scholarly journals Design Strategy Transfer in Cognitively-Inspired Agents

Author(s):  
Christopher McComb ◽  
Jonathan Cagan ◽  
Ayush Raina

Planning and strategizing are essential parts of the design process and are based on the designer’s skill. Further, planningis an abstract skill that can be transferred between similar problems. However, planning and strategy transfer within design have not been effectively modeled within computational agents. This paper presents an approach to represent this strategizing behavior using a probabilistic model. This model is employed to select the operations that computational agents should perform while solving configuration design tasks. This work also demonstrates that this probabilistic model can be used to transfer strategies from human data to computational agents ina way that is general and useful. This study shows a successful • transfer of design strategy from human-to-computer agents, opening up the possibility of deriving high-performing behavior from designers and using it to guide computational design agents. Finally, a quintessential behavior of transfer learning is illustrated by agents while transferring design strategies across different problems, improving agent performance significantly. The work presented in this study leverages a computational framework built by embedding cognitive characteristics into agents, which has shown to mimic human problem-solving in configuration design problems.

Author(s):  
Ayush Raina ◽  
Christopher McComb ◽  
Jonathan Cagan

Planning and strategizing are essential parts of the design process and are based on the designer’s skill. Further, planning is an abstract skill that can be transferred between similar problems. However, planning and strategy transfer within design have not been effectively modeled within computational agents. This paper presents an approach to represent this strategizing behavior using a probabilistic model. This model is employed to select the operations that computational agents should perform while solving configuration design tasks. This work also demonstrates that this probabilistic model can be used to transfer strategies from human data to computational agents in a way that is general and useful. This study shows a successful transfer of design strategy from human-to-computer agents, opening up the possibility of deriving high-performing behavior from designers and using it to guide computational design agents. Finally, a quintessential behavior of transfer learning is illustrated by agents while transferring design strategies across different problems, improving agent performance significantly. The work presented in this study leverages a computational framework built by embedding cognitive characteristics into agents, which has shown to mimic human problem-solving in configuration design problems.


2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Ayush Raina ◽  
Jonathan Cagan ◽  
Christopher McComb

Abstract 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.


2018 ◽  
Author(s):  
Christopher McComb ◽  
Kenneth Kotovsky ◽  
Jonathan Cagan

Configuration design problems, characterized by the assembly of components into a final desired solution, are common in engineering design. Various theoretical approaches have been offered for solving configuration type problems, but few studies have examined the approach that humans naturally use to solve such problems. This work applies data-mining techniques to quantitatively study the processes that designers use to solve configuration design problems. The guiding goal is to extract beneficial design process heuristics that are generalizable to the entire class of problems. The extraction of these human problem-solving heuristics is automated through the application of hidden Markov models to the data from two behavioral studies. Results show that designers proceed through four procedural states in solving configuration design problems, roughly transitioning from topology design to shape and parameter design. High-performing designers are distinguished by their opportunistic tuning of parameters early in the process, enabling a more effective and nuanced search for solutions.


Author(s):  
Jenmu Wang ◽  
H. Craig Howard

AbstractHuman designers often adopt strategies from previous similar cases to guide their search in new design tasks. We have developed an approach for automated design strategy capture and reuse. That approach has been implemented in DDIS, a prototype structural design system that uses a blackboard framework to integrate case-based and domain-based reasoning. Plans, goals, and critical constraints from user-selected previous cases are combined with case-independent reasoning to solve underconstrained parametric structural design problems. This article presents a detailed example of design strategy recording and reuse in base plate design for electrical transmission poles.


