ion built in (Price’s [116] “[e]ncapsulate complex behavior within a component” or their use of function labels to simplify the output; Iwasaki et al.’s [78] model fragments), but their simulations and thus verifications produce results for the entire model in one chunk or otherwise, like with [78], are producing output for a specific aspect of themodel. Simulation enables individual verifications to stay focused on one function or one behavior at a time even if the functional decomposition is very large while not requiring that a user scope the verification themselves. This automatic focusing should make results to handle compared to those that produce output for the entire model. Additionally, DESC is a step towards the “[m]ulti-level modelling” mentioned by Price et al. [117] as necessary to achieve future targets for qualitative reasoning. Second, DESC leverages the same causal process representation (state diagrams, a.k.a., behaviors) in SBF* for both reasoning and representing simulation results, whereas other work uses representations for reasoning (e.g., component models or model fragments) that differ from the state-based representations in their simulation results. From the perspective of SBF* modeling, DESC thus does not require modelers to learn a new representation for reasoning since it leverages aspects of the models that are already part of the SBF* models being built–with the exceptions that modelers will need to learn equation syntax and simulation semantics (although the latter should be generally intuitive relative to modeling expectations). Additionally, that the verification results are couched in terms of the alreadymodeled elements (i.e., as issues in state conditions and function provides conditions) should lessen the cognitive burden relative to other systems because users do not need to learn a second representation to interpret the results as they would if one built a component model and then interpreted state-based representation results. DESC also differs from [78, 116] by incorporating functions into the simulation. They impact the simulation process by acting as pointers to subbehaviors rather than just being used in evaluation/output. This empowers the simulator to use existing structural aspects of the model (i.e., the functional decomposition) in its reasoning, which should also, in the

Creative problems are ill-defined, and thus experimentation, evaluation, and iteration are key elements of creative problem solving. We present a computational theory of evaluation in creative design. Our technique evaluates a design concept by analogically comparing it with alternative articulations of the concept. We operationalize this theory of analogical comparison in the context of biologically inspired design that uses biological analogies for conceptual design of technological systems. Our technique of analogical comparison supports evaluation of prior technological designs, biological source cases, as well as candidate conceptual designs through analogical mapping between alternative functional models of these design concepts. Given a functional model of a design concept and an alternative functional model of the same design concept, analogical comparison leverages a novel hierarchically organized analogical mapping technique to align the two models and identify the differences between them. Our technique is implemented in an operational artificial intelligence agent called Design Evaluation through Simulation and Comparison (DESC). We evaluate DESC through computational experimentation across several models to illustrate its strengths and limits and to highlight areas for future research.

Evaluation is a key task in design, and a major goal in research on computational design is to develop techniques for evaluating design concepts throughout the design process, starting as early as possible. Conceptual design in engineering is abstracted as a function-to-structure mapping and engages the use of functional models of design candidates. This suggests functional model simulation as a method for early evaluation of these alternatives. We describe a computational technique that evaluates such candidates in the conceptual phase through simulation of hierarchically organized Structure-Behavior-Function models. We demonstrate the capabilities of our technique for evaluation in biologically inspired system design that uses biological analogues to address design problems.

We describe an experiment in using IBM’s Watson tool in a Georgia Tech Spring 2015 class on compu-tational creativity. The semester-long projects in the class used Watson as a tool to develop cognitive assistants in support of biologically inspired design, a well-established paradigm for design creativity. In this paper, we describe the experiment in using Watson as a creativity support tool and present two projects in detail. We draw lessons for using Watson for constructing cognitive assistants to support design creativity.

