The SmartWheeler project is a multi-disciplinary initiative aimed at integrating state-of-the-art robotic and AI technologies for developing intelligent wheeled mobility platforms. The project is a collaboration between researchers, technicians and clinicians, from the fields of computer science, engineering and rehabilitation.The scientific goals of the project range from a sociological investigation of the needs for high-tech mobility solutions, to the development of machine learning algorithms to achieve robust communication, to AI techniques for socially adaptive path planning, to in-depth validation with clinically-functional outcomes. In this short paper, we outline some of the main contributions of the project in terms of integrating AI in the design and development of the intelligent wheelchair platform.

In this paper we outline the development of \Caesar{}, a domestic service robot with which we participated in the robot competition RoboCup@Home for many years. We sketch the system components, in particular the parts relevant to the high-level reasoning system, that make CAESAR an intelligent robot. We report on the development and discuss the lessons we learnt over the years designing, developing and maintaining an intelligent service robot. From our perspective of having participated in RoboCup@Home for a long time, we answer the core questions of the workshop about platforms, challenges and the evaluation of integrative research.

This paper introduces the novel problem of autonomous mobile-robot error recovery, namely the development of algorithms that enable a robot to extricate itself from a previously unseen trapped configuration.

Fuzzy logic is an important technique for modeling uncertainty in expert systems (i.e., in cases where inferencing of conclusion from given evidence is difficult to ascertain). This paper proposes a fuzzy expert system framework that combines case-based and rule-based reasoning effectively to produce a usable tool for Type 2 Diabetes Mellitus (T2DM) management. The major targets are on combined therapies (i.e., lifestyle and pharmacologic), and the recognition of management data dynamics (trends) during reasoning. The Knowledge base (KB) is constructed using fuzzified input values which are subsequently de-fuzziffied after reasoning, to produce crisp outputs to patients in the form of low-risk advice. The extended framework features a combined reasoning approach for simplified output in the form of decision support for clinicians. With seven operational input variables and two additional pre-set variables for testing, the results of the proposed work will be compared with other methods using similarity to expert’s decision as metrics.

The author discusses the relationship between symbolic play, abstract thinking, and divergent and associative thinking based on analogies, and finally connects symbolic play with the creative process. Play and the creative act are seen as similar by definition, since they are characterized as divergent, regulative, expressive and autotelic processes. Symbolic play is not only a product of the animistic and concrete logical way of thinking in childhood but also represents a mode of abstract thinking at the fictional symbolic level, which provides different options important for creativity development. Symbolic play is based on analogies with reality, and in this way reality is transformed in the imagination to be comprehended by the child. This transformation, which takes place in the nest of analogy at the symbolic level, is a key for creative production. Analogies in symbolic play are created through the divergent associative thinking process, also basic for any creative activity. The author has already used play as a tool to enhance creative behavior among young students in primary schools, and currently one project is being implemented in Serbia by the Institute for Educational Research with the intention of promoting initiative, cooperation and creativity by using play among other learning methods.

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.

Standard divergent thinking tasks, e.g., the Wallach-Kogan Tests (1965), and the Thinking Creatively in Action and Movement test (TCAM; Torrance, 1981) have verbal, representational, and imitative requirements limiting their use for children under 3 years. We present a new non-verbal, non-representational divergent thinking test that shows validity in relation to other standardized tests in 3- and 4-year-olds, and is also reliable for use with toddlers as young as 19 months. This research is of value in order to understand the early emergence of creativity. It could also aid research into Artificial Intelligence and robotics.

Swarm intelligence via its infamous struggle to identify a suitable balance between exploration and exploitation phases, provides a valuable mean to approach artificial creativity. This work deploys two swarm intelligence algorithms, one simulating the behaviour of birds flocking and fish schooling (Particle Swarm Optimisation) and the other mimicking the behaviour of ants foraging (Stochastic Diffusion Search) in order to lay the foundation for a discussion addressing the concepts of freedom and constraint within the topic of creativity in general, and more specifically their impact on the artificial creativity of the underlying systems. An analogy is drawn on mapping these two `prerequisites' of creativity onto the two well-known aforementioned phases of exploration and exploitation in swarm intelligence algorithms. This is accompanied by the visualisation of the behaviour of the swarms whose performance are evaluated in the context of the arguments presented. Additionally in the spirit of Searle's definition of weak and strong artificial intelligence, a discussion on weak vs. strong artificial creativity in swarm intelligence systems is presented.

Two features of microtext that challenge language processing tools are addressed in the context of linking messages in the emergency response domain. First, the effect of very short texts on several classifiers is estimated by comparing the results when classifiers are applied to the full text of news reports vs. only the headlines. These experiments demonstrate a decrease of 5 - 20% in accuracy. A second challenging feature of microtexts is their accumulation in real time, which can be massive for sources such as Twitter. A dynamic hierarchical clustering algorithm that clusters messages as they accumulate is described, and a preliminary experiment in clustering tweets is demonstrated.

Due to the vast amount of user-generated content in the emerging Web 2.0, there is a growing need for computational processing of sentiment analysis in documents. Most of the current research in this field is devoted to product reviews from websites. Microblogs and social networks pose even a greater challenge to sentiment classification. However, especially marketing and political campaigns leverage from opinions expressed on Twitter or other social communication platforms. The objects of interest in this paper are the presidential candidates of the Republican Party in the USA and their campaign topics. In this paper we introduce the combination of the noun phrases’ frequency and their PMI measure as constraint on aspect extraction. This compensates for sparse phrases receiving a higher score than those composed of high-frequency words. Evaluation shows that the meronymy relationship between politicians and their topics holds and improves accuracy of aspect extraction.