2017 ◽  
Vol 139 (11) ◽  
Author(s):  
Christopher McComb ◽  
Jonathan Cagan ◽  
Kenneth Kotovsky

Configuration design problems, characterized by the assembly of components into a final desired solution, are common in engineering design. Various theoretical approaches have been offered for solving configuration type problems, but few studies have examined the approach that humans naturally use to solve such problems. This work applies data-mining techniques to quantitatively study the processes that designers use to solve configuration design problems. The guiding goal is to extract beneficial design process heuristics that are generalizable to the entire class of problems. The extraction of these human problem-solving heuristics is automated through the application of hidden Markov models to the data from two behavioral studies. Results show that designers proceed through four procedural states in solving configuration design problems, roughly transitioning from topology design to shape and parameter design. High-performing designers are distinguished by their opportunistic tuning of parameters early in the process, enabling a more effective and nuanced search for solutions.


Author(s):  
Jiyuan Gao ◽  
Kezheng Shang ◽  
Yichun Ding ◽  
Zhenhai Wen

Flexible and wearable sensors have shown great potential in tremendous applications such as human health monitoring, smart robots, and human–machine interfaces, yet the lack of suitable flexible power supply devices...


Author(s):  
Jungmok Ma ◽  
Minjung Kwak ◽  
Harrison M. Kim

The Predictive Product Lifecycle Design (PPLD) model that is proposed in this paper enables a company to optimize its product lifecycle design strategy by considering pre-life and end-of-life at the initial design stage. By combining lifecycle design and predictive trend mining technique, the PPLD model can reflect both new and remanufactured product market demands, capture hidden and upcoming trends, and finally provide an optimal lifecycle design strategy in order to maximize profit over the span of the whole lifecycle. The outcomes are lifecycle design strategies such as product design features, the need for buy-backs at the end of its life, and the quantity of products remanufacturing. The developed model is illustrated with an example of a cell phone lifecycle design. The result clearly shows the benefit of the model when compared to a traditional Pre-life design model. The benefit would be increased profitability, while saving more natural resources and reducing wastes for manufacturers own purposes.


2013 ◽  
Author(s):  
Ties van Bruinessen ◽  
Hans Hopman ◽  
Frido Smulders

The majority of European ship-design industry concentrates on the development of complex, one-off ‘specials’ for the offshore industry, like dredgers, drill ships, pipe-laying ships, et cetera. This industry is complex, not just in terms of the industrial structure but also in the terms of the object. To control the complexity the industry uses large and expansive knowledge basis that support the design, engineering and manufacturing activities. Within academic research the focus is close to practice and dominantly aims at developing knowledge and tools that supports engineering practices. As these strategies are aimed at controlling the complexity, they leave very little room for more innovative developments. On the other side of the spectrum there is a ship-design practice that does allow radical ship design: design and engineering from a blank sheet of paper. Not surprising that these projects are laborious and expensive. The space in between these two design strategies seems unaddressed in literature. The literature on the design of complex structures appears to be scarce, even though this is an area where European ship-design industry is heavily involved. The research this paper reports on aims to develop a design strategy for complex ships in between incremental and radical innovation. We interviewed stakeholders from ship industry, looked into the design literature to describe the present situation and finally performed case-studies in other fields of application for inspiration. Based on these studies we illustrate an alternative design strategy that leaves more space for innovation without the requirement to start from scratch. The approach focuses on the complex interactions between the different levels of decomposition in a complex structure such as a ship.


Author(s):  
Youmna Bassiouny ◽  
Rimon Elias ◽  
Philipp Paulsen

Computational design takes a computer science view of design, applying both the science and art of computational approaches and methodologies to design problems. This article proposes to convert design methodologies studied by designers into rule-based computational design software and help them by providing suggestions for designs to build upon given a set of primitive shapes and geometrical rules. iPattern is a pattern-making software dedicated to designers to generate innovative design patterns that can be used in a decorative manner. They may be applied on wallpapers, carpets, fabric textiles, three-dimensional lanterns, tableware, etc. The purpose is to create a modern pattern design collection that adds a new essence to the place. In order to generate creative design patterns, primitive shapes and geometrical rules are used. The generated design pattern is constructed based on the grid of the Flower of Life of the sacred geometry or similar grids constructed using primitive shapes (rectangles, squares and triangles) combined in the layout of the Flower of Life.


Sign in / Sign up

Export Citation Format

Share Document