We describe an experiment in using IBM’s Watson tool to construct cognitive assistants in a Georgia Tech Spring 2015 class on computational creativity. The project-based class used Watson to support biologically inspired design, a paradigm that uses biological systems as analogues for inventing technological systems. The students worked in small teams and developed semester-long projects that used Watson to build cognitive assistants for conducting research in support of biologically inspired design. In this paper, we describe this experiment in using Watson, present two of the projects in detail, draw best practices for using Watson, and characterize and critique the Watson tool for constructing cognitive assistants. 1. Background and Motivations In 2011 IBM’s Watson system surprised and delighted much of the world by winning the game show Jeopardy! against human opponents. Since then IBM has claimed Watson to be a “cognitive system” that has ushered in an era of “cognitive computing” (Kelly & Hamm 2013). It has published several articles on Watson (e.g., Brown et al. 2013; Ferruci et al. 2010; Kalyanpur & Murdock 2015), including a special issue of the IBM Journal of Research and Development (e.g., Ferruci 2012). In addition, it has incrementally provided access to various versions of Watson, starting with the skeletal Watson Engagement Advisor (n.d.) that is freely available to most faculty and students for educational purposes, and recently, the more robust Bluemix Platform (n.d.) that provides access to various components of Watson as services and is available to most anyone for most any purpose but typically at a charge. Given the large-scale IBM publicity and investment, Watson has come to exemplify cognitive systems in much of the popular media. Yet, at least outside IBM, our understanding of Watson remains modest. The articles published by IBM often go into enormous algorithmic and representational detail on selected technical issues, but typically leave out both critical elements of the representations and algorithms as well

We describe an interactive tool called the Design Study Library (DSL) that provides access to a digital library of case studies of biologically inspired design. Each case study in DSL describes a project in biologically inspired design from the inception of a design problem to the completion of a conceptual design. The approximately 70 case studies in DSL come from several years of collaborative design projects in an interdisciplinary class on biologically inspired design. Compilation of these case studies enables deeper analysis of biologically inspired design projects. An analysis of some 40 case studies indicates that environmental sustainability was a major factor in about two thirds of the projects. DSL also appears to support learning about biologically inspired design. Preliminary results from a small, formative pilot study indicate that DSL supports learning about the processes of biologically inspired design.

Digital libraries of case studies of analogical design have been popular since their advent in the early 1990s. We consider four benefits of digital libraries of case studies of analogical design in the context of biologically inspired design. First, a digital library affords documentation. The 83 case studies in our work come from 8 years of extended, collaborative design projects in an interdisciplinary class on biologically inspired design. Second, a digital library provides on-demand access to the case studies. We describe a web-based library of case studies of biologically inspired design called the Design Study Library (DSL). Third, a compilation of case studies supports analyses of broader patterns and trends. As an example, an analysis of DSL's case studies found that environmental sustainability was a major factor in about a third of the case studies and an explicit design goal in about a fourth. Fourth, a digital library of case studies can support analogical learning. Preliminary results from an exploratory study indicate that DSL may support novice learning about the processes of biologically inspired design.

In Biologically Inspired Design (BID), engineers use biology as a source of ideas for solving engineering problems. However, locating relevant literature is difficult due to vocabulary differences and lack of domain knowledge. IBID is an intelligent search mechanism that uses a functional taxonomy to direct search and a formal modeling notation for annotating relevant search targets.

