Transferring Design Strategies From Human To Computer And Across Design Problems

Solving any design problem involves planning and strategizing, where intermediate processes are identified and then sequenced. This is an abstract skill that designers learn over time and then use across similar problems. However, this transfer of strategies in design has not been effectively modeled or leveraged within computational agents. This note presents an approach to represent design strategies using a probabilistic model. The model provides a mechanism to generate new designs based on certain design strategies while solving configuration design task in a sequential manner. This work also demonstrates that this probabilistic representation can be used to transfer strategies from human designers to computational design agents in a way that is general and useful. This transfer-driven approach opens up the possibility of identifying high-performing behavior in human designers and using it to guide computational design agents. Finally, a quintessential behavior of transfer learning is illustrated by agents as transferring design strategies across different problems led to an improvement in agent performance. The work presented in this study leverages the Cognitively Inspired Simulated Annealing Teams (CISAT) framework, an agent-based model that has been shown to mimic human problem-solving in configuration design problems. [DOI: 10.1115/1.4044258]

[1]  Tomislav Martinec,et al.  Agent-based simulation framework to support management of teams performing development activities , 2016 .

[2]  Bob J. Wielinga,et al.  Configuration-Design Problem Solving , 1997, IEEE Expert.

[3]  Maria C. Yang,et al.  A PROBABILISTIC APPROACH FOR EXTRACTING DESIGN PREFERENCES FROM DESIGN TEAM DISCUSSION , 2007 .

[4]  Mohammed Owais Qureshi,et al.  The Impact of Robotics on Employment and Motivation of Employees in the Service Sector, with Special Reference to Health Care , 2014, Safety and health at work.

[5]  Christopher McComb,et al.  Data on the configuration design of internet-connected home cooling systems by engineering students , 2017, Data in brief.

[6]  Van de velde Breuker.  Common KADS Library for Expertise Modelling , 1994 .

[7]  Christopher McComb,et al.  Mining Process Heuristics From Designer Action Data via Hidden Markov Models , 2017 .

[8]  T. Husén,et al.  The International Encyclopedia of Education , 1994 .

[9]  B. Chandrasekaran,et al.  Design Problem Solving: A Task Analysis , 1990, AI Mag..

[10]  Mary Lou Maher,et al.  Process Models for Design Synthesis , 1990, AI Mag..

[11]  Raymonde Guindon.  Designing the design process: exploiting opportunistic thoughts , 1990 .

[12]  Doina Precup,et al.  Algorithms for multi-armed bandit problems , 2014, ArXiv.

[13]  Peter G. Harrison,et al.  Adapting Hidden Markov Models for Online Learning , 2015, UKPEW.

[14]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[15]  Robert R. Hoffman,et al.  How Can Expertise be Defined? Implications of Research From Cognitive Psychology , 1998 .

[16]  John S. Gero,et al.  Computational studies to understand the role of social learning in team familiarity and its effects on team performance , 2012 .

[17]  H A SIMON,et al.  HUMAN ACQUISITION OF CONCEPTS FOR SEQUENTIAL PATTERNS. , 1963, Psychological review.

[18]  Jonathan Cagan,et al.  Unlocking Organizational Potential: A Computational Platform for Investigating Structural Interdependence in Design , 2006 .

[19]  Gavriel Salomon,et al.  T RANSFER OF LEARNING , 1992 .

[20]  Christopher McComb,et al.  Design Strategy Transfer in Cognitively-Inspired Agents , 2018, Volume 2A: 44th Design Automation Conference.

[21]  Christopher McComb,et al.  Lifting the Veil: Drawing insights about design teams from a cognitively-inspired computational model , 2015 .

[22]  Peter Stone,et al.  Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..

[23]  Robin Williams,et al.  Exploring Expertise: Issues and Perspectives , 1998 .

[24]  Christopher McComb,et al.  Utilizing Markov Chains to Understand Operation Sequencing in Design Tasks , 2017 .

[25]  Hiroki Sayama,et al.  The effects of mental model formation on group decision making: An agent-based simulation , 2011, Complex..

[26]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[27]  YAN JIN,et al.  The virtual design team: A computational model of project organizations , 1996, Comput. Math. Organ. Theory.

[28]  J. Gero,et al.  Building a computational laboratory for the study of team behaviour in product development , 2017 .

[29]  Shelley D. Dionne,et al.  The role of leadership in shared mental model convergence and team performance improvement: An agent-based computational model , 2010 .

[30]  B. Chandrasekaran.  Design Problem Solving : A Task Analysis 1 , 1990 .

[31]  Jonathan Cagan,et al.  A-Design: An Agent-Based Approach to Conceptual Design in a Dynamic Environment , 1999 .

[32]  John S. Gero,et al.  Social learning in design teams: The importance of direct and indirect communications , 2013, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[33]  Pierre Baldi,et al.  Smooth On-Line Learning Algorithms for Hidden Markov Models , 1994, Neural Computation.

[34]  Benjamin A Clegg,et al.  Sequence learning , 1998, Trends in Cognitive Sciences.

[35]  Timothy W. Simpson,et al.  DESIGN AS A SEQUENTIAL DECISION PROCESS: A METHOD FOR REDUCING DESIGN SET SPACE USING MODELS TO BOUND OBJECTIVES , 2015, DAC 2015.

[36]  Sanjay Mittal,et al.  Towards a Generic Model of Configuraton Tasks , 1989, IJCAI.

[37]  Jonathan Cagan,et al.  Multiagent Shape Grammar Implementation: Automatically Generating Form Concepts According to a Preference Function , 2009 .

[38]  Ulrich Müller-Kolck,et al.  Systematic introduction to expert systems: Knowledge representations and problem-solving methods , 1994 .

[39]  Christopher McComb,et al.  Capturing Human Sequence-Learning Abilities in Configuration Design Tasks through Markov Chains , 2017 .