Modeling a Strategic Human Engineering Design Process: Human-Inspired Heuristic Guidance Through Learned Visual Design Agents

Puentes, Lucas; Raina, Ayush; Cagan, Jonathan; McComb, Christopher

doi:10.1017/dsd.2020.42

Cited by 7 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The heuristic is enacted for a preset number of design actions, referred to as the burst length [20], after which a new classification is performed. This heuristic guidance enhances the performance of Vanilla DLAgents [10].…”

Section: Background 21 Dlagents and Heuristic Guided Dlagentsmentioning

confidence: 89%

“…To expand the decision making capabilities of Vanilla DLAgents, Puentes et al [10] incorporated a guidance method to the framework that allows agents to follow multi-step design heuristics, experience-derived strategies that help focus on achieving specific design goals or subgoals [16]. Heuristics can improve the efficiency of design space exploration [17][18][19].…”

Section: Background 21 Dlagents and Heuristic Guided Dlagentsmentioning

confidence: 99%

“…To address this challenge, the proposed agent framework splits the design process into two parts based on the availability of feedback. When the feedback is unavailable, the agent simulates the intuition by visually imitating human designers using a deep learning framework defined in [9] and a mechanism of heuristic guidance [10], which are complementary and objective-agnostic. Alternatively, when the feedback is available, the agent uses lookahead search to make designs, allowing better versatilility and more focus on explicit goals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Goal-Directed Design Agents: Integrating Visual Imitation With One-Step Lookahead Optimization for Generative Design

Raina

Puentes

Cagan

et al. 2021

Journal of Mechanical Design

View full text Add to dashboard Cite

Engineering design problems often involve large state and action spaces along with highly sparse rewards. Since an exhaustive search of those spaces is not feasible, humans utilize relevant domain knowledge to condense the search space. Deep learning agents (DLAgents) were previously introduced to use visual imitation learning to model design domain knowledge. This note builds on DLAgents and integrates them with one-step lookahead search to develop goal-directed agents capable of enhancing learned strategies for sequentially generating designs. Goal-directed DLAgents can employ human strategies learned from data along with optimizing an objective function. The visual imitation network from DLAgents is composed of a convolutional encoder-decoder network, acting as a rough planning step that is agnostic to feedback. Meanwhile, the lookahead search identifies the fine-tuned design action guided by an objective. These design agents are trained on an unconstrained truss design problem modeled as a sequential, action-based configuration design problem. The agents are then evaluated on two versions of the problem: the original version used for training and an unseen constrained version with an obstructed construction space. The goal-directed agents outperform the human designers used to train the network as well as the previous feedback-agnostic versions of the agent in both scenarios. This illustrates a design agent framework that can efficiently use feedback to not only enhance learned design strategies but also adapt to unseen design problems.

show abstract

Section: Background 21 Dlagents and Heuristic Guided Dlagentsmentioning

confidence: 89%

Section: Background 21 Dlagents and Heuristic Guided Dlagentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Goal-Directed Design Agents: Integrating Visual Imitation With One-Step Lookahead Optimization for Generative Design

Raina

Puentes

Cagan

et al. 2021

Journal of Mechanical Design

View full text Add to dashboard Cite

show abstract

“…• Purely data-driven approach: Unlike previous approaches [25,34,66], DSN does not require rule-based inference algorithms to make action selections and is a data-driven methodology to predict human actions. • Modularity: The framework is decomposed into three different deep networks that have independent learning tasks.…”

Section: Design Strategy Network (Dsn)mentioning

confidence: 99%

Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces

Raina

Cagan

McComb

2021

Journal of Mechanical Design

View full text Add to dashboard Cite

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.

show abstract

“…Even without knowledge of design metrics and performance, the RL agents were found to generate competitive designs compared to humans. Puentes et al [112] expand on this work by learning action sequence heuristics instead of individual design actions. Raina et al [111] further expand on this work with a goal-based reinforcement learning agent.…”

Section: Kinematic Synthesismentioning

confidence: 99%

Deep Generative Models in Engineering Design: A Review

Regenwetter¹,

Nobari²,

Ahmed³

2021

Preprint

View full text Add to dashboard Cite

Automated design synthesis has the potential to revolutionize the modern human design process and improve access to highly optimized and customized products across countless industries. Successfully adapting generative Machine Learning to design engineering may be the key to such automated design synthesis and is a research subject of great importance. We present a review and analysis of Deep Generative Learning models in engineering design. Deep Generative Models (DGMs) typically leverage deep networks to learn from an input dataset and learn to synthesize new designs. Recently, DGMs such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), feedforward Neural Networks (NNs) and certain Deep Reinforcement Learning (DRL) frameworks have shown promising results in design applications like structural optimization, materials design, and shape synthesis. The prevalence of DGMs in Engineering Design has skyrocketed since 2016. Anticipating continued growth, we conduct a review of recent advances with the hope of benefitting researchers interested in DGMs for design. We structure our review as an exposition of the algorithms, datasets, representation methods, and applications commonly used in the current literature. In particular, we discuss key works that have introduced new techniques and methods in DGMs, successfully applied DGMs to a design-related domain, or directly supported development of DGMs through datasets or auxiliary methods. We further identify key challenges and limitations currently seen in DGMs across design fields, such as design creativity, handling complex constraints and objectives, and modeling both form and functional performance simultaneously. In our discussion we identify possible solution pathways as key areas on which to target future work.

show abstract

Modeling a Strategic Human Engineering Design Process: Human-Inspired Heuristic Guidance Through Learned Visual Design Agents

Cited by 7 publications

References 29 publications

Goal-Directed Design Agents: Integrating Visual Imitation With One-Step Lookahead Optimization for Generative Design

Goal-Directed Design Agents: Integrating Visual Imitation With One-Step Lookahead Optimization for Generative Design

Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces

Deep Generative Models in Engineering Design: A Review

Contact Info

Product

Resources

About