Abstract

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.

References

1.
Ferguson
,
E. S.
,
1994
,
Engineering and the Mind’s Eye
,
MIT Press
,
Cambridge, MA
.
2.
Kosslyn
,
S. M.
,
Pascual-Leone
,
A.
,
Felician
,
O.
,
Camposano
,
S.
,
Keenan
,
J. P.
,
Thompson
,
W. L.
,
Ganis
,
G.
,
Sukel
,
K. E.
, and
Alpert
,
N. M.
,
1999
, “
The Role of Area 17 in Visual Imagery: Convergent Evidence From PET and RTMS
,”
Science
,
284
(
5411
), pp.
167
170
.
3.
Kosslyn
,
S. M.
, and
Shwartz
,
S. P.
,
1977
, “
A Simulation of Visual Imagery
,”
Cogn. Sci.
,
1
(
3
), pp.
265
295
.
4.
Brown
,
D. C.
, and
Chandrasekaran
,
B.
,
1989
,
Design Problem Solving: Knowledge Structures and Control Strategies
,
Morgan Kaufmann Publishers Inc.,
San Francisco, CA
, pp.
35
64
.
5.
Oh
,
S.
,
Jung
,
Y.
,
Kim
,
S.
,
Lee
,
I.
, and
Kang
,
N.
,
2019
, “
Deep Generative Design: Integration of Topology Optimization and Generative Models
,”
ASME J. Mech. Des.
,
141
(
11
), p.
111405
.
6.
Xiong
,
Y.
,
Duong
,
P. L. T.
,
Wang
,
D.
,
Park
,
S.-I.
,
Ge
,
Q.
,
Raghavan
,
N.
, and
Rosen
,
D. W.
,
2019
, “
Data-Driven Design Space Exploration and Exploitation for Design for Additive Manufacturing
,”
ASME J. Mech. Des.
,
141
(
10
), p.
101101
.
7.
Odonkor
,
P.
, and
Lewis
,
K.
,
2019
, “
Data-Driven Design of Control Strategies for Distributed Energy Systems
,”
ASME J. Mech. Des.
,
141
(
11
), p.
111404
.
8.
Silver
,
D.
,
Huang
,
A.
,
Maddison
,
C. J.
,
Guez
,
A.
,
Sifre
,
L.
,
van den Driessche
,
G.
,
Schrittwieser
,
J.
,
Antonoglou
,
I.
,
Panneershelvam
,
V.
,
Lanctot
,
M.
,
Dieleman
,
S.
,
Grewe
,
D.
,
Nham
,
J.
,
Kalchbrenner
,
N.
,
Sutskever
,
I.
,
Lillicrap
,
T.
,
Leach
,
M.
,
Kavukcuoglu
,
K.
,
Graepel
,
T.
, and
Hassabis
,
D.
,
2016
, “
Mastering the Game of Go With Deep Neural Networks and Tree Search
,”
Nature
,
529
(
7587
), pp.
484
489
.
9.
Anthony
,
T.
,
Tian
,
Z.
, and
Barber
,
D.
,
2017
, “
Thinking Fast and Slow With Deep Learning and Tree Search
,”
Adv. Neural Inf. Process. Syst.
,
2017
(
Dec.(Il)
), pp.
5361
5371
.
10.
Lee
,
K.
,
Kim
,
S.-A.
,
Choi
,
J.
, and
Lee
,
S.-W.
,
2018
, “
Deep Reinforcement Learning in Continuous Action Spaces: A Case Study in the Game of Simulated Curling
,”
PMLR
,
Stockholm, Sweden
,
July 10–15
, pp.
2937
2946
.
11.
Wielinga
,
B.
, and
Schreiber
,
G.
,
1997
, “
Configuration-Design Problem Solving
,”
IEEE Exp. Syst. Appl.
,
12
(
2
), pp.
49
56
.
12.
Yukish
,
M. A.
,
Miller
,
S. W.
, and
Simpson
,
T. W.
,
2015
, “
A Preliminary Model of Design as a Sequential Decision Process
,”
Procedia Comput. Sci.
,
44
, pp.
174
183
.
13.
Raina
,
A.
,
McComb
,
C.
, and
Cagan
,
J.
,
2019
, “
Learning to Design From Humans: Imitating Human Designers Through Deep Learning
,”
ASME J. Mech. Des.
,
141
(
11
), p.
111102
.
14.
Puentes
,
L.
,
Raina
,
A.
,
Cagan
,
J.
, and
McComb
,
C.
,
2020
, “
Modeling a Strategic Human Engineering Design Process: Human-Inspired Heuristic Guidance Through Learned Visual Design Agents
,”
Proc. Des. Soc. Des. Conf.
,
1
, pp.
355
364
.
15.
Verschure
,
P. F. M. J.
,
Pennartz
,
C. M. A.
, and
Pezzulo
,
G.
,
2014
, “
The Why, What, Where, When and How of Goal-Directed Choice: Neuronal and Computational Principles
,”
Philos. Trans. R. Soc. B: Biol. Sci.
,
369
(
1655
), p.
20130483
.
16.
Thomas
,
N. J. T.
,
2021
,
Mental Imagery – The Stanford Encyclopedia of Philosophy
,
E. N.
Zalta
, ed.,
Spring 2021
,
Metaphysics Research Lab, Stanford University
,
Stanford, CA
, pp.
1
45
.
17.
Athavankar
,
U. A.
,
1997
, “
Mental Imagery as a Design Tool
,”
Cybern. Syst.
,
28
(
1
), pp.
25
42
.
18.
Goldschmidt
,
G.
,
1992
, “
Serial Sketching: Visual Problem Solving in Designing
,”
Cybern. Syst.
,
23
(
2
), pp.
