My research seeks to answer the question of how any agent that is tasked with making sense of its world, by finding explanations for evidence (e.g., sensor reports) using domain-general strategies, may accurately and efficiently handle incomplete evidence, noisy evidence, and an incomplete knowledge base. I propose the following answer to the question. The agent should employ an optimal abductive reasoning algorithm (developed piece-wise and shown to be best in a class of similar algorithms) that allows it to reason from evidence to causes. For the sake of efficiency and operational concerns, the agent should establish beliefs periodically rather than waiting until it has obtained all evidence it will ever be able to obtain. If the agent commits to beliefs on the basis of incomplete or noisy evidence or an incomplete knowledge base, these beliefs may be incorrect. Future evidence obtained by the agent may result in failed predictions or anomalies. The agent is then tasked with determining whether it should retain its beliefs and therefore discount the newly-obtained evidence, revise its prior beliefs, or expand its knowledge base (what can be described as anomaly-driven or explanation-based learning). I have developed an abductive metareasoning procedure that aims to appropriately reason about these situations. Preliminary experiments in two reasoning tasks indicate that the procedure is effective.

Diverse planning consists of generating multiple different solutions for the same planning problem. I explore solution diversity, based on quantitative (domain-independent) and qualitative (domain-dependent) distance metrics, in deterministic and nondeterministic planning domains.

Businesses deploy chatter bots to engage in text-based conversations with customers that are intended resolve their issues. However, these chatter bots are only effective in exchanges consisting of question-answer pairs, where the context may switch with every pair. I am designing a semantic architecture that enables chatter bots to hold short conversations, where context is maintained throughout the exchange. I leverage specific ideas from conversation theory, speech acts theory, and knowledge representation. My architecture models a conversation as a stochastic process that flows through a set of states. The main contribution of this work is that it analyses and models the semantics of conversations as entities, instead of lower level grammatical and linguistics forms. I evaluate the performance of the architecture in accordance with Grice’s cooperative maxims, which form the central idea in the theory of pragmatics.

As of the writing of this abstract, the first stage is complete with respect to my Heuristic search is a technique used pervasively in the fields dissertation. The second stage will focus on the setting of of artificial intelligence, automated planning and operations off-line heuristic search where the entire plan is synthesized research to solve a wide range of problems from planning before any actions are executed. I will be near the completion military deployments to planning tasks for a robot that must of my work on second stage by the time of the AAAI clean a messy kitchen. An automated agent can use heuristic doctoral consortium. The third and final stage will focus on search to construct a plan that, when executed, will achieve planning under time pressure when planning and execution a desired task. The search algorithm explores different sequences of actions may happen concurrently. The remainder of this of actions that the agent can execute, looking for a abstract discusses these three topics in more detail.

Groups of robots are often able to to accomplish missions that no single robot can achieve by themselves. Teamwork is a very important factor in complex, dynamic domains. In heterogeneous teams, robustness and flexibility are increased by the diversity of the robots, each contributing different capabilities. In such heterogeneous Multi-Robot Systems it is reasonable to explicitly take the robots' capabilities into account when determining which one is best suited for a task. In this paper I present a framework that formalizes robots' capabilities and provides a means to estimate their suitability for a task. In highly unpredictable domains, accurate predictions of the outcomes of a robot's actions are virtually impossible. Approximate models and algorithms are required which help to estimate the outcome with highest possible confidence. The proposed architecture can provide estimates of task solution qualities at three levels of confidence: the lowest level only taking the mere existence of capabilities into account, the middle level considering task-specific details with approximate parameters of the capabilities, and the highest confidence level considering more elaborate planning algorithms.

A General Similarity Measurement (GSM), which takes into account of both non-temporal and rich temporal aspects including temporal order, temporal duration and temporal gap, is proposed for state-sequence matching. It is believed to be versatile enough to subsume representative existing measurements as its special cases.

Key challenges to widespread deployment of mobile robots to interact with humans in real-world domains include the ability to: (a) robustly represent and revise domain knowledge; (b) autonomously adapt sensing and processing to the task at hand; and (c) learn from unreliable high-level human feedback. Partially observable Markov decision processes (POMDPs) have been used to plan sensing and navigation in different application domains. It is however a challenge to include common sense knowledge obtained from sensory or human inputs in POMDPs. In addition, information extracted from sensory and human inputs may have varying levels of relevance to current and future tasks. On the other hand, although a non-monotonic logic programming paradigm such as Answer Set Programming (ASP) is wellsuited for common sense reasoning, it is unable to model the uncertainty in real-world sensing and navigation (Gelfond 2008). This paper presents a hybrid framework that integrates ASP, hierarchical POMDPs (Zhang and Sridharan 2012) and psychophysics principles to address the challenges stated above. Experimental results in simulation and on mobile robots deployed in indoor domains show that the framework results in reliable and efficient operation.

However, this approach usually requires expert users to write individual transformations for each data source manually. Figure 2: Delete grammar A variety of work (Kandel et al. 2011; Raman and Hellerstein 2001; Liang, Jordan, and Klein 2010) tries to take advantage of user input to solve the transformation problem, cally learn transformation rules through examples. As shown but these methods either cannot learn rules from training in Figure 1, a user might want to reverse the order of the date data or need the training data to contain all the intermediate and use hyphens to replace slashes. The user would just provide steps. We have developed an approach where the user the system with an example "30/07/2010" and "2010-only needs to provide the target value as an example.

We are developing a testbed for learning by demonstration combining spoken language and sensor data in a natural real-world environment. Microsoft Kinect RGB-Depth cameras allow us to infer high-level visual features, such as the relative position of objects in space, with greater precision and less training than required by traditional systems. Speech is recognized and parsed using a “deep” parsing system, so that language features are available at the word, syntactic, and semantic levels. We collected an initial data set of 10 episodes of 7 individuals demonstrating how to “make tea”, and created a “gold standard” hand annotation of the actions performed in each. Finally, we are constructing “baseline” HMM-based activity recognition models using the visual and language features, in order to be ready to evaluate the performance of our future work on deeper and more structured models.

This work presents a new algorithm based on the Bucket Elimination framework that efficiently determines strong controllability of temporal plans formulated as Labeled Simple Temporal Networks with Uncertainty (LSTNU) with controllable and uncontrollable plan branches (choices).