Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem solving team can be created. This paper presents an approach to extract human design strategies and implicit rules, purely from historical human data, and use that for design generation. A two-step framework that learns to imitate human design strategies from observation is proposed and implemented. This framework makes use of deep learning constructs to learn to generate designs without any explicit information about objective and performance metrics. The framework is designed to interact with the problem through a visual interface as humans did when solving the problem. It is trained to imitate a set of human designers by observing their design state sequences without inducing problem-specific modelling bias or extra information about the problem. Furthermore, an endto-end agent is developed that uses this deep learning framework as its core in conjunction with image processing to map pixel-todesign moves as a mechanism to generate designs. Finally, the designs generated by a computational team of these agents are then compared to actual human data for teams solving a truss design problem. Results demonstrates that these agents are able to create feasible and efficient truss designs without guidance, showing that this methodology allows agents to learn effective design strategies.

No 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.

Generative design problems often encompass complex action spaces that may be divergent over time, contain state-dependent constraints, or involve hybrid (discrete and continuous) domains. To address those challenges, this work introduces Design Strategy Network (DSN), a data-driven deep hierarchical framework that can learn strategies over these arbitrary complex action spaces. The hierarchical architecture decomposes every action decision into first predicting a preferred spatial region in the design space and then outputting a probability distribution over a set of possible actions from that region. This framework comprises a convolutional encoder to work with image-based design state representations, a multi-layer perceptron to predict a spatial region, and a weight-sharing network to generate a probability distribution over unordered set-based inputs of feasible actions. Applied to a truss design study, the framework learns to predict the actions of human designers in the study, capturing their truss generation strategies in the process. Results show that DSNs significantly outperform non-hierarchical methods of policy representation, demonstrating their superiority in complex action space problems.

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.