Our long-term goal is to develop autonomous robotic systems that have the cognitive abilities of humans, including communication, coordination, adapting to novel situations, and learning through experience. Our approach rests on the integration of the Soar cognitive architecture with both virtual and physical robotic systems. Soar has been used to develop a wide variety of knowledge-rich agents for complex virtual environments, including distributed training environments and interactive computer games. For development and testing in robotic virtual environments, Soar interfaces to a variety of robotic simulators and a simple mobile robot. We have recently made significant extensions to Soar that add new memories and new non-symbolic reasoning to Soar’s original symbolic processing, which improves Soar abilities for control of robots. These extensions include mental imagery, episodic and semantic memory, reinforcement learning, and continuous model learning. This paper presents research in mobile robotics, relational and continuous model learning, and learning by situated, interactive instruction.

A robot coexisting with humans must not only be able to successfully perform physical tasks, but must also be able to interact with humans in a socially appropriate manner. In many social settings, this involves the use of social signals like gaze, facial expression, and language. In this paper we discuss preliminary work focusing on the problem of combining social interaction with task-based action in a dynamic, multiagent bartending domain, using an embodied robot. We discuss how social states are inferred from low-level sensors, using vision and speech as input modalities, and present a planning approach that models task, dialogue, and social actions in a simple bartending scenario. This approach allows us to build interesting plans, which have been evaluated in a real-world study with human subjects, using a general purpose, off-the-shelf planner, as an alternative to more mainstream methods of interaction management.

Existing robot guides are able to offer a tour of a building, such as a museum, bank, science center, to a single person or to a group of participants. Usually the tours are predefined and there is no support for dynamic interactions between multiple robots. This paper focuses on distributed collaboration between several robot guides providing a building tour to groups of participants. Semantic techniques are adopted in order to formally define the tour topics, available content on a specific topic, and the robot and human profiles including their interests and content knowledge. The robot guides select different topics depending on their participants' interests and prior knowledge. Optimization of the topics of interests is achieved through exchange of participants between the robot guides whenever in each others neighborhood. Evaluation of the implemented algorithms presents a 90% content coverage of relevant topics for the individual participants.

Multi-agent path finding has been proven to be a PSPACE-hard problem. Generating such a centralised multi-agent plan can be avoided, by allowing agents to plan their paths separately. However, this results in an increased number of collisions and agents must re- plan frequently. In this paper we present a framework for multi-agent path planning, which allows agents to plan independently and solve conflicts locally when they occur. The framework is a generalisation of the CQ-learning algorithm which learns sparse interactions between agents in a multi-agent reinforcement learning setting

In an Artificial Intelligence course, a basic concept is Constraint Satisfaction (CS), which is acknowledged as a hard domain for teachers to teach and student to understand. In this paper, we present a game-based learning approach to assist students in learning CS algorithms, such as arc consistency and search algorithms, for problem solving in an easy, interactive and motivating way. Preliminary valuation has showed promising results.

In the field of probabilistic robotics, a central problem is to determine a robot's state given knowledge of a time series of control commands and sensor readings. The effects of control commands and the behavior of sensor devices are both modeled probabilistically. A variety of methods are available for deriving the robot's belief state, which is a probabilistic representation of the robot's true state (which cannot be directly known). This paper presents a series of five assignments to teach this material at the advanced undergraduate/graduate level. The theoretical aspect of the work is reinforced by practical implementation exercises using ROS (Robot Operating System), and the Bilibot, an educational robot platform.

The constraints arising from DAG models with latent variables can be naturally represented by means of acyclic directed mixed graphs (ADMGs). Such graphs contain directed and bidirected arrows, and contain no directed cycles. DAGs with latent variables imply independence constraints in the distribution resulting from a 'fixing' operation, in which a joint distribution is divided by a conditional. This operation generalizes marginalizing and conditioning. Some of these constraints correspond to identifiable 'dormant' independence constraints, with the well known 'Verma constraint' as one example. Recently, models defined by a set of the constraints arising after fixing from a DAG with latents, were characterized via a recursive factorization and a nested Markov property. In addition, a parameterization was given in the discrete case. In this paper we use this parameterization to describe a parameter fitting algorithm, and a search and score structure learning algorithm for these nested Markov models. We apply our algorithms to a variety of datasets.

Using the theory of group action, we first introduce the concept of the automorphism group of an exponential family or a graphical model, thus formalizing the general notion of symmetry of a probabilistic model. This automorphism group provides a precise mathematical framework for lifted inference in the general exponential family. Its group action partitions the set of random variables and feature functions into equivalent classes (called orbits) having identical marginals and expectations. Then the inference problem is effectively reduced to that of computing marginals or expectations for each class, thus avoiding the need to deal with each individual variable or feature. We demonstrate the usefulness of this general framework in lifting two classes of variational approximation for MAP inference: local LP relaxation and local LP relaxation with cycle constraints; the latter yields the first lifted inference that operate on a bound tighter than local constraints. Initial experimental results demonstrate that lifted MAP inference with cycle constraints achieved the state of the art performance, obtaining much better objective function values than local approximation while remaining relatively efficient.

Case vs control comparisons have been the classical approach to the study of neurological diseases. However, most patients will not fall cleanly into either group. Instead, clinicians will typically find patients that cannot be classified as having clearly progressed into the disease state. For those subjects, very little can be said about their brain function on the basis of analyses of group differences. To describe the intermediate brain function requires models that interpolate between the disease states. We have chosen Gaussian Processes (GP) regression to obtain a continuous spectrum of brain activation and to extract the unknown disease progression profile. Our models incorporate spatial distribution of measures of activation, e.g. the correlation of an fMRI trace with an input stimulus, and so constitute ultra-high multi-variate GP regressors. We applied GPs to model fMRI image phenotypes across Alzheimer's Disease (AD) behavioural measures, e.g. MMSE, ACE etc. scores, and obtained predictions at non-observed MMSE/ACE values. The overall model confirmed the known reduction in the spatial extent of activity in response to reading versus false-font stimulation. The predictive uncertainty indicated the worsening confidence intervals at behavioural scores distance from those used for GP training. Thus, the model indicated the type of patient (what behavioural score) that would need to included in the training data to improve models predictions.

A lot of effort has been invested into characterizing the convergence rates of gradient based algorithms for non-linear convex optimization. Recently, motivated by large datasets and problems in machine learning, the interest has shifted towards distributed optimization. In this work we present a distributed algorithm for strongly convex constrained optimization. Each node in a network of n computers converges to the optimum of a strongly convex, L-Lipchitz continuous, separable objective at a rate O(log (sqrt(n) T) / T) where T is the number of iterations. This rate is achieved in the online setting where the data is revealed one at a time to the nodes, and in the batch setting where each node has access to its full local dataset from the start. The same convergence rate is achieved in expectation when the subgradients used at each node are corrupted with additive zero-mean noise.