In Environment Design, one interested party seeks to affect another agent's decisions by applying changes to the environment. Most research on planning environment (re)design assumes the interested party's objective is to facilitate the recognition of goals and plans, and search over the space of environment modifications to find the minimal set of changes that simplify those tasks and optimise a particular metric. This search space is usually intractable, so existing approaches devise metric-dependent pruning techniques for performing search more efficiently. This results in approaches that are not able to generalise across different objectives and/or metrics. In this paper, we argue that the interested party could have objectives and metrics that are not necessarily related to recognising agents' goals or plans. Thus, to generalise the task of Planning Environment Redesign, we develop a general environment redesign approach that is metric-agnostic and leverages recent research on top-quality planning to efficiently redesign planning environments according to any interested party's objective and metric. Experiments over a set of environment redesign benchmarks show that our general approach outperforms existing approaches when using well-known metrics, such as facilitating the recognition of goals, as well as its effectiveness when solving environment redesign tasks that optimise a novel set of different metrics.

Implementations of the Belief-Desire-Intention (BDI) architecture have a long tradition in the development of autonomous agent systems. However, most practical implementations of the BDI framework rely on a pre-defined plan library for decision-making, which places a significant burden on programmers, and still yields systems that may be brittle, struggling to achieve their goals in dynamic environments. This paper overcomes this limitation by introducing an operational semantics for BDI systems that rely on Classical Planning at run time to both cope with failures that were unforeseeable and synthesise new plans that were unspecified at design time. This semantics places particular emphasis on the interaction of the reasoning cycle and an underlying planning algorithm. We empirically demonstrate the practical feasibility and generality of such an approach in an implementation of this semantics within two popular BDI platforms together with in-depth computational evaluation.

Abstract Goal Recognitionis the task of discerning the intended goal that an agent aims to achieve, given a set of goal hypotheses, a domain model, and a sequence of observations (i.e., a sample of the plan executed in the environment). Existing approaches assume that goal hypotheses comprise a single conjunctive formula over a single final state and that the environment dynamics are deterministic, preventing the recognition of temporally extended goals in more complex settings. In this paper, we expand goal recognition totemporally extended goalsinFully Observable Non-Deterministic(fond) planning domain models, focusing on goals on finite traces expressed inLinear Temporal Logic(ltl $$_f$$ f ) andPure-Past Linear Temporal Logic(ppltl). We develop the first approach capable of recognizing goals in such settings and evaluate it using differentltl $$_f$$ f andppltlgoals over sixfondplanning domain models. Empirical results show that our approach is accurate in recognizing temporally extended goals in different recognition settings.

Goal Recognition is the task of discerning the intended goal of an agent given a sequence of observations, whereas Plan Recognition consists of identifying the plan to achieve such intended goal. Regardless of the underlying techniques, most recognition approaches are directly affected by the quality of the available observations. In this paper, we develop neuro-symbolic recognition approaches that can combine learning and planning techniques, compensating for noise and missing observations using prior data. We evaluate our approaches in standard human-designed planning domains as well as domain models automatically learned from real-world data. Empirical experimentation shows that our approaches reliably infer goals and compute correct plans in the experimental datasets. An ablation study shows that outperform approaches that rely exclusively on the domain model, or exclusively on machine learning in problems with both noisy observations and low observability.

The use of multi-queue heuristic search and tie-breaking strategies has shown to be very effective for satisficing planning in the Classical Planning setting. However, to the best of our knowledge, the use of such techniques has never been studied and employed in heuristic search algorithms for Fully Observable Non-Deterministic (FOND) Planning. In this paper, we adapt existing satisficing techniques for scaling-up an AND/OR heuristic search algorithm for FOND Planning. Namely, we employ multi-queue heuristic search, dead-end detection, and tie-breaking strategies in LAO* for improving the extraction of strong-cyclic policies. We assess the efficiency of our techniques in LAO* through an extensive ablation study over two different FOND Planning benchmarks. Empirical results show that our techniques improve the performance of LAO* in terms of coverage, expanded nodes, and planning time compared to a well-known planner based on vanilla LAO*. Indeed, the best configuration of our techniques is competitive with the current state-of-the-art in FOND Planning.

Plan Recognition is the task of identifying the goals and plans of an agent by observing its behavior within the environment. The problem has been extensively studied in the context of planning, in particular bringing forward stochastic techniques dealing with probability distributions over the possible agent goals, under the assumption that observations are reliable. More recently, a connection between this problem and process mining techniques has been established, paving the way towards the application of alignment-based conformance checking techniques from process mining to tackle plan recognition problems in a setting where observations may be faulty. In this work, we reconcile these two lines of research in a unified framework that deals at once with uncertainty over the goals and the faithfulness of observations. Instead of using ad-hoc techniques to solve this problem, we cast it as a probabilistic trace alignment problem, trading off between the similarity of observations and plans, and the likelihood that the agent is performing those plans. We assess the effectiveness of our approach by conducting a comparative experimental evaluation on state-of-the-art benchmarks.

