Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 15245

Reformat results as: short short into frame detailed detailed into frame

_id	caadria2016_259
id	caadria2016_259
authors	Chen, Jia-Yih and Shao-Chu Huang
year	2016
title	Adaptive Building Facade Optimisation: An integrated Green-BIM approach
doi	https://doi.org/10.52842/conf.caadria.2016.259
source	Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 259-268
summary	This study focused on the optimal design of adaptive build- ing fac?ade for achieving better energy performance. Iterative fac?ade components design are studied between virtual and physical models with integrated tools of BIM, parametric design and sensor devices. The main objectives of this study are: (1) exploring systematic design process via the analysis of adaptive components in responsive fac?ade design; (2) developing compliance checking system for green building regulations; (3) developing optimization system for adaptive fac?ade design process. This paper demonstrated the integration of various digital design methods and concluded with the energy modelling re- sults of a demo project unit for various fac?ade component designs.
keywords	Building fac?ade design; energy performance; design optimization; parametric design; BIM
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	caadria2021_038
id	caadria2021_038
authors	Chen, Jielin and Stouffs, Rudi
year	2021
title	From Exploration to Interpretation - Adopting Deep Representation Learning Models to Latent Space Interpretation of Architectural Design Alternatives
doi	https://doi.org/10.52842/conf.caadria.2021.1.131
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 131-140
summary	An informative interpretation of the hyper-dimensional design solution space can potentially enhance the cognitive capacity of designers with respect to both conventional design practice and the research domain of computational-aided generative design. However, the hitherto research of design space exploration has had limited focus on the interpretation of the hyper solution space per se due to the knowledge gap pertaining to representation and generation. Representation learning techniques, as a core paradigm in the statistically empowered domain of machine learning, possess the capability of extracting a convoluted probabilistic distribution of hyperspace with latent features from unorganized data sources in a generalized manner, which can be an intuitive modus operandi for a structural interpretation of the intricate latent design solution space and benefit the challenging task of architectural design exploration. We examine and demonstrate the potential capabilities of representation learning techniques for the interpretation of latent architectural design solution space with consideration of disentanglement and diversity.
keywords	Design space exploration; latent space interpretation; representation learning; deep generative modelling; generative architectural design
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	caadria2021_039
id	caadria2021_039
authors	Chen, Jielin, Stouffs, Rudi and Biljecki, Filip
year	2021
title	Hierarchical (multi-label) architectural image recognition and classification
doi	https://doi.org/10.52842/conf.caadria.2021.1.161
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 161-170
summary	The task of architectural image recognition for both architectural functionality and style remains an open challenge. In addition, the paucity of well-organized, large-scale architectural image datasets with specific consideration for the domain of architectural design research has hindered the exploration of these challenging tasks. Drawing upon images from the professional architectural website ArchdailyÂ®, and leveraging state-of-the-art deep-learning-based classification models, we explore a hierarchical multi-label classification model as a potential baseline for the task of architectural image classification. The resulting model showcases the potential for innovative architectural discipline-related analyses and demonstrates some heuristic insights for visual feature extraction pertaining to both architectural functionality and architectural style.
keywords	image recognition; hierarchical classification; multi-label classification; architectural functionality; style
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	ecaade2024_89
id	ecaade2024_89
authors	Chen, Jingwen
year	2024
title	Cast Adaptive/Kinetic Façades: The application of sand casting on manufacturing the adaptive/kinetic facades
doi	https://doi.org/10.52842/conf.ecaade.2024.1.431
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 431–438
summary	The escalating focus on sustainability across diverse domains has instigated multifaceted strategies to achieve this objective, encompassing modifications in resource utilization and the incorporation of renewable energy sources alongside recyclable materials. In the realm of architecture, the façade serves not only as an aesthetic feature but also as a regulator of both interior and exterior environments, with kinetic facades emerging as a dynamic solution. Unlike the dynamic external conditions and active building occupants, architecture, as a whole, remains relatively stationary. As integral components of architectural design, kinetic facades are purposefully engineered to actively and dynamically modulate external environmental conditions to align with occupant requirements. This paper delves into the specific realm of cast kinetic joints within the broader context of kinetic facades in architecture. As sustainability gains prominence, the study focuses on the manufacturing processes of these crucial components, narrowing its scope to the use of sand casting. With its rich historical legacy and inherent adaptability, this technique emerges as a focal point for crafting kinetic joints. The analysis delves into crucial considerations, including design intricacies, scale dynamics, and material selections, emphasising the potential of sand casting as a sustainable method for manufacturing these dynamic and active architectural elements. Through a meticulous examination of the intricacies associated with kinetic joints, this study aims to provide targeted insights into the viability of sand casting, thereby providing a refined exploration of its role in advancing sustainability within the realm of kinetic facades.
keywords	Sand casting, Adaptive/Kinetic Façade, Sustainability
series	eCAADe
email
last changed	2024/11/17 22:05