191
219
.
19.
Wang
,
Z.
,
Bovik
,
A. C.
,
Sheikh
,
H. R.
, and
Simoncelli
,
E. P.
,
2004
, “
Image Quality Assessment: From Error Visibility to Structural Similarity
,”
IEEE Trans. Image Process.
,
13
(
4
), pp.
600
612
.
20.
Nisbett
,
R. E.
, and
Ross
,
L.
,
1980
,
Human Inference: Strategies and Shortcomings of Social Judgment
,
Prentice-Hall
,
Englewood Cliffs, NJ
.
21.
Yilmaz
,
S.
,
Seifert
,
C.
,
Daly
,
S. R.
, and
Gonzalez
,
R.
,
2016
, “
Design Heuristics in Innovative Products
,”
ASME J. Mech. Des.
,
138
(
7
), p.
071102
.
22.
Daly
,
S. R.
,
Seifert
,
C. M.
,
Yilmaz
,
S.
, and
Gonzalez
,
R.
,
2016
, “
Comparing Ideation Techniques for Beginning Designers
,”
ASME J. Mech. Des.
,
138
(
10
), p.
101108
.
23.
Lenat
,
D. B.
,
1983
, “
EURISKO: A Program That Learns New Heuristics and Domain Concepts
,”
Artif. Intell.
,
21
(
1–2
), pp.
61
98
.
24.
Laird
,
J.
,
Newell
,
A.
, and
Rosenbloom
,
P. S.
,
1987
, “
SOAR : An Architecture for General Intelligence
,”
Artif. Intell.
,
33
(
1
), pp.
1
64
.
25.
Langley
,
P.
,
McKusick
,
K. B.
,
Allen
,
J. A.
,
Iba
,
W. F.
, and
Thompson
,
K.
,
1991
, “
A Design for the ICARUS Architecture
,”
ACM SIGART Bull.
,
2
(
4
), pp.
104
109
.
26.
Blösch-Paidosh
,
A.
, and
Shea
,
K.
,
2019
, “
Design Heuristics for Additive Manufacturing Validated Through a User Study
,”
ASME J. Mech. Des.
,
141
, p.
041101
.
27.
Daly
,
S.
, and
Christian
,
J. L.
,
2012
, “
Assessing Design Heuristics for Idea Generation in an Introductory Engineering Course
,”
Int. J. Eng. Educ.
,
28
(
2
), pp.
463
473
.
28.
Königseder
,
C.
, and
Shea
,
K.
,
2016
, “
Visualizing Relations Between Grammar Rules, Objectives, and Search Space Exploration in Grammar-Based Computational Design Synthesis
,”
ASME J. Mech. Des.
,
138
(
10
), p.
101101
.
29.
Schrittwieser
,
J.
,
Antonoglou
,
I.
,
Hubert
,
T.
,
Simonyan
,
K.
,
Sifre
,
L.
,
Schmitt
,
S.
,
Guez
,
A.
,
Lockhart
,
E.
,
Hassabis
,
D.
,
Graepel
,
T.
,
Lillicrap
,
T.
, and
Silver
,
D.
,
2019
, “
Mastering Atari, Go, Chess and Shogi by Planning With a Learned Model
,” arXiv:1911.08265v2, pp.
1
21
.
30.
Brown
,
N.
, and
Sandholm
,
T.
,
2018
, “
Superhuman AI for Heads-Up No-Limit Poker: Libratus Beats Top Professionals
,”
Science
,
359
(
6374
), pp.
418
424
.
31.
Nair
,
A.
,
Pong
,
V.
,
Dalal
,
M.
,
Bahl
,
S.
,
Lin
,
S.
, and
Levine
,
S.
,
2018
, “
Visual Reinforcement Learning With Imagined Goals
,”
Adv. Neural Inf. Process. Syst.
,
2018
, pp.
9191
9200
.
32.
Sutton
,
R. S.
, and
Barto
,
A. G.
,
2018
,
Reinforcement Learning: An Introduction
,
The MIT Press
,
Cambridge, MA
, pp.
73
94
.
33.
McComb
,
C.
,
Cagan
,
J.
, and
Kotovsky
,
K.
,
2015
, “
Rolling With the Punches: An Examination of Team Performance in a Design Task Subject to Drastic Changes
,”
Des. Stud.
,
36
, pp.
99
121
.
34.
McComb
,
C.
,
Cagan
,
J.
, and
Kotovsky
,
K.
,
2017
, “Utilizing Markov Chains to Understand Operation Sequencing in Design Tasks,”
Design Computing and Cognition ‘16
,
J. S.
Gero
, ed.,
Springer International Publishing
,
Cham
, pp.
401
418
.
35.
McComb
,
C.
,
Cagan
,
J.
, and
Kotovsky
,
K.
,
2017
, “
Mining Process Heuristics From Designer Action Data Via Hidden Markov Models
,”
ASME J. Mech. Des.
,
139
(
11
), p.
111412
.
36.
Raina
,
A.
,
Cagan
,
J.
, and
McComb
,
C.
,
2019
, “
Transferring Design Strategies From Human to Computer and Across Design Problems
,”
ASME J. Mech. Des.
,
141
(
11
), p.
114501
.
37.
Brownell
,
E.
,
Cagan
,
J.
, and
Kotovsky
,
K.
,
2021
, “
Only as Strong as the Strongest Link: The Relative Contribution of Individual Team Member Proficiency in Configuration Design
,”
ASME J. Mech. Des.
,
143
(
8
), p.
081402
.
You do not currently have access to this content.