Artificial intelligence techniques to support design and construction

A. Mohammadpour, E. Karan, Somayeh Asadi

Research output: Contribution to conferencePaper

Abstract

In recent years, researchers have relied heavily on data (historical and real-time) and digital solutions to support informed decisions. Consequently, data analysis has become an integral part of the design and construction process. Researchers spend a tremendous amount of time cleaning, organizing, and understanding the data. Artificial Intelligence (AI) can be used to help overcome human limitations in processing and enriching large volumes of data from a variety of sources. AI can encompass millions of alternatives for various design and project delivery solutions and ultimately improve project planning, construction, and maintenance and operation process. AI can be a solution to the severely under-digitized Architecture, Engineering, and Construction (AEC) industry, however, there are two challenges with respect to creating intelligent agents in AEC; (1) finding appropriate ways of gathering information from the environment and transforming them into internal context, and (2) selecting an appropriate AI technique to succeed in decision-making based on the relevant knowledge about the environment. This study focuses primarily on the second challenge by looking at potential applications of AI in AEC. The AI techniques in AEC can generally be classified into two main areas: (1) decision making methods and algorithms, and (2) learning methods. Regarding the first area, search methods and optimization theories are used when there is enough information to tackle decision-making and the problem is solved by the selection of the best action (with regard to some constraints and criteria) from a set of alternatives. The learning methods, on the other hand, are further classified into knowledge-based, reasoning, and planning methods (to learn how to adapt to changing conditions), learning probabilistic methods (e.g. Bayesian learning), and machine learning (e.g. supervised learning, reinforcement learning).

Original languageEnglish (US)
Pages1282-1289
Number of pages8
StatePublished - Jan 1 2019
Event36th International Symposium on Automation and Robotics in Construction, ISARC 2019 - Banff, Canada
Duration: May 21 2019May 24 2019

Conference

Conference36th International Symposium on Automation and Robotics in Construction, ISARC 2019
CountryCanada
CityBanff
Period5/21/195/24/19

Fingerprint

Artificial intelligence
Decision making
Planning
Intelligent agents
Supervised learning
Reinforcement learning
Construction industry
Learning systems
Cleaning
Processing

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Building and Construction
  • Human-Computer Interaction

Cite this

Mohammadpour, A., Karan, E., & Asadi, S. (2019). Artificial intelligence techniques to support design and construction. 1282-1289. Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.
Mohammadpour, A. ; Karan, E. ; Asadi, Somayeh. / Artificial intelligence techniques to support design and construction. Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.8 p.
@conference{056b6d4618b74eb28e2678850368f4e6,
title = "Artificial intelligence techniques to support design and construction",
abstract = "In recent years, researchers have relied heavily on data (historical and real-time) and digital solutions to support informed decisions. Consequently, data analysis has become an integral part of the design and construction process. Researchers spend a tremendous amount of time cleaning, organizing, and understanding the data. Artificial Intelligence (AI) can be used to help overcome human limitations in processing and enriching large volumes of data from a variety of sources. AI can encompass millions of alternatives for various design and project delivery solutions and ultimately improve project planning, construction, and maintenance and operation process. AI can be a solution to the severely under-digitized Architecture, Engineering, and Construction (AEC) industry, however, there are two challenges with respect to creating intelligent agents in AEC; (1) finding appropriate ways of gathering information from the environment and transforming them into internal context, and (2) selecting an appropriate AI technique to succeed in decision-making based on the relevant knowledge about the environment. This study focuses primarily on the second challenge by looking at potential applications of AI in AEC. The AI techniques in AEC can generally be classified into two main areas: (1) decision making methods and algorithms, and (2) learning methods. Regarding the first area, search methods and optimization theories are used when there is enough information to tackle decision-making and the problem is solved by the selection of the best action (with regard to some constraints and criteria) from a set of alternatives. The learning methods, on the other hand, are further classified into knowledge-based, reasoning, and planning methods (to learn how to adapt to changing conditions), learning probabilistic methods (e.g. Bayesian learning), and machine learning (e.g. supervised learning, reinforcement learning).",
author = "A. Mohammadpour and E. Karan and Somayeh Asadi",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
pages = "1282--1289",
note = "36th International Symposium on Automation and Robotics in Construction, ISARC 2019 ; Conference date: 21-05-2019 Through 24-05-2019",

}

Mohammadpour, A, Karan, E & Asadi, S 2019, 'Artificial intelligence techniques to support design and construction' Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada, 5/21/19 - 5/24/19, pp. 1282-1289.