_id	7f0a
authors	Chen, K.-Z.,Feng, X.-A. and Ding, L.
year	2002
title	Intelligent approaches for generating assembly drawings from 3-D computer models of mechanical products
source	Computer-Aided Design, Vol. 34 (5) (2002) pp. 347-355
summary	In order to reduce the time of mechanical product design and ensure the high quality of their assembly drawings, this paper develops an intelligent approach for generatingassembly drawings automatically from three-dimensional (3-D) computer assembly models of mechanical products by simulating the experienced human designer's thinkingmode with the aid of computer graphics and knowledge-based expert system. The key issues include the strategies and methods for selecting the necessary views in anassembly drawing, determining necessary sectional views in each view, eliminating the unreasonable projective overlap of the components in each view, and minimizing thenumbers of both the views in an assembly drawing and the sectional views in each view. Based on the approach, corresponding software prototype was developed. Finally, itis demonstrated, from an example of the fixture in a modularized drilling machine, that its assembly drawing was generated successfully using this intelligent softwareprototype.
keywords	CAD, Intelligent CAD, Expert System, Artificial Intelligence, Assembly, Drawing
series	journal paper
email
last changed	2003/05/15 21:33

_id	3264
authors	Chen, Kuang-Hsiung and Tsai, Wen-Hsiang
year	2000
title	Vision-based obstacle detection and avoidance for autonomous land vehicle navigation in outdoor roads
source	Automation in Construction 10 (1) (2000) pp. 1-25
summary	An effective approach to obstacle detection and avoidance for autonomous land vehicle (ALV) navigation in outdoor road environments using computer vision and image sequence techniques is proposed. To judge whether an object newly appearing in the image of the current cycle taken by the ALV is an obstacle, the object shape boundary is first extracted from the image. After the translation from the ALV location in the current cycle to that in the next cycle is estimated, the position of the object shape in the image of the next cycle is predicted, using coordinate transformation techniques based on the assumption that the height of the object is zero. The predicted object shape is then matched with the extracted shape of the object in the image of the next cycle to decide whether the object is an obstacle. We use a reasonable distance measure to compute the correlation measure between two shapes for shape matching. Finally, a safe navigation point is determined, and a turn angle is computed to guide the ALV toward the navigation point for obstacle avoidance. Successful navigation tests show that the proposed approach is effective for obstacle detection and avoidance in outdoor road environments.
series	journal paper
more	http://www.elsevier.com/locate/autcon
last changed	2003/05/15 21:22

