Artificial agents need to adapt in order to performeffectively in situations outside of their normal operation specifications.Agents that do not have the capability to adapt to unanticipated situations cannotrecover from unforeseen failures and hence are brittle systems. One approach todeal with the brittleness problem is to have a metacognitive component thatwatches the performance of a host agent and suggests corrective actions torecover from failures. This paper presents the architecture of a metacognitiveagent that can be integrated with any host cognitive agent so that theresulting system can dynamically create expectations about observations from ahost agent’s sensors, and make use of these expectations to notice expectationviolations, assess the cause of a violation and guide a correction if requiredto deal with the violation. The agent makes use of the metacognitive loop (MCL)and three generic ontologies — indications of failures, causes of failures andresponses to deal with failures. This paper describes the work undertaken toenhance the current version of an MCL based agent with the ability toautomatically generate expectations.

As humans, we live in a remarkably complex social environment. One cognitive tool which helps us manage all this complexity is our theory of mind, the ability to reason about the mental states of others. By deducing what other people want, feel and think, we can understand their actions, predict how our actions will influence them, and decide how we should behave to be successful. Theory of mind is the cognitive capacity to understand and predict external behavior of others and oneself by attributing internal mental states, such as knowledge, beliefs, and intentions [17]. This is thought to be the pinnacle of social cognition.

The AAAI-12 Workshop program was held Sunday and Monday, July 22–23, 2012 at the Sheraton Centre Toronto Hotel in Toronto, Ontario, Canada. The AAAI-12 workshop program included 9 workshops covering a wide range of topics in artificial intelligence. The titles of the workshops were Activity Context Representation: Techniques and Languages, AI for Data Center Management and Cloud Computing, Cognitive Robotics, Grounding Language for Physical Systems, Human Computation, Intelligent Techniques for Web Personalization and Recommendation, Multiagent Pathfinding, Neural-Symbolic Learning and Reasoning, Problem Solving Using Classical Planners, Semantic Cities. This article presents short summaries of those events.

David L. Waltz (1943-2012), was director, Center for Computational Learning Systems In 1973, Dave Waltz with Richard P. Gabriel in tow headed Dave Waltz delivers his AAAI Presidential Address at AAAI-98 in Madison, Wisconsin. While at Illinois, Dave produced system, paving the way for an engineering-style 11 Ph.D. students and many more MS students, approach to emergent AI techniques; and even mentored junior researchers and postdocs, attracted though their first attempts to create a multidisciplinary new AI faculty, and helped create the Beckman AI degree program failed, Dave was able in Institute for Advanced Science and Technology. In 1984, Marvin Minsky asked Dave to return to During the late 1970s and early 1980s, Waltz's Thinking Machines, Inc., an MIT spinoff in Cambridge group explored new ideas in natural language processing, -- with the temptation that the atmosphere cognitive science, qualitative reasoning, would be like the early days of the AI Lab all over and parallel computation in a collaborative environment again. At the same time he took a parttime including researchers in computer science, tenured position at Brandeis. Machines and Brandeis, Dave developed the ideas He chaired and brought the influential of massively parallel AI and, with Craig Stanfill, the Theoretical Issues in Natural Language Processing memory-based reasoning approach to case-based conference to Urbana in 1978.

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.

All aspects of cognitive robotics are of interest to the workshop, especially discussions and demonstrations of implemented systems. Research in robotics has traditionally emphasized low-level sensing and control tasks including sensory processing, path planning, and manipulator design and control. In contrast, research in cognitive robotics is concerned with endowing robots and soware agents with higher level cognitive functions that enable them to reason, act and perceive in changing, incompletely known, and unpredictable environments. Such robots must, for example, be able to reason about goals, actions, when to perceive and what to look for, the cognitive states of other agents, time, resources, collaborative task execution, etc. In short, cognitive robotics is concerned with integrating reasoning, perception, and action within a uniform theoretical and implementation framework (using methods drawn from logic, probability and decision theory, reinforcement learning, game theory, and so on).

We present a model of unsupervised learning in the hybrid SAL (Synthesis of ACT-R and Leabra) architecture. This model follows the hypothesis that higher evaluative cognitive mechanisms can serve to provide training signals for perceptual learning. This addresses the problem that supervised learning seems necessary for strong perceptual performance, but explicit feedback is rare in the real world and difficult to provide for artificial learning systems. The hybrid model couples the perceptual strengths of Leabra with ACT-R's cognitive mechanisms, specifically its declarative memory, to evolve its own symbolic representations of objects encountered in the world. This is accomplished by presenting the objects to the Leabra visual system and committing the resulting representation to ACT-R's declarative memory. Subsequent presentations are either recalled as instances of a previous object category, in which case the positive association with the representation is rehearsed by Leabra, or they cause ACT-R to generate new category labels, which are also subject to the same rehearsal. The rehearsals drive the network's representations to convergence for a given category; at the same time, rehearsals on the ACT-R side reinforce the chunks that encode the associations between representation and label. In this way, the hybrid model bootstraps itself into learning new categories and their associated features; this framework provides a potential approach to solving the symbol grounding problem. We outline the operations of the hybrid model, evaluate its performance on the CU3D-100 (cu3d.colorado.edu) image set, and discuss further potential improvements to the model, including the integration of motor functions as a way of providing an internal feedback signal to augment and guide a purely bottom-up unsupervised system.

One issue facing agents that accumulate large bodies of knowledge is determining whether they have knowl- edge that is relevant to its current goals. Performing comprehensive searches of long-term memory in every situation can be computationally expensive and disrup- tive to task reasoning. In this paper, we demonstrate that the recognition judgment — a heuristic for whether memory structures have been previously perceived — can serve as a low-cost indicator of the existence of potentially relevant knowledge. We present an approach for computing both context-dependent and context- independent recognition judgments using processes and data shared with declarative memories. We then de- scribe an initial, efficient implementation in the Soar cognitive architecture and evaluate our system in a word sense disambiguation task, showing that it reduces the number of memory searches without degrading agent performance.

ABSTRACT: The causal structure of cognition can be simulated but not implemented computationally, just as the causal structure of a furnace can be simulated but not implemented computationally. It lacks the essential causal property of a furnace. This is obvious with computational furnaces. The only thing that allows us even to imagine that it is otherwise in the case of computational cognition is the fact that cognizing, unlike heating, is invisible (to everyone except the cognizer). Chalmers's "Dancing Qualia" Argument is hence invalid: Even if there could be a computational model of cognition that was behaviorally indistinguishable from a real, feeling cognizer, it would still be true that if, like heat, feeling is a dynamical property of the brain, a flip-flop from the presence to the absence of feeling would be undetectable anywhere along Chalmers's hypothetical component-swapping continuum from a human cognizer to a computational cognizer -- undetectable to everyone except the cognizer. But that would only be because the cognizer was locked into being incapable of doing anything to settle the matter simply because of Chalmers's premise of input/output indistinguishability. That is not a demonstration that cognition is computation; it is just the demonstation that you get out of a premise what you put into it.

In this article, an enactive architecture is described that allows a humanoid robot to learn to compose simple actions into turn-taking behaviors while playing interaction games with a human partner. The robot's action choices are reinforced by social feedback from the human in the form of visual attention and measures of behavioral synchronization. We demonstrate that the system can acquire and switch between behaviors learned through interaction based on social feedback from the human partner. The role of reinforcement based on a short term memory of the interaction is experimentally investigated. Results indicate that feedback based only on the immediate state is insufficient to learn certain turn-taking behaviors. Therefore some history of the interaction must be considered in the acquisition of turn-taking, which can be efficiently handled through the use of short term memory.