Artificial intelligence techniques to support design and construction. / Mohammadpour, A.; Karan, E.; Asadi, Somayeh.

2019. 1282-1289 Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Artificial intelligence techniques to support design and construction

AU - Mohammadpour, A.

AU - Karan, E.

AU - Asadi, Somayeh

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In recent years, researchers have relied heavily on data (historical and real-time) and digital solutions to support informed decisions. Consequently, data analysis has become an integral part of the design and construction process. Researchers spend a tremendous amount of time cleaning, organizing, and understanding the data. Artificial Intelligence (AI) can be used to help overcome human limitations in processing and enriching large volumes of data from a variety of sources. AI can encompass millions of alternatives for various design and project delivery solutions and ultimately improve project planning, construction, and maintenance and operation process. AI can be a solution to the severely under-digitized Architecture, Engineering, and Construction (AEC) industry, however, there are two challenges with respect to creating intelligent agents in AEC; (1) finding appropriate ways of gathering information from the environment and transforming them into internal context, and (2) selecting an appropriate AI technique to succeed in decision-making based on the relevant knowledge about the environment. This study focuses primarily on the second challenge by looking at potential applications of AI in AEC. The AI techniques in AEC can generally be classified into two main areas: (1) decision making methods and algorithms, and (2) learning methods. Regarding the first area, search methods and optimization theories are used when there is enough information to tackle decision-making and the problem is solved by the selection of the best action (with regard to some constraints and criteria) from a set of alternatives. The learning methods, on the other hand, are further classified into knowledge-based, reasoning, and planning methods (to learn how to adapt to changing conditions), learning probabilistic methods (e.g. Bayesian learning), and machine learning (e.g. supervised learning, reinforcement learning).

AB - In recent years, researchers have relied heavily on data (historical and real-time) and digital solutions to support informed decisions. Consequently, data analysis has become an integral part of the design and construction process. Researchers spend a tremendous amount of time cleaning, organizing, and understanding the data. Artificial Intelligence (AI) can be used to help overcome human limitations in processing and enriching large volumes of data from a variety of sources. AI can encompass millions of alternatives for various design and project delivery solutions and ultimately improve project planning, construction, and maintenance and operation process. AI can be a solution to the severely under-digitized Architecture, Engineering, and Construction (AEC) industry, however, there are two challenges with respect to creating intelligent agents in AEC; (1) finding appropriate ways of gathering information from the environment and transforming them into internal context, and (2) selecting an appropriate AI technique to succeed in decision-making based on the relevant knowledge about the environment. This study focuses primarily on the second challenge by looking at potential applications of AI in AEC. The AI techniques in AEC can generally be classified into two main areas: (1) decision making methods and algorithms, and (2) learning methods. Regarding the first area, search methods and optimization theories are used when there is enough information to tackle decision-making and the problem is solved by the selection of the best action (with regard to some constraints and criteria) from a set of alternatives. The learning methods, on the other hand, are further classified into knowledge-based, reasoning, and planning methods (to learn how to adapt to changing conditions), learning probabilistic methods (e.g. Bayesian learning), and machine learning (e.g. supervised learning, reinforcement learning).

UR - http://www.scopus.com/inward/record.url?scp=85071431275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071431275&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85071431275

SP - 1282

EP - 1289

ER -

Mohammadpour A, Karan E, Asadi S. Artificial intelligence techniques to support design and construction. 2019. Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.