Goal-driven autonomy is an agent model for managing a dynamic environment by reasoning about current and potential goals while planning and acting. Since unexpected events and conditions may cause an agent’s goals and plans to become invalid or infeasible, an agent with goal-driven autonomy should monitor the environment against its expectations. Designed for dynamic, open, and partially observable environments, such an agent can create new goals or change its existing goals as needed. We present a formalisation of expectations for agents operating in these kinds of environments. Our formalisation includes situations where agents have the capability to sense the environment with some associated costs. We examine agent choices and behaviour in these domains and evaluate multiple approaches for selecting a subset of the agent’s sensing actions to execute. The contributions of this work are (1) a specification of different approaches to generating expectations; (2) a formalisation of the autonomy problem that minimises sensing costs; (3) a complexity analysis of the problem; (4) new algorithms for deciding which sensing actions to perform; and (5) empirical results demonstrating the benefit and cost of these approaches.

In part motivated by topics such as agency safety, there is an increasing interest in goal reasoning, a form of agency where the agents formulate their own goals. One of the crucial aspects of goal reasoning agents is their ability to detect if the execution of their courses of actions meet their own expectations. We present a taxonomy of different forms of expectations as used by goal reasoning agents when monitoring their own execution. We summarize and contrast the current understanding of how to define and check expectations based on different knowledge sources used. We also identify gaps in our understanding of expectations.

We present a metacognitive, integrated, dual-cycle architecture whose function is to provide agents with a greater capacity for acting robustly in a dynamic environment and managing unexpected events. We present MIDCA 1.3, an implementation of this architecture which explores a novel approach to goal generation, planning and execution given surprising situations. We formally define the mechanism and report empirical results from this goal generation algorithm. Finally, we describe the similarity between its choices at the cognitive level with those at the metacognitive.

We describe HTN‐MAKER, an algorithm for learning hierarchical planning knowledge in the form of task‐reduction methods for hierarchical task networks (HTNs). HTN‐MAKER takes as input a set of planning states from a classical planning domain and plans that are applicable to those states, as well as a set of semantically annotated tasks to be accomplished. The algorithm analyzes this semantic information to determine which portion of the input plans accomplishes a particular task and constructs task‐reduction methods based on those analyses. We present theoretical results showing that HTN‐MAKER is sound and complete. Our experiments in five well‐known planning domains confirm the theoretical results and demonstrate convergence toward a set of HTN methods that can be used to solve any problem expressible as a classical planning problem in that domain, relative to a set of goal types for which tasks have been defined. In three of the five domains, HTN planning with the learned methods scales much better than a modern classical planner.

Cervical cancer is the second most common type of cancer for women. Existing screening programs for cervical cancer, such as Pap Smear, suffer from low sensitivity. Thus, many patients who are ill are not detected in the screening process. Using images of the cervix as an aid in cervical cancer screening has the potential to greatly improve sensitivity, and can be especially useful in resource-poor regions of the world. In this paper, we develop a data-driven computer algorithm for interpreting cervical images based on color and texture. We are able to obtain 74% sensitivity and 90% specificity when differentiating high-grade cervical lesions from low-grade lesions and normal tissue. On the same dataset, using Pap tests alone yields a sensitivity of 37% and specificity of 96%, and using HPV test alone gives a 57% sensitivity and 93% specificity. Furthermore, we develop a comprehensive algorithmic framework based on Multimodal Entity Coreference for combining various tests to perform disease classification and diagnosis. When integrating multiple tests, we adopt information gain and gradient-based approaches for learning the relative weights of different tests. In our evaluation, we present a novel algorithm that integrates cervical images, Pap, HPV, and patient age, which yields 83.21% sensitivity and 94.79% specificity, a statistically significant improvement over using any single source of information alone.

Welcome to the Twenty-Fifth Annual Conference on the Innovative Applications of Artificial Intelligence (IAAI-13), the premier conference focusing on applied AI research ranging from exciting new potential ap- plications to innovative deployments of AI technology.

Diversity-aware planning consists of generating multiple plans which, while solving the same problem, are dissimilar from one another. Quantitative plan diversity is domain-independent and does not require extensive knowledge-engineering effort, but can fail to reflect plan differences that are relevant to users. Qualitative plan diversity is based on domain-specific characteristics, thus being of greater practical value, but may require substantial knowledge engineering. We demonstrate a domain-independent diverse plan generation method that is based on customizable plan distance metrics and amenable to both quantitative and qualitative diversity. Qualitative plan diversity is obtained with minimal knowledge-engineering effort, using distance metrics which incorporate domain-specific content.

We consider how to learn Hierarchical Task Networks (HTNs) for planning problems in which both the quality of solution plans generated by the HTNs and the speed at which those plans are found is important. We describe an integration of HTN Learning with Reinforcement Learning to both learn methods by analyzing semantic annotations on tasks and to produce estimates of the expected values of the learned methods by performing Monte Carlo updates. We performed an experiment in which plan quality was inversely related to plan length. In two planning domains, we evaluated the planning performance of the learned methods in comparison to two state-of-the-art satisficing classical planners, FastForward and SGPlan6, and one optimal planner, HSP*. The results demonstrate that a greedy HTN planner using the learned methods was able to generate higher quality solutions than SGPlan6 in both domains and FastForward in one. Our planner, FastForward, and SGPlan6 ran in similar time, while HSP* was exponentially slower.

A significant challenge in developing planning systems for practical applications is the difficulty of acquiring the domain knowledge needed by such systems. One method for acquiring this knowledge is to learn it from plan traces, but this method typically requires a huge number of plan traces to converge. In this paper, we show that the problem with slow convergence can be circumvented by having the learner generate solution plans even before the planning domain is completely learned. Our empirical results show that these improvements reduce the size of the training set that is needed to find correct answers to a large percentage of planning problems in the test set. 1.

A great challenge in developing planning systems for practical applications is the difficulty of acquiring the domain information needed to guide such systems. This paper describes a way to learn some of that knowledge. More specifically, the following points are discussed. (1) We introduce a theoretical basis for formally defining algorithms that learn preconditions for Hierarchical Task Network (HTN) methods. (2) We describe Candidate Elimination Method Learner (CaMeL), a supervised, eager, and incremental learning process for preconditions of HTN methods. We state and prove theorems about CaMeL's soundness, completeness, and convergence properties. (3) We present empirical results about CaMeL's convergence under various conditions. Among other things, CaMeL converges the fastest on the preconditions of the HTN methods that are needed the most often. Thus CaMeL's output can be useful even before it has fully converged.

This article presents case‐base maintenance policies for case index revision and case retention. The policies are formulated in the context of case‐based planners performing case adaptation by derivational replay. I implemented these policies on a particular case‐based planner and claim that my case‐index revision policy improves the accuracy of the retrieval and that the case‐retention policy filters redundant cases better than other case‐retention policies known from the literature. My claims are validated by empirical validation. It will be seen that there is an interrelation between the two policies that improves the filtering process of the case‐retention policy.