Goal recognition aims to recognize the set of candidate goals that are compatible with the observed behavior of an agent. In this paper, we develop a method based on the operator-counting framework that efficiently computes solutions that satisfy the observations and uses the information generated to solve goal recognition tasks. Our method reasons explicitly about both partial and noisy observations: estimating uncertainty for the former, and satisfying observations given the unreliability of the sensor for the latter. We evaluate our approach empirically over a large data set, analyzing its components on how each can impact the quality of the solutions. In general, our approach is superior to previous methods in terms of agreement ratio, accuracy, and spread. Finally, our approach paves the way for new research on combinatorial optimization to solve goal recognition tasks.

Goal Recognition is the task of inferring an agent's goal, from a set of hypotheses, given a model of the environment dynamic, and a sequence of observations of such agent's behavior. While research on this problem gathered momentum as an offshoot of plan recognition, recent research has established it as a major subject of research on its own, leading to numerous new approaches that both expand the expressivity of domains in which to perform goal recognition and substantial advances to the state-of-the-art on established domain types. In this survey, we focus on the advances to goal recognition achieved in the last decade, categorizing the resulting techniques and identifying a number of opportunities for further breakthrough research.

Goal recognition is the task of identifying the goal an observed agent is pursuing. The quality of its results depends on the quality of the observed information. In most goal recognition approaches, the accuracy significantly decreases in settings with missing observations. To mitigate this issue, we develop a learning model based on LSTMs, leveraging attention mechanisms, to enhance observed traces by predicting missing observations in goal recognition problems. We experiment using a dataset of goal recognition problems and apply the model to enhance the observation traces where missing. We evaluate the technique using a state-of-the-art goal recognizer in four different domains to compare the accuracy between the standard and the enhanced observation traces. Experimental evaluation shows that recurrent neural networks with self-attention mechanisms improve the accuracy metrics of state-of-the-art goal recognition techniques by an average of 60%.

Assessing whether an agent has abandoned a goal or is actively pursuing it is important when multiple agents are trying to achieve joint goals, or when agents commit to achieving goals for each other. Making such a determination for a single goal by observing only plan traces is not trivial, as agents often deviate from optimal plans for various reasons, including the pursuit of multiple goals or the inability to act optimally. In this article, we develop an approach based on domain independent heuristics from automated planning, landmarks, and fact partitions to identify sub-optimal action steps—with respect to a plan—within a fully observable plan execution trace. Such capability is very important in domains where multiple agents cooperate and delegate tasks among themselves, such as through social commitments , and need to ensure that a delegating agent can infer whether or not another agent is actually progressing towards a delegated task. We demonstrate how a creditor can use our technique to determine—by observing a trace—whether a debtor is honouring a commitment. We empirically show, for a number of representative domains, that our approach infers sub-optimal action steps with very high accuracy and detects commitment abandonment in nearly all cases.

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

Recent approaches to goal recognition have progressively relaxed the assumptions about the amount and correctness of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume completeness and correctness of the domain theory against which their algorithms match observations: this is too strong for most real-world domains. In this work, we develop a goal recognition technique capable of recognizing goals using incomplete (and possibly incorrect) domain theories.

Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. We show the effectiveness of the technique in a number of domains and compare the recognition effectiveness of the autoencoded against hand-coded versions of these domains.

Automated planning can be used to efficiently recognize goals and plans from partial or full observed action sequences. In this paper, we propose goal recognition heuristics that rely on information from planning landmarks - facts or actions that must occur if a plan is to achieve a goal when starting from some initial state. We develop two such heuristics: the first estimates goal completion by considering the ratio between achieved and extracted landmarks of a candidate goal, while the second takes into account how unique each landmark is among landmarks for all candidate goals. We empirically evaluate these heuristics over both standard goal/plan recognition problems, and a set of very large problems. We show that our heuristics can recognize goals more accurately, and run orders of magnitude faster, than the current state-of-the-art.

Recognition of goals and plans using incomplete evidence from action execution can be done efficiently by using planning techniques. In many applications it is important to recognize goals and plans not only accurately, but also quickly. In this paper, we develop a heuristic approach for recognizing plans based on planning techniques that rely on ordering constraints to filter candidate goals from observations. These ordering constraints are called landmarks in the planning literature, which are facts or actions that cannot be avoided to achieve a goal. We show the applicability of planning landmarks in two settings: first, we use it directly to develop a heuristic-based plan recognition approach; second, we refine an existing planning-based plan recognition approach by pre-filtering its candidate goals. Our empirical evaluation shows that our approach is not only substantially more accurate than the state-of-the-art in all available datasets, it is also an order of magnitude faster.