_id	caadria2007_687
id	caadria2007_687
authors	Chen, Liang
year	2007
title	Constructing Structural Shape Grammars
doi	https://doi.org/10.52842/conf.caadria.2007.x.a9l
source	CAADRIA 2007 [Proceedings of the 12th International Conference on Computer Aided Architectural Design Research in Asia] Nanjing (China) 19-21 April 2007
summary	Shape grammar has been shown to be a frame of work applicable to design issues in various fields. Almost all published grammars work only on the bottom level of shape replacement, however in practice, when using grammars to generate designs, the designer may work on different levels of abstractions, concerning about the hierarchy of the design as well. This suggests that, to make the generating process more coherent, the grammar itself need be able to work on different levels, too. This paper introduces the research work that aims at proposing a set of guidelines for writing shape grammar with which the designer could write structured shape grammars that will be easily automated for generating designs.
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	6651
id	6651
authors	Chen, N., Kvan, T., Wojtowicz, J., Van Bakergem, D., Casaus, T., Davidson, J., Fargas, J., Hubbell, K., Mitchell, W., Nagakura, T. and Papazian, P.
year	1994
title	PLACE, TIME AND THE VIRTUAL DESIGN STUDIO
doi	https://doi.org/10.52842/conf.acadia.1994.115
source	Reconnecting [ACADIA Conference Proceedings / ISBN 1-880250-03-9] Washington University (Saint Louis / USA) 1994, pp. 115-132
summary	A design problem shared over the Internet raises issues of how digital media and group dynamics affect networked design collaborations. This paper describes how to conduct a long-distance studio and compares asynchronous and synchronous collaborative techniques. Digital methods are discussed in relationship to both the creative process and design communication. In schematic stages, less precise tools used asynchronously allow free exploration and creative misreadings, while in later stages, more direct real-time exchanges bring a project to resolution. For the final review, synchronous video-conferencing with interactive graphics allow comparison of cross-cultural differences. Used effectively, these tools can electronically create a compelling sense of place. Ways to foster a strong virtual community are discussed in an agenda for future virtual design.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:55

_id	caadria2009_112
id	caadria2009_112
authors	Chen, Pei-Lin; Jen Yen
year	2009
title	A Color Combination Knowledge-Based System for Designer
doi	https://doi.org/10.52842/conf.caadria.2009.737
source	Proceedings of the 14th International Conference on Computer Aided Architectural Design Research in Asia / Yunlin (Taiwan) 22-25 April 2009, pp. 737-745
summary	The purpose of this paper is to investigate colour combination tools of visual communication designers’ need. Participants were twentythree students of Visual Communication Design Graduate School to follow the questionnaire survey and seven students of Design Doctoral Program Graduate School to follow the interview survey. The findings display that visual communication designers seldom use web-based colour combination systems. Based on the findings, we developed a colour combination support system: the adobe illustrator plug-in to proof this hypothesis. The databases of the tool use the book of “colour combination charts”, and the tool of this paper provides a personal database.
keywords	Colour; colour image; colour set; colour combination
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	caadria2021_115
id	caadria2021_115
authors	Chen, Qin Chuan, Lakshmi Narasimhan, Vaishnavi and Lee, Hyunsoo
year	2021
title	The potential of IoT-based smart environment in reaction to COVID-19 pandemic
doi	https://doi.org/10.52842/conf.caadria.2021.2.709
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 709-718
summary	COVID-19 was first reported in late December 2019 and quickly become a global health crisis. In the COVID-19 pandemic context, the dense and open characteristics make the public spaces a potential virus transmission hotspot. Therefore, it is extremely critical to adopt a more advanced and effective method in public environments to slow down its spread until a vaccine is widely used. A smart environment in the form of IoT, also known as the architecture of IoT, consists of three layers: perception layer, network layer, and application layer. A smart environment allows data and activities that happen in this environment to be collected, processed, and shared in real-time through various sensors. It can be introduced for early detection, tracking, and monitoring of potential confirmed cases. The smart environment is considered one of the most promising approaches to face and tackle the current scenario. However, research focusing on the potential of IoT smart environment in reaction to COVID-19 is still meager. Therefore, this paper identifies the smart environments potential based on the concept of IoT architectures three layers and further discusses how IoT can be introduced in public spaces to help battle the pandemic.
keywords	Internet of Things; Smart environment; COVID-19
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	cf2009_328
id	cf2009_328
authors	Chen, Qunli; de Vries, Bauke
year	2009
title	Human visual perceptions in built environment: Applying image-based approach for architectural cue recognition
source	T. Tidafi and T. Dorta (eds) Joining Languages, Cultures and Visions: CAADFutures 2009, PUM, 2009, pp. 328-341
summary	This paper first presents a review on visual perception in the built environment and human vision simulation. Followed by the description of the Standard Feature Model of visual cortex (SFM), an architectural cue recognition model is proposed using SFM-based features. Based on the findings of the experiments it can be concluded that the visual differences between architectural cues are too subtle to realistically simulate human vision for the SFM model.
keywords	Architectural cue recognition, human vision simulation, built environment
series	CAAD Futures
email
last changed	2009/06/08 20:53

