C. Zhou, B. Tang, L. Ding, P. Sekula, Y. Zhou, Z. Zhang | 2020 | Automation in Construction
DOI 10.1016/j.autcon.2020.103282Review state
Last reviewed
Not reviewed yet
Last approved reanalysis
No approved reanalysis yet
This paper discusses the design and automated assembly of Planetary LEGO Brick for lunar in-situ construction. It describes a modular system for lunar habitat construction and uses finite element analysis and a Deep Convolutional Neural Network (DCNN) for brick recognition. No lunar regolith simulants or samples are mentioned. The paper presents a design and methodology for constructing lunar habitats using a concept called Planetary LEGO Brick. This approach involves designing modular bricks that can be assembled automatically using recognition algorithms. The study includes structural, thermal, and meteorite impact analyses to ensure the durability and safety of the habitat. Additionally, it explores automated recognition techniques, such as deep convolutional neural networks (DCNN), for efficient assembly processes in lunar environments. The paper presents the design and development of a modular, reconfigurable robotic system for lunar and planetary exploration. The system is based on LEGO Mindstorms EV3 and is designed to be scalable, adaptable, and programmable for various tasks such as terrain navigation, sample collection, and scientific experiments. The system includes a ce
These are the records this paper contributes to the simulant, returned sample, method, and property browsers.
No simulants extracted yet.
No returned samples extracted yet.
gr1
Figure Thumbnail
gr10
Figure Thumbnail
gr11
Figure Thumbnail
gr12ab
Figure Thumbnail
gr13ab
Figure Thumbnail
gr14
Figure Thumbnail
gr15
Figure Thumbnail
gr16
Figure Thumbnail
URL Pattern
1-s2.0-S0926580519312841-.
File Extension
sml (thumbnail), jpg (image), gif (image)
Content Type
Academic/Technical Document Figures
Research Framework
Overall framework integrating design, simulation, and construction phases for lunar habitat development
Temperature range
374 K (101 °C) to 120 K (-153 °C)
Training data impact
More data improves model accuracy
Model performance
Xception outperforms VGG-18, ResNet50, and Inception V3
Lunar habitat design
Modular arched structure using Planetary LEGO Brick