The AAAI 2014 Fall Symposium Series was held Thursday through Saturday, November 13–15, at the Westin Arlington Gateway in Arlington, Virginia adjacent to Washington, DC. The titles of the seven symposia were Artificial Intelligence for Human-Robot Interaction, Energy Market Prediction, Expanding the Boundaries of Health Informatics Using AI, Knowledge, Skill, and Behavior Transfer in Autonomous Robots, Modeling Changing Perspectives: Reconceptualizing Sensorimotor Experiences, Natural Language Access to Big Data, and The Nature of Humans and Machines: A Multidisciplinary Discourse. The highlights of each symposium are presented in this report.

The program also included six keynote presentations, a funding panel, a community panel, and multiple breakout sessions. The keynote presentations, given by speakers that have been working on AI for HRI for many years, focused on the larger intellectual picture of this subfield. Each speaker was asked to address, from his or her personal perspective, why HRI is an AI problem and how AI research can bring us closer to the reality of humans interacting with robots on everyday tasks. Speakers included Rodney Brooks (Rethink Robotics), Manuela Veloso (Carnegie Mellon University), Michael Goodrich (Brigham Young University), Benjamin Kuipers (University of Michigan), Maja Mataric (University of Southern California), and Brian Scassellati (Yale University).

We study the computational complexity of candidate control in elections with few voters (that is, we take the number of voters as a parameter). We consider both the standard scenario of adding and deleting candidates, where one asks if a given candidate can become a winner (or, in the destructive case, can be precluded from winning) by adding/deleting some candidates, and a combinatorial scenario where adding/deleting a candidate automatically means adding/deleting a whole group of candidates. Our results show that the parameterized complexity of candidate control (with the number of voters as the parameter) is much more varied than in the setting with many voters.

We study the complexity of deciding if a given profile of incomplete votes (i.e., a profile of partial orders over a given set of alternatives) can be extended to a single-crossing profile of complete votes (total orders). This problem models settings where we have partial knowledge regarding voters' preferences and we would like to understand whether the given preference profile may be single-crossing. We show that this problem admits a polynomial-time algorithm when the order of votes is fixed and the input profile consists of top orders, but becomes NP-complete if we are allowed to permute the votes and the input profile consists of weak orders or independent-pairs orders. Also, we identify a number of practical special cases of both problems that admit polynomial-time algorithms.

In this paper a method to integrate inference and machine learning is proposed. Execution of learning algorithm is defined as a complex inference rule, which generates intrinsically new knowledge. Such a solution makes the reasoning process more creative and allows to re-conceptualize agent's experiences depending on the context. Knowledge representation used in the model is based on the Logic of Plausible Reasoning (LPR). Three groups of knowledge transmutations are defined: search transmutations that are looking for the information in data, inference transmutations that are formalized as LPR proof rules, and complex ones that can use machine learning algorithms or knowledge representation change operators. All groups can be used by inference engine in a similar manner. In the paper appropriate system model and inference algorithm are proposed. Additionally, preliminary experimental results are presented.

We present a system that produces emotionally rich poetry inspired by personalized and empathic interpretation of text, particularly Internet blogs. Our implemented system is based on the blackboard architecture, and generates poetry from a theme that it considers the most inspiring. It also incorporates a model of emotions with an individual optimism rate that defines an affective state. The poems produced by the system contain emotional expressions that describe these feelings. We explain how the system re-conceptualizes the text by the empathic interpretation of its content. We also present how the blackboard architecture may support divergent problem solving in the field of computational creativity.We describe the system architecture and the generation algorithm followed by some illustrative results. Finally, we mention possible continuation of this work by incorporating other language generating systems as well as human experts in the blackboard architecture.

An oft-touted mantra for creativity is: think like a child. We focus on one particular aspect of child-like thinking here, namely surface similarities. Developmental psychology has convincingly demonstrated, time and again, that younger children use surface similarities for categorization and related tasks; only as they grow older they start to consider functional and structural similarities. We consider examples of puzzles, research on creative problem solving, and two of our recent empirical studies to demonstrate how surface similarities can stimulate creative thinking. We examine the implications of this approach for designing creativity-support systems.

We believe that current research in creativity (especially in artificial intelligence and to a great extent psychology) focuses too much on the product and on exceptional (big-C) creativity. In this paper we want to argue that creative thinking and creative behavior result from the continuation of typical human cognitive development and that by looking into the early stages of this development, we can learn more about creativity. Furthermore, we wish to see analogy as a core mechanism in human cognitive development rather than a special skill among many. Some developmental psychology results that support this claim are reviewed. Analogy and metaphor are also seen as central for the creative process. Whereas mainstream research in artificial creativity and computational models of reasoning by analogy stresses the importance of matching the structure between the source and the target domains, we suggest that perceptual similarities play a much more important role, at least when it comes to creative problem solving. We provide some empirical data to support these claims and discuss their consequences.

We consider the problem of predicting winners in elections given complete knowledge about all possible candidates, all possible voters (together with their preferences), but in the case where it is uncertain either which candidates exactly register for the election or which voters cast their votes. Under reasonable assumptions our problems reduce to counting variants of election control problems. We either give polynomial-time algorithms or prove #P-completeness results for counting variants of control by adding/deleting candidates/voters for Plurality, k -Approval, Approval, Condorcet, and Maximin voting rules.

The conventional model of coalition formation considers every possible subset of agents as a potential coalition. However, in many real-world applications, there are inherent constraints on feasible coalitions: for instance, certain agents may be prohibited from being in the same coalition, or the coalition structure may be required to consist of coalitions of the same size. In this paper, we present the first systematic study of constrained coalition formation (CCF). We propose a general framework for this problem, and identify an important class of CCF settings, where the constraints specify which groups of agents should/should not work together. We describe a procedure that transforms such constraints into a structured input that allows coalition formation algorithms to identify, without any redundant computations, all the feasible coalitions. We then use this procedure to develop an algorithm for generating an optimal (welfare-maximizing) constrained coalition structure, and show that it outperforms existing state-of-the-art approaches by several orders of magnitude.