_id	ecaade2022_169
id	ecaade2022_169
authors	Chen, Ting-Chia, Tsai, Tsung-Han, Huang, Ching-Wen and Wang, Shih-Yuan
year	2022
title	Compliant Mechanism Moulding via NiChrome Wire Sintering Method
doi	https://doi.org/10.52842/conf.ecaade.2022.1.281
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 281–290
summary	This research proposed a unique process for the rapid manufacturing of large-scale compliant mechanism components. Using the characteristics of the NiChrome wire sintering method, it aims to rapidly fabricate a large-scale compliant mechanism model at low cost. NiChrome wire sintering is a method in which NiChrome wire is wound into a target pattern and then placed in a hot-melt material (TPU powder) to be energized and moulded. The low cost, high degree of freedom and one-piece characteristic of this new method bring new possibilities for the manufacturing process of compliant mechanism components. This research applies a new fabrication method to reduce the production cost and manufacturing difficulty of large kinetic installations. In benefitting from the non-mechanical wear characteristics of compliant mechanisms, the service life of manufactured installations can be greatly prolonged as well. The new fabrication method demonstrates an efficient way to produce a large scale of kinetic structure and provides a toolkit for designers.
keywords	Nichrome Wire Sintering, Rapid Prototyping, Elastic Material, Digital Fabrication, Compliant Mechanism
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2012_164
id	ecaade2012_164
authors	Chen, Ting-Han; Lu, Kai-Tzu
year	2012
title	Creating Spatial-Interactive Service Experiences: A Framework for Designing Interactive Service Spaces
doi	https://doi.org/10.52842/conf.ecaade.2012.2.327
source	Achten, Henri; Pavlicek, Jiri; Hulin, Jaroslav; Matejovska, Dana (eds.), Digital Physicality - Proceedings of the 30th eCAADe Conference - Volume 2 / ISBN 978-9-4912070-3-7, Czech Technical University in Prague, Faculty of Architecture (Czech Republic) 12-14 September 2012, pp. 327-335
summary	Inspired by the emergence of interactive space design and service design, this paper explores the concept of interactive service space and proposes a framework for designing interactive service space experiences. The framework has been applied in two design projects of successful commercial setting, mojo iCuisine interactive restaurant and Yun-Ching Real Estate VIP Center, as validation of its feasibility and applicability. We believe that this framework is beneficial for designers who have interests in creating service experience with interactive space approach, and for further studies regarding the concept of interactive service space.
wos	WOS:000330320600033
keywords	Service design; interaction design; interactive space; interactive exhibit; user experience
series	eCAADe
email
last changed	2022/06/07 07:55

_id	bf5f
authors	Chen, Xiangping
year	1995
title	Representation, Evaluation and Edition of Feature-based and Constraint- based Design
source	Purdue University
summary	This thesis investigates a general and systematic approach to feature-based and constraint-based design. We combine feature-based design and constraint-based design by globally decomposing a design into a sequence of feature attachments and locally defining and positioning each feature by constraints. Analogous to the concept of high-level programming languages, we formalize a layered design model that eliminates the dependency of a design representation on a solid modeler. With this design model, design intent, such as feature descriptions and constraints, is stored in an unevaluated, modeler-independent design representation while the geometry to which it corresponds is stored in an evaluated, modeler-dependent design representation. The separation essentially relies on a naming and matching schema that converts between a geometric reference and a generic name, and a design compiler that automatically instantiates the unevaluated design representation to an evaluated design representation with respect to a solid modeler. The geometric references for defining feature attributes and constraints are recorded with their generic names in the unevaluated design representation. We propose several techniques for naming geometric entities unambiguously. The design compilation or instantiation involves remapping a generic name back to a geometric reference in the selected geometric modeler, solving constraints and implementing feature operations or attachments. Instead of developing a constraint solver for this design compiler, we use an independent and general solver. Feature attachment operations are different from classical Boolean operations in solid modeling. However, we provide a semantics for them that is based on existing operations in solid modeling. The layered design model allows users to edit archived conceptual designs to derive new designs quickly. We investigate the coordination of later features in the unevaluated and modeler-independent representation when a feature is edited and provide a method for editing feature-based and constraint-based design. We also discuss how to extend this work to a commercial feature-based and constraint-based CAD system.
series	thesis:PhD
last changed	2003/02/12 22:37

