TY - JOUR
T1 - Goal-Directed Design Agents
T2 - Integrating Visual Imitation with One-Step Lookahead Optimization for Generative Design
AU - Raina, Ayush
AU - Puentes, Lucas
AU - Cagan, Jonathan
AU - McComb, Christopher
N1 - Funding Information:
This material is based upon work supported by the Defense Advanced Research Projects Agency through cooperative agreement no. N66001-17-1-4064. Any opinions, findings, and conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the sponsors.
Publisher Copyright:
© 2021 by ASME.
PY - 2021/12/1
Y1 - 2021/12/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85107780483&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107780483&partnerID=8YFLogxK
U2 - 10.1115/1.4051013
DO - 10.1115/1.4051013
M3 - Article
AN - SCOPUS:85107780483
VL - 143
JO - Journal of Mechanical Design - Transactions of the ASME
JF - Journal of Mechanical Design - Transactions of the ASME
SN - 1050-0472
IS - 12
M1 - 124501
ER -