Key Centre of Design Computing and Cognition – University of Sydney Concept Formation in a Design Optimization Tool Wei Peng and John S. Gero 7, July, 2006
Key Centre of Design Computing and Cognition – University of Sydney Outlines Design Optimization Concept formation Concept formation from a situated lens A situated agent-based design optimization tool The agent’s experience and concept formation engine Prototype system Testing results and future direction
Key Centre of Design Computing and Cognition – University of Sydney Design Optimization Three major tasks Interactive process Design knowledge requirement Application scenario – how the agent learn to recognize design optimization problem
Key Centre of Design Computing and Cognition – University of Sydney Recognition of appropriate optimization model is fundamental to design decision problems Can be expressed into semantic relationships between design elements For example Focus on learning and adapting the knowledge of recognizing an optimization problem if all the variables are of continuous type and all the constraints are linear and the objective function in linear then conclude that the model is linear programming and execute linear programming algorithm Design Optimization Knowledge
Key Centre of Design Computing and Cognition – University of Sydney Concept Formation (CF) Concept learning – given a set of examples of some concept/class/category, determine if a given example is an instance of concept Concept formation – incremental unsupervised acquisition of categories and their intentional descriptions Concept in designing – a consequence of the situatedness of designing
Key Centre of Design Computing and Cognition – University of Sydney Situated Agent Effector Concept Formation Experience Sensor Designer Interactions in Designing Concept – Coupled Interactions in Designing Virtual Knowledge Flows between two Worlds
Key Centre of Design Computing and Cognition – University of Sydney Concept Formation through a Situated Lens Situatedness – notion of conceptual situations that are based on the observers’ experiences and inseparable from interactions (Dewey, 1902) The concept formation process – the way agent orders its experience in time (Clancey,1999) as conceptual coordination Concept formation framework – in a situated agent (Gero and Fujii, 2000)
Key Centre of Design Computing and Cognition – University of Sydney Situated Concept Formation Perceptual Categorization 2 Perceptual Categorization 1 C1 C2 what I’m-doing-now C time t’ time t Concept as higher order categorization of a sequence Situated concept formation
Key Centre of Design Computing and Cognition – University of Sydney A Constructive Memory Model
Key Centre of Design Computing and Cognition – University of Sydney A Situated Agent I A situated agent contains sensors, effectors, experience and a concept formation engine A concept formation engine consists of a perceptor, a cue_Maker, a conceptor, a hypothesizer, a validator and related processes Sense data takes the form of a sequence of actions and their initial descriptions S (t) {…… “click on objective function text field”, key stroke of “x”, “(”, “1”, “)”, “+”, “x”, “(, “2”, “)”…} Percepts are intermediate data structures of environment states with multimodal information. It can be described as (Objective Function Object, Objective_Function, “x(1)+x(2)”)
Key Centre of Design Computing and Cognition – University of Sydney A Situated Agent II Proto-concepts are initial or intermediate concept structures Tree or rule structures Hypotheses depict the agent’s explanations about failures in correctly predicting a situation Backward chaining rules Validation allows concepts and hypotheses to be evaluated in interactions Concepts are grounded proto-concepts or hypotheses Invariants about the agent’s experience
Key Centre of Design Computing and Cognition – University of Sydney Concept Formation I Recast Concept Formation in A Constructive Memory Model
Key Centre of Design Computing and Cognition – University of Sydney Concept Formation II Recast Concept Formation in A Constructive Memory Model
Key Centre of Design Computing and Cognition – University of Sydney Learning Scenario I
Key Centre of Design Computing and Cognition – University of Sydney System Architecture Situated Agent-based Design Optimization Tool
Key Centre of Design Computing and Cognition – University of Sydney Learning Scenario II
Key Centre of Design Computing and Cognition – University of Sydney The Agent’s Experience
Key Centre of Design Computing and Cognition – University of Sydney The Experiential Response
Key Centre of Design Computing and Cognition – University of Sydney Grounding Experience I
Key Centre of Design Computing and Cognition – University of Sydney Grounding Experience II
Key Centre of Design Computing and Cognition – University of Sydney Prototype System
Key Centre of Design Computing and Cognition – University of Sydney Using similar design tasks – linear programming Test I
Key Centre of Design Computing and Cognition – University of Sydney Using novel design optimization scenarios {L, Q, Q, L, NL, Q, NL, L, L, NL, Q, Q, L, L, L} Initial experience – a quadratic experience Behaviour charts and characteristics Performance (prediction rate) for a static, reactive and situated system: Test II
Key Centre of Design Computing and Cognition – University of Sydney Behaviour Charts
Key Centre of Design Computing and Cognition – University of Sydney Behaviour Characteristics
Key Centre of Design Computing and Cognition – University of Sydney Prediction Rates
Key Centre of Design Computing and Cognition – University of Sydney Summary and Future Work Concept formation in a situated agent New concept (new knowledge structure) Interaction plays a role in shaping structures and behaviours Co-evolution relation between structures and behaviours Future direction 1: maintaining user models in design interactions Future direction 2: learning from enriched contexts in design optimisation
Key Centre of Design Computing and Cognition – University of Sydney The End Thanks!