_id	maver_089
id	maver_089
authors	Chen, Y., Fram, I. and Maver, T.W.
year	1998
title	A Virtual Studio Environment for Design Integration
source	Advances in Engineering Software, vol 29, No 10, 787-800
summary	In this paper the authors attempt to stress the social dimension of design and the role of explicit support for human-level interaction during design systems integration. A human-centred approach is proposed by taking design integration as the collaborative use of design artefacts, and a virtual studio environment (VSE) framework is presented as an integration vehicle to link the social and technical dimensions. A VSE consists of two subsystems: the VSE base system and the domain resources. While common generic facilities for human-human interaction are embedded within the VSE base system, the domain-specific resources are loosely coupled into VSE via resource agents. A VSE prototype for the domain of building design is described, and a demonstration of the use of the VSE prototype is presented. This is then followed by some discussion on related research and further work.
keywords	Design Integration, Collaborative Design, Human-Human Interaction, Virtual Design Studio, Building Design
series	journal paper
email
last changed	2003/09/03 13:23

_id	maver_075
id	maver_075
authors	Chen, Y.Z. and Maver, T.W.
year	1995
title	Some Experiments on Implementing Collaborative Building Design Environments
source	Building Simulation 95 Conference (Ed: J Mitchell et al) Madison, USA
summary	A collaborative building design environment has been proposed to integrate together both the heterogeneous applications and the dispersed project participants. Based on the functional requirements identified, the conventional building product models have been extended to incorporate high-level concepts such as activity and organisation, which are essential for coordination, and a generic human- human interaction model has been developed, which could not only make the building domain models interaction-aware, but also serve as a base model for developing general interaction utilities. Collaborative design environment prototyping has been described, covering the common project workspace, general interaction utilities and multiuser interfaces. Three distribution schemes for implementing the common project workspace within a distributed environment have also been discussed.
series	other
type	normal paper
email
last changed	2015/02/20 14:46

_id	sigradi2021_53
id	sigradi2021_53
authors	Chen, Yao, Lo, Tiantian, Guo, Xiangmin and Wang, Xiangming
year	2021
title	Interactive Virtual Sand Table: An Improved Alternative Participatory Design Tool for Architectural Design
source	Gomez, P and Braida, F (eds.), Designing Possibilities - Proceedings of the XXV International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2021), Online, 8 - 12 November 2021, pp. 67–78
summary	With the planning reform in China, public participation is becoming increasingly crucial to the success of rural planning. However, it is difficult to involve various stakeholders in planning and design projects, mainly due to insufficient planning knowledge and computer skills. Therefore, this paper introduces the Interactive Virtual Sand Table (IVST) as a participatory design tool so that non-professional users can use it conveniently and promote interactive and efficient collaborative design discussion. The IVST based participatory tool was applied in Xidong Village, Chaozhou City, Guangdong Province, China. The results show that IVST interaction is more natural and reduces non-professional users' difficulty participating in the design. Participants' ability to participate was highly enhanced, and their interest in IVST visualization was highly activated. In conclusion, the Interactive Virtual Sand Table highly supports the participatory village planning process and may apply to other areas and domains.
keywords	Mixed reality, Participatory design, Architectural design, Interactive Virtual Sand Table
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	2006_644
id	2006_644
authors	Chen, Yu-Shu and Hong-Sheng Chen
year	2006
title	Tangible User Interface Design for Lower Limb Disabled Children - A composite function of toy accompanying children at home
doi	https://doi.org/10.52842/conf.ecaade.2006.644
source	Communicating Space(s) [24th eCAADe Conference Proceedings / ISBN 0-9541183-5-9] Volos (Greece) 6-9 September 2006, pp. 644-648
summary	This study describes the requirement of lower limb disabled children. Lower limb disabled children that limit their movement in nowadays environment. Ubiquitous computing concept is more popular now. This research uses tangible user interface to be a toy accompanying children at home, combine ubiquitous computing concept to help them control the electronic equipment so that disable children can earn their lives.
keywords	Disable; disability; tangible; user interface;children; ubiquitous computing
series	eCAADe
email
last changed	2022/06/07 07:54