We describe an experiment in using IBM’s Watson cognitive system to teach about human-computer co-creativity in a Georgia Tech Spring 2015 class on computational creativity. The project-based class used Watson to support biologically inspired design, a design paradigm that uses biological systems as analogues for inventing technological systems. The twenty-four students in the class selforganized into six teams of four students each, and developed semester-long projects that built on Watson to support biologically inspired design. In this paper, we describe this experiment in using Watson to teach about human-computer co-creativity, present one project in detail, and summarize the remaining five projects. We also draw lessons on building on Watson for (i) supporting biologically inspired design, and (ii) enhancing human-computer co-creativity. Background, Motivations and Goals Creativity is one of humanity’s most special traits and resources as well as goals and ideals. Humans are creative as individuals, as societies, and as a species. It is human creativity that leads to visual and performance arts, scientific discoveries and technological inventions, social and cultural movements as well as political and economic revolutions. Successful business organizations value creative people. While it was the increase in human productivity due to the use of the assembly line by Ford Motor Company in the early twentieth century that was responsible for the production of the first commonly affordable automobiles, it was Henry Ford’s creativity that led to the introduction of the assembly line in his eponymous company (Dasgupta 1996). All this naturally raises several questions for computational creativity: What is creativity? Can creativity be enhanced? Can creativity be taught? How might a computer aid human creativity? How might we enhance human-computer co-creativity where the creativity emerges from interactions between humans and computers? Copyright © 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Goel, the first author of this paper, conducts research on computational creativity. In late 2014, IBM gave him free access to a version of Watson (Brown et al. 2013; Ferruci et al. 2010) in the cloud called the Watson Engagement Advisor. In Spring 2015, he used Watson in the Georgia Tech CS4803/8803 class on Computational Creativity with Wiltgen as the teaching assistant. The project-based class used Watson to support biologically inspired design, a design paradigm that uses biological systems as analogues for inventing technological systems. The twenty-four students in the class self-organized into six teams of four students each, and developed semester-long projects that built on Watson to support biologically inspired design. In this paper, we describe this experiment in using Watson to teach about human-computer co-creativity, present the project of one team, consisting of Creeden, Kumble, Salunke and Shetty, in some detail, and summarize the remaining five projects. We also draw some lessons about “best practices” for using Watson for (i) supporting biologically inspired design, and (ii) enhancing human-computer co-creativity. The Computational Creativity Class The Georgia Tech CS4803/8803 class on Computational Creativity in Spring 2015 consisted of 24 students, including 21 graduate students and 3 undergraduate senior students. 18 of the 21 graduate students and all 3 undergraduate students were majoring in computer science. According to the course description handed out to the students at the start of the class, the learning goals were (1) To become familiar with the literature on computational creativity (concepts, methods, tasks), (2) To become familiar with the state of art in computational creativity (systems, techniques, tools), (3) To learn about the processes of designing, developing and deploying interactive/autonomous creative systems from ideation to realization, (4) To acquire experience in designing an interactive creative tool, and (5) To become an independent thinker in computational creativity. The observable learning outcomes were (i) To be able to analyze/critique developments Cognitive Assistance in Government Papers from the AAAI 2015 Fall Symposium

Analogies play multiple roles in cognition. In this paper, we explore the roles of analogy in collaborative interdisciplinary design. We describe two analyses of a case study of a design team engaged in biologically inspired design. In the first analysis, we sought to understand the multiple roles of analogy in interdisciplinary design. The goal of the second analysis was to understand the relationship between analogy and collaboration. During this latter analysis, we discovered another, unexpected, role for analogy: resolving cognitive dissonance. Cognitive dissonance typically refers to the mental discomfort a person experiences when simultaneously holding two conflicting goals, values, beliefs, thoughts or feelings. We observed that interdisciplinary design teams too have cognitive dissonance. We also observed that analogies play an important role in helping induce shifts in the perspectives of teammates, align their mental models, and thereby resolve the cognitive dissonance in interdisciplinary design teams. We discuss some implications of our observations for developing case-based systems for collaborative interdisciplinary design.

We envision that the next generation of knowledge-based CAD systems will be characterized by four features: they will be based on cognitive accounts of design, and they will support collaborative design, conceptual design, and creative design. In this paper, we first analyze these four dimensions of CAD. We then report on a study in the design, development and deployment of a knowledge-based CAD system for supporting biologically inspired design that illustrates these four characteristics. This system, called DANE for Design by Analogy to Nature Engine, provides access to functional models of biological systems. Initial results from in situ deployment of DANE in a senior-level interdisciplinary class on biologically inspired design indicates its usefulness in helping designers conceptualize design of complex systems, thus promising enough to motivate continued work on knowledge-based CAD for biologically inspired design. More importantly from our perspective, DANE illustrates how cognitive studies of design can inform the development of CAD systems for collaborative, conceptual, and creative design, help assess their use in practice, and provide new insights into human interaction with knowledge-based CAD systems.

