RLayout: Interior Design System Based on Reinforcement Learning

The advanced artificial intelligence technologies have promoted the development of other industries. As a combination of AI technologies and art, intelligent design has become a research hotspot in recent years. Intelligent design uses computer to simulate human thinking activities with AI technolog...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Ningqi, Niu, Chang, Li, Zizhong
Format: Conference Proceeding
Language:English
Subjects:
intelligent design
interior design
reinforcement learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The advanced artificial intelligence technologies have promoted the development of other industries. As a combination of AI technologies and art, intelligent design has become a research hotspot in recent years. Intelligent design uses computer to simulate human thinking activities with AI technologies, enabling the computers to undertake more complex design tasks in a better way. At the same time, reinforcement learning plays an increasingly important role in many fields, such as system control, game theory, computer network, decision making, etc. In this work, an intelligent design system based on the reinforcement learning algorithm was proposed, and corresponding reward rules were developed according to the design principles. The system can help the designer to generate the optimal scheme automatically, which can be extended and applied to find the best scheme in many problems, including interior design, daily schedule, resource arrangement, etc. Our demo shows that the system can offer excellent design scheme according to pre-set reward rules, and reduce workload of related designers.
ISSN:2473-3547
DOI:10.1109/ISCID.2019.00033