM can take advantage of the independence properties inherent in a model of plan execution, leading to an algorithm for online probabilistic plan recognition that scales well with the number of levels in the plan hierarchy. This illustrates that while stochastic models for plan execution can be complex, they exhibit special structures which, if exploited, can lead to efficient plan recognition algorithms. We demonstrate the usefulness of the AHMM framework via a behaviour recognition system in a complex spatial environment using distributed video surveillance data.

Monitoring Teams by Overhearing: A Multi-Agent Plan-Recognition Approach

Recent years are seeing an increasing need for on-line monitoring of teams of cooperating agents, e.g., for visualization, or performance tracking. However, in monitoring deployed teams, we often cannot rely on the agents to always communicate their state to the monitoring system. This paper presents a non-intrusive approach to monitoring by 'overhearing', where the monitored team's state is inferred (via plan-recognition) from team-members' *routine* communications, exchanged as part of their coordinated task execution, and observed (overheard) by the monitoring system. Key challenges in this approach include the demanding run-time requirements of monitoring, the scarceness of observations (increasing monitoring uncertainty), and the need to scale-up monitoring to address potentially large teams. To address these, we present a set of complementary novel techniques, exploiting knowledge of the social structures and procedures in the monitored team: (i) an efficient probabilistic plan-recognition algorithm, well-suited for processing communications as observations; (ii) an approach to exploiting knowledge of the team's social behavior to predict future observations during execution (reducing monitoring uncertainty); and (iii) monitoring algorithms that trade expressivity for scalability, representing only certain useful monitoring hypotheses, but allowing for any number of agents and their different activities to be represented in a single coherent entity. We present an empirical evaluation of these techniques, in combination and apart, in monitoring a deployed team of agents, running on machines physically distributed across the country, and engaged in complex, dynamic task execution. We also compare the performance of these techniques to human expert and novice monitors, and show that the techniques presented are capable of monitoring at human-expert levels, despite the difficulty of the task.

Evaluating Plan Recognition Systems: Three Properties of a Good Explanation

Plan recognition in a dialogue system is the process of explaining why an utterance was made, in terms of the plans and goals that its speaker was pursuing in making the utterance. I present a theory of how such an explanation of an utterance may be judged as to its merits as an explanation. I propose three criteria for making such judgments: applicability, grounding, and completeness. The first criterion is the applicability of the explanation to the needs of the system that will use it. The second criterion is the grounding of the explanation in what is already known of the speaker and of the dialogue. Finally, the third criterion is the completeness of the explanation's coverage of the goals that motivated the production of the utterance. An explanation of an utterance is a good explanation of that utterance to the extent that it meets these three criteria. In addition to forming the basis of a method for evaluating the merit of an explanation, these criteria are useful in designing and evaluating a plan recognition algorithm and its associated knowledge base.

Applying plan recognition algorithms to program understanding

Program understanding is often viewed as the task of extracting plans and design goals from program source. As such, it is natural to try to apply standard AI plan recognition techniques to the program understanding problem. Yet program understanding researchers have quietly, but consistently, avoided the use of these plan recognition algorithms. This paper shows that treating program understanding as plan recognition is too simplistic and that traditional AI search algorithms for plan recognition are not suitable. In particular, we show that: the program understanding task differs significantly from the typical general plan recognition task along several key dimensions; the program understanding task has particular properties that make it particularly amenable to constraint satisfaction techniques; and augmenting AI plan recognition algorithms with these techniques can lead to effective solutions for the program understanding problem.

On the interaction between plan recognition and intelligent interfaces

Plan recognition is an active research area in automatic reasoning, as well as a promising approach to engineering interfaces that can exploit models of user's plans and goals. Much research in the field has focused on the development of plan recognition algorithms to support particular user/system interactions, such as found in naturally occurring dialogues. However, two questions have typically remained unexamined: 1) exactly what kind of interface tasks can knowledge of a user's plans be used to support across communication modalities, and 2) how can such tasks in turn constrain development of plan recognition algorithms? In this paper we present a concrete exploration of these issues. In particular, we provide an assessment of plan recognition, with respect to the use of plan recognition in enhancing user interfaces. We clarify how use of a user model containing plans makes interfaces more intelligent and interactive (by providing an intelligent assistant that supports such tasks as advice generation, task completion, context-sensitive responses, error detection and recovery). We then show how interface tasks in turn provide constraints that must be satisfied in order for any plan recognizer to construct and represent a plan in ways that efficiently support these tasks. Finally, we survey how interfaces are fundamentally limited by current plan recognition approaches, and use these limitations to identify and motivate current research. Our research is developed in the context of CHECS, a plan-based design interface.