Biologically inspired design is an increasingly popular design paradigm. Biologically inspired design differs from many traditional case-based reasoning tasks because it employs cross-domain analogies. The wide differences in biological source cases and technological target problems present challenges for determining what would make good or useful schemes for case representation, indexing, and adaptation. In this paper, we provide an information-processing analysis of biologically inspired design, a scheme for representing knowledge of designs of biological systems, and a computational technique for automatic indexing and retrieval of biological analogues of engineering problems. Our results highlight some important issues that a case-based reasoning system must overcome to succeed in supporting biologically inspired design.

Sustainable design is as an important movement in design. Biologically inspired design is a major paradigm for sustainable design. In this paper, we analyze a corpus of biologically inspired design projects in terms of sustainability. We then describe a case study of analogical design of a fog harvesting net, and abstract from it the patterns of Hydrophobia and Hydrophilia. We indicate how these two function-mechanism design patterns occur in several design projects in our corpus. This analysis indicates how biologically inspired sustainable design can be analyzed in terms of cross-domain analogical transfer of design patterns.

Biologically inspired design uses cross-domain analogies from biology to engineering to enhance design creativity and innovation. This analogical transfer requires conceptual understanding of biological systems. In this paper, we describe a prototype interactive knowledge-based design environment called DANE for supporting conceptual understanding through learning about functional models of biological designs. We present initial results from deploying DANE in an interdisciplinary class on biologically inspired design, indicating that designers found DANE's functional models useful for conceptualizing complex systems.

Biologically inspired design is a rapidly growing movement in environmentally sustainable design. According to the biologically inspired design paradigm, nature is the best design case base. This recognition has led to a race to develop case-based techniques and tools to aid biologically inspired design. It is noteworthy that all current case-based tools perform only the task of generation of design concepts. However, some cognitive studies have suggested that case-based reasoning plays an important role in design solution evaluation and design solution explanation in addition to design concept generation. In this paper, we describe an ethnographic study of biologically inspired design that confirms the above finding. In addition, our study indicates that case-based reasoning may support a fourth task in biologically inspired design especially in the context of collaborative design: explanation of biological source cases. These findings suggest a significantly expanded role for case-based reasoning in biologically inspired design.

In this paper, we present an initial attempt at systemizing knowledge of biological systems from an engineering perspective. In particular, we describe an interactive knowledge-based design environment called DANE that uses the Structure-Behavior-Function (SBF) schema for capturing the functioning of biological systems. We present preliminary results from deploying DANE in an interdisciplinary class on biologically inspired design, indicating that designers found the SBF schema useful for conceptualizing complex systems.

Household robots are becoming commonplace. The application of social cues, such as emotion, has the potential to make such robots easier to use and understand. However, it remains unclear how household robots can or should display emotion, and what considerations should be given to emotive behavior regarding the expected set of contexts in which the robot will operate. In this paper, we report the results of our systematic evaluation of context and emotion recognition of a non-anthropomorphic robot, the iRobot Roomba. Considerations, implications, and future work are discussed.

Summary Dynamic time warping (DTW) has been widely used in various pattern recognition and time series data mining applications. However, as examples will illustrate, both the classic DTW and its later alternative, derivative DTW, may fail to align a pair of sequences on their common trends or patterns. Furthermore, the learning capability of any supervised learning algorithm based on classic/derivative DTW is very limited. In order to capture trends or patterns that a sequence presents during the alignment process, we first derive a global feature and a local feature for each point in a sequence. Then, a method called feature based dynamic time warping (FBDTW) is designed to align two sequences based on each point‟s local and global features instead of its value or derivative. Experimental study shows that FDBTW outperforms both classic DTW and derivative DTW on pairwise distance evaluation of time series sequences. In order to enhance the capacity of supervised learning based on DTW, we further design a method called adaptive feature based dynamic time warping (AFDBTW) by equipping the FDBTW with a novel feature selection algorithm. This feature selection algorithm is able to expand the learning capability of any DTW based supervised learning algorithm by a dual learning process. The first-fold learning process learns the significances of both the local feature and global feature towards classification; then the second-fold learning process learns a classification model based on the pairwise distances generated by the AFDBTW. A comprehensive experimental study shows that the AFDBTW is able to make further improvement over the FDBTW in time series classification.