The Development of the Intuitive Teaching-based Design Method for Robot-assisted Fabrication Applied to Bricklaying Design and Construction
JIA-SHUO HSU, National Cheng Kung University
YANG-TING SHEN, National Cheng Kung University
FANG-CHE CHENG, National Cheng Kung University
Human-Computer Interaction,
HCI International Virtual, 2022
Abstract.
The development of CAD/CAM systems has shortened the process from concept to implementation in recent years. However, there are still several problems in the design-to-fabrication process. First, most of the tools used in the design process make unintuitive due to the diversity of functions, making it more complex for the designer's work. A lot of time and effort has been spent on learning operating software and interfaces. These factors make the designer's job more complicated. Moreover, suppose the designer does not have a certain level of understanding of the manufacturing techniques or tools of the design. In that case, it may also increase the difficulty of translation from design to digital fabrication. Second, designers need to spend the effort to solve the problem of information conversion if there is no integration or continuity between design and fabrication. And even increase the gap between the design end and the implementation end. Based on these two problems, this study proposes a TRAC (Teaching-based Robotic Arm Construction) system to support the intuitive teaching design method and the process of automatically translating fabrication information to achieve an integration process from design to build.
Clustering and Topological Interlocking for the Robotic Assembly of a Martian Habitat
Fang-Che Cheng
Arwin Hidding
Feras Alsaggaf
Henriette Bier
Delft University of Technology
National Cheng Kung University
University of Sydney
Abstract.
To construct a Martian habitat using complex and irregular 3D-printed Voronoi-based components, it is necessary to perform component classification and ensure proper interlocking assembly. This paper presents a robotic assembly method based on a K-means clustering and topological interlocking approach. The topological interlocking based on Voronoi aims to provide an internally force-locked system, which facilitates both the robotic assembly process and the structural stability of the habitat. The clustering is leveraged for production planning objectives, including resource allocation, and scheduling operations for assembling components. This method addresses assembly challenges of non-uniform components and facilitates the stacking of prefabricated 3D-printed Voronoi-based components using mobile robots.
Object Recognition and User Interface Design for Vision-Based Autonomous Robotic Grasping Point Determination
FANG-CHE CHENG, National Cheng Kung University
CHIA-CHING YEN, National Cheng Kung University
TAY-SHENG JENG, National Cheng Kung University
Computer-Aided Architectural Design Research in Asia,
CAADRIA Hong Kong, 2021
Abstract
The integration of Robot Operating System (ROS) with Human-Machine Collaboration (HMC) currently represents the future tendency toward Autonomous Robotic In-Situ Assembly on Construction Sites. In comparison with the industrial environment, construction sites nowadays are extremely complex and unpredictable, due to the different building components and customized designs. This paper presents a visual-based object recognition method and user interface enabling on-site robot arms to autonomously handle building components and to build specific designs without the influence of material, shape, and environment. The implementation is an object recognition approach that serves with KUKA industrial robotic manipulator along with an RGB-depth stereo camera in an eye-in-hand configuration to grasp and manipulate found elements to build the desired structure. Opportunities for using vision-based autonomous robotic in-situ assembly on construction sites are reviewed.
.jpg){kind=small}