_id	architectural_intelligence2023_10
id	architectural_intelligence2023_10
authors	Cheng Bi Duan, Su Yi Shen, Ding Wen Bao & Xin Yan
year	2023
title	Innovative design solutions for contemporary Tou-Kung based on topological optimisation
doi	https://doi.org/https://doi.org/10.1007/s44223-023-00028-x
source	Architectural Intelligence Journal
summary	Tou-Kung, which is pronounced in Chinese and known as Bracket Set (Liang & Fairbank, A pictorial history of Chinese architecture, 1984), is a vital support component in the Chinese traditional wooden tectonic systems. It is located between the column and the beam and connects the eave and pillar, making the heavy roof extend out of the eaves longer. The development of Tou-Kung is entirely a microcosm of the development of ancient Chinese architecture; the aesthetic structure and Asian artistic temperament behind Tou-Kung make it gradually become the cultural and spiritual symbol of traditional Chinese architecture. In the contemporary era, inheriting and developing Tou-Kung has become an essential issue. Several architects have attempted to employ new materials and techniques to integrate the traditional Tou-Kung into modern architectural systems, such as the China Pavilion at the 2010 World Expo and Yusuhara Wooden Bridge Museum. This paper introduces the topological optimisation method bi-directional evolutionary structural optimisation (BESO) for form-finding. BESO method is one of the most popular topology optimisation methods widely employed in civil engineering and architecture. Through analyzing the development trend of Tou-Kung and mechanical structure, the authors integrate 2D and 3D optimisation methods and apply the hybrid methods to form-finding. Meanwhile, mortise and tenon joint used to create stable connections with components of Tou-Kung are retained. This research aims to design a new Tou-Kung corresponding to “structural performance-based aesthetics”. The workflow proposed in this paper is valuable for Architrave and other traditional building components.
series	Architectural Intelligence
email
last changed	2025/01/09 15:00

_id	ecaade2016_079
id	ecaade2016_079
authors	Cheng, Chi-Li and Hou, June-Hao
year	2016
title	Biomimetic Robotic Construction Process - An approach for adapting mass irregular-shaped natural materials
doi	https://doi.org/10.52842/conf.ecaade.2016.1.133
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 1, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 133-142
summary	Beaver dams are formed by two main processes. One is that beavers select proper woods for constructing. The other one is that streams aggregate those woods to be assembled. Using this approach to construction structure is suitable for natural environment. In this paper, we attempt to develop a construction process which is suitable for all-terrain construction robot in the future. This construction process is inspired by beavers' construction behavior in nature. Beavers select proper sticks to make the structure stable. We predict that particular properties of sticks contribute gravity-driven assembly of wood structure. Thus, we implement the system with machine learning to find proper properties of sticks to improve selection mechanism of construction process. During this construction process, 3D scanner on robotic arm scans and recognizes sticks on terrain, and then robot will select proper sticks and place them. After placement, the system will scan and record the results for learning mechanism.
wos	WOS:000402063700015
keywords	Biomimetic Design; Machine Learning; Natural Material; Point Cloud Analysis; Robotic Fabrication
series	eCAADe
email
last changed	2022/06/07 07:55

For more results click below: