Upgrading Path of Sustainable Design Driven by Modern Artificial Intelligence

Yunting Gao

PDF(1873 KB)
International Journal of Design Science
International Journal of Design Science ›› 2023, Vol. 3 ›› Issue (3) : 32-49.

Upgrading Path of Sustainable Design Driven by Modern Artificial Intelligence

Author information +
History +

Abstract

Artificial intelligence (AI) is moving toward a new stage in its generalized development. To explain the upgrading path of sustainable design driven by AI can provide a certain basis and support for its application in design. Based on research into modern intelligence technology and design practices, this article (1) focuses on AI+, through relational comparisons and hierarchical structure analysis; (2) studies the value-added effect and new characteristics exhibited by the content, method, process, form, effect, and other aspects of design under the concept of sustainability; and (3) explores the upgrading mode and technological application of sustainable design, whose development is obviously influenced by the new generation of intelligence technology, through the upgrading paths of sensation, thinking, simulacrum, and construction. The continuous integration of sustainable design and AI is a trend that will endow the design process and designed objects with intelligent functions and multiple characteristics from the dimensions of cognition, thought, expression, and action. New tools and subjects will profoundly affect the value creation of design in the dimensions of environment, economy, and society.

Key words

sustainable design / artificial intelligence / technology application / upgrade

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
Yunting Gao. Upgrading Path of Sustainable Design Driven by Modern Artificial Intelligence. International Journal of Design Science. 2023, 3(3): 32-49

1 Introduction

Artificial intelligence (AI) refers to intelligent machines, technologies, or systems that can simulate human intelligent activities [1]. This technology was developed from a branch of computer science, stemming from an academic conference held in the United States in 1956. In the embryonic stage of sustainable design in the 1960s [2], designers were already experimenting with AI. Buckminster Fuller was an early representative [3]. Its research can be traced back to morphological grammar in the 1970s [4]. Generations of sustainable designers have brought computing and machines into design. However, owing to insufficient data, weak computing power, and obstacles in converting to application, AI has not played an important role in sustainable design.
After experiencing two troughs and a half-century of development, artificial intelligence finally entered an explosive period in 2016, moving toward a new stage of technological capability and generalized development [5]. A series of changes brought by AI are pushing human society into the intelligent era, which has shown the power to subvert the order of various industries. Owing to its unique complexity and characteristics, contemporary artificial intelligence is obviously different from the past. With its effectiveness and influence, it can be considered a new generation. Many countries now include AI as a national development strategy, and provide strong support to it in terms of technical support, talent training, legal construction, institutional improvement, and in ensuring it has a good material, economic, and social foundation [6⇓⇓⇓⇓-11]. While sustainability of design is a popular research topic, since 2017 the focus on AI has eclipsed that of sustainability. With its strong momentum, using AI to promote the upgrading of sustainable design has become an notable trend (Figure 1).
Figure 1 Integration of sustainable design and artificial intelligence

Full size|PPT slide

Artificial intelligence has become a new kind of intelligence in a new information environment with a goal to integrate humans, computers, and the internet [12,13]. It is infiltrating most areas of sustainable design, and has become the development direction of popular technologies such as big data and the Internet of Things, which deeply influence sustainable design (Table 1), with the following characteristics: (1) Collaboration of processes. This includes the joint creation of many types of designs and machine algorithms, the synergy between intelligent technologies and design tools, and the intertwined interaction of “human-machine” creative factors, which jointly promote design in the connection of thinking and behavior. (2) Complexity of technology. This is manifested through the self-organization generation and self-adaptive optimization of information integration, association establishment, and the decision-making process. Technology in design has changed from focusing on assistance to autonomy, from using single to multiple technologies, and from combination to composite forms [14,15]. (3) Diversification of forms. This includes new forms arising from the deep integration of technology, ecology, and humanity, as well as intelligent forms with sustainable content and style. Considering the two development directions of a larger capacity and non-geometric shapes, product morphology tends to be standardized, irregular and unconstrained, simplified, and natural, while having multiple characteristics.
Table 1 AI technologies that can be applied to sustainable design
Picture processing Material recognition, color recognition, shape recognition, expression recognition, situation recognition, image generation, video generation
Sensing technology Sound, light, wind, temperature, humidity, touch, motion, brain wave, and pulse sensing
Imaging technology Point cloud appearance imaging, 3D holographic projection reproduction, virtual reality (VR) scene representation, augmented reality (AR)-enhanced environment performance, thermal object imaging
Interaction technology Voice, expression, body, behavior, and brain-computer interaction
Simulation technology Dynamic scenarios, functional effects, energy consumption, physical attributes, dynamic environment simulation
Voice processing Speech recognition, semantic understanding, speech synthesis, text generation
Control technology Product condition tracking, automatic evaluation feedback, environmental factor monitoring, pollution source warning, infrared remote temperature measurement, environmental photogrammetry
Data processing Feature extraction, cluster analysis, cloud databases, knowledge graphs, knowledge presentation, association retrieval
Intelligent decision Performance mapping, pattern matching, feature recognition, model generation
2 Upgrading: Sustainable Design in the Intelligent Era
If the process of sustainability in design only begins when the corresponding connections between sustainable design and all other elements are formed [16], then the role that sustainable design plays will only begin when the generalized connections between sustainable design and modern artificial intelligence are formed. The role of sustainable design has just begun. AI that can listen, see, speak, think, learn, and act [17] will have an unprecedented impact on sustainable design. Intelligence transforms technology from external conditions to design elements, promoting innovation regarding environmental protection, value, and design. The field of resources that can be utilized by sustainable design is expanding from physical space to information space [5], and the ability of sustainable design to transform and coordinate the environment, society, and economy is constantly increasing [18]. Sustainable design will have the ability to identify, define, and solve problems in a complex environmental, social, economic, and technological system, placing the environment in a better balance between the objects of protection and the elements of development, unleashing the growth potential of economic value on the basis of environmental benefits, better covering the interests of multiple parties, and responding more effectively to social problems at all levels (Figure 2).
Figure 2 AI-driven changes in the role of sustainable design technology

Full size|PPT slide

2.1 Characteristics of Design Appeal

The rapid generalization of AI is based on an understanding of natural intelligence [19,20], and the high-tech industries it relies on have obvious advantages in low-carbon and environmental protection, which is the embodiment of the concept of sustainability. Most areas where modern artificial intelligence is good are precisely where sustainable designers are not good. Many algorithms can understand the structure of the world and create value independently [21]. Sustainable design has a clear demand for AI, a new driving force for development.

2.1.1 Demand for High-tech Design Innovation

Sustainable design has shown insufficient innovation or lacked technical support. Intelligent new-tech applications can reverse this situation. The high-tech features of AI can provide strong green technical support for design. The connection or integration of new technologies has opened rich possibilities that can trigger new sustainable design innovations [22⇓-24]. The multiple perspectives and defocused observation of AI can often lead to entirely new scenes in terms of systems, information, calculations, splicing, and mutations. These characteristics can expand the scope of exploration and reflection on the "eco-humanities, " facilitating autonomous machine innovation, as well as design innovation inspired by new intelligent elements [25].

2.1.2 Demand for Depth of Multilateral Participation

The effective participation of multiple parties is an important feature and method of sustainable design. Intelligent simulation technologies such as digital twins, virtual scenes, and real-time interaction can realize preset schemes in real time. Data-driven sustainable performance-mapping models and intelligent modeling software are increasingly blurring the boundaries between designers and participants. Users, experts, producers, managers, and stakeholders can participate in the design of "ideal objects" in terms of performance, structure, style, and color [26⇓⇓-29]. The interaction between people and products creates multidimensional sustainable value before products are generated, ensuring that the design meets the expectation of the target audience in an increasingly complex environment. This further promotes the shift of the functional paradigm to a more value-oriented experience paradigm [30].

2.1.3 Demand for Large-scale Heterogeneous Data Processing

Data have become an important asset in sustainable design, and the core source of value creation. About 80% of sustainable design data are unstructured "miscellaneous" data [31,32]. Due to the limitations of designers’ knowledge and skills, the drawbacks of traditional technology, and a lack of knowledge in environmental discipline, it is difficult to handle large and diverse data processing needs [33]. In addition, the digital survival problem in the modern complex “eco-economy-culture” environment is difficult to deal with [34]. Artificial intelligence and big data are natural partners [35]. AI can extract environmental information and object knowledge from functions, ecology, culture, morphology, and other data, and make rational explanations and active applications. This is the key to truly integrating data value into design value and functional meaning.

2.1.4 Demand for Diversified and Precise Function Positioning

With the continuous improvement of sustainable design concepts and methods, the problems explored have shown a systemization beyond various functions, emphasizing the diversity and individualization of system functions. The traditional subjectivity, ambiguity, and abstract cognitive features make it difficult for designers to obtain the real needs of the objects, and it is not easy to accurately quantify design decisions. Technologies such as multichannel identification, intelligent sensing, and large-scale data analysis can learn more comprehensive and accurate information about ecology, environment, resources, systems, platforms, and people. It is helpful to establish an accurate match between the design orientation and the real demands on the huge number of “long tails, ” which fundamentally liberates the functional users, system service objects, or resource consumers on the demand side. This liberation is the required technical support for sustainable design to meet the diverse personal values of use, ecology, and culture.

2.1.5 Demand for Design and Operation Efficiency Iteration

With the in-depth influence of intelligent concepts and technologies, the operation mode, work rhythm, and technical compatibility of sustainable design can no longer adapt to the environmental requirements of the new era. It is necessary to make timely adjustments to achieve the iteration of the design itself that conforms to the changing trend. The transformation of sustainable design has great significance for resource management and environmental protection. AI design is essentially based on the joint operation of data, computing power, and algorithms, and accordingly improves or replaces the designer's memory, reaction, and analysis capabilities. The machine can take over much tedious and inefficient repetitive work, which can effectively shorten the design cycle; improve work efficiency; save manpower, material resources and financial resources [36,37]; and release the designer's creativity. This new human-machine adaptation relationship is the most effective driving force for sustainable design efficiency improvement.

2.2 Five Types of Upgrading Technologies

The complexity, collaboration, and interconnection of modern AI show digital, group, combined, mixed, and self-intelligent characteristics. Accordingly, their application in sustainable design is summarized as five types of technology systems: big data intelligence, internet-based collective intelligence, cross-media intelligence, human-machine hybrid enhanced intelligence, and autonomous intelligence [25][38-44]. They are a new form of combined and integrated applications of basic technologies such as computer vision, voice processing, natural language processing, planning and decision-making systems, and big data or statistical analysis based on computing programs and the Internet of Things to connect people, things, and computers [45].
1.Big data intelligence (data processing, database, knowledge representation) is an intelligent technology that combines big data drive and knowledge guidance to analyze characteristics and create output.
2.Internet-based collective intelligence (open-source information system, usage feedback platform, resource control platform) is a swarm intelligence technology based on the internet for information integration and collaborative linkage.
3.Cross-media intelligence (multi-type sensor integration, multi-information conversion, panoramic simulation) is an intelligent technology that fits multichannel intelligent technology to form information and behavioral intelligence.
4.Human-machine hybrid enhanced intelligence (smart wearable devices, human-machine collaboration systems, remote operation participation) is a hybrid intelligent technology that enhances human capabilities under preset conditions of machines.
5.Autonomous intelligence (performance mapping models, information modeling systems, autonomous decision-making) is a machine or procedural intelligence technology that can automatically complete design tasks or perform sustainable functions.
Compared with traditional intelligent technology, the new generation of AI technology is beyond the scope of the relationship between man and machine, as a comprehensive intelligent technology with a networked architecture (Figure 3). Intelligent technology related to data dimensions has the widest application range. There are traditional tendencies in the group intelligence technology of the combination of multiple agents. Multichannel intelligent integration technology has the highest dependence on other intelligent technologies. Although autonomous intelligent technology has been unmanned, its scope of application is relatively narrow. Enhanced collaborative intelligence technology requires the highest degree of human participation. Intelligent technology with a narrow scope of application with human participation allows sustainable design to retain certain traditional characteristics. Unmanned intelligent technology with a wide range of applications makes it easier to automate sustainable design. These technologies with different characteristics can be used individually or in combination in a complex and diverse way in the system of environment, society, and economy, enabling sustainable design to better realize value creation.
Figure 3 Fractal dimension properties of main application technologies

Full size|PPT slide

3 Four-fold