Validating and Refining Cognitive Process Models Using Probabilistic Graphical Models.

We describe a new approach for developing and validating cognitive process models. In our methodology, graphical models (specifically, hidden Markov models) are developed both from human empirical data on a task and synthetic data traces generated by a cognitive process model of human behavior on the task. Differences between the two graphical models can then be used to drive model refinement. We show that iteratively using this methodology can unveil substantive and nuanced imperfections of cognitive process models that can then be addressed to increase their fidelity to empirical data.

Evaluation of Goal Recognition Systems on Unreliable Data and Uninspectable Agents.

Goal or intent recognition, where one agent recognizes the goals or intentions of another, can be a powerful tool for effective teamwork and improving interaction between agents. Such reasoning can be challenging to perform, however, because observations of an agent can be unreliable and, often, an agent does not have access to the reasoning processes and mental models of the other agent. Despite this difficulty, recent work has made great strides in addressing these challenges. In particular, two Artificial Intelligence (AI)-based approaches to goal recognition have recently been shown to perform well: goal recognition as planning, which reduces a goal recognition problem to the problem of plan generation; and Combinatory Categorical Grammars (CCGs), which treat goal recognition as a parsing problem. Additionally, new advances in cognitive science with respect to Theory of Mind reasoning have yielded an approach to goal recognition that leverages analogy in its decision making. However, there is still much unknown about the potential and limitations of these approaches, especially with respect to one another. Here, we present an extension of the analogical approach to a novel algorithm, Refinement via Analogy for Goal Reasoning (RAGeR). We compare RAGeR to two state-of-the-art approaches which use planning and CCGs for goal recognition, respectively, along two different axes: reliability of observations and inspectability of the other agent's mental model. Overall, we show that no approach dominates across all cases and discuss the relative strengths and weaknesses of these approaches. Scientists interested in goal recognition problems can use this knowledge as a guide to select the correct starting point for their specific domains and tasks.

Shared control-based bimanual robot manipulation.

Human-centered environments provide affordances for and require the use of two-handed, or bimanual, manipulations. Robots designed to function in, and physically interact with, these environments have not been able to meet these requirements because standard bimanual control approaches have not accommodated the diverse, dynamic, and intricate coordinations between two arms to complete bimanual tasks. In this work, we enabled robots to more effectively perform bimanual tasks by introducing a bimanual shared-control method. The control method moves the robot's arms to mimic the operator's arm movements but provides on-the-fly assistance to help the user complete tasks more easily. Our method used a bimanual action vocabulary, constructed by analyzing how people perform two-hand manipulations, as the core abstraction level for reasoning about how to assist in bimanual shared autonomy. The method inferred which individual action from the bimanual action vocabulary was occurring using a sequence-to-sequence recurrent neural network architecture and turned on a corresponding assistance mode, signals introduced into the shared-control loop designed to make the performance of a particular bimanual action easier or more efficient. We demonstrate the effectiveness of our method through two user studies that show that novice users could control a robot to complete a range of complex manipulation tasks more successfully using our method compared to alternative approaches. We discuss the implications of our findings for real-world robot control scenarios.

An Account of Interference in Associative Memory: Learning the Fan Effect.

Associative learning is an essential feature of human cognition, accounting for the influence of priming and interference effects on memory recall. Here, we extend our account of associative learning that learns asymmetric item-to-item associations over time via experience (Thomson, Pyke, Trafton, & Hiatt, 2015) by including link maturation to balance associations between longer-term stability while still accounting for short-term variability. This account, combined with an existing account of activation strengthening and decay, predicts both human response times and error rates for the fan effect (Anderson, 1974; Anderson & Reder, 1999) for both target and foil stimuli.

Familiarity, Priming, and Perception in Similarity Judgments.

We present a novel way of accounting for similarity judgments. Our approach posits that similarity stems from three main sources-familiarity, priming, and inherent perceptual likeness. Here, we explore each of these constructs and demonstrate their individual and combined effectiveness in explaining similarity judgments. Using these three measures, our account of similarity explains ratings of simple, color-based perceptual stimuli that display asymmetry effects, as well as more complicated perceptual stimuli with structural properties; more traditional approaches to similarity solve one or the other and have difficulty accounting for both. Overall, our work demonstrates the importance of each of these components of similarity in explaining similarity judgments, both individually and together, and suggests important implications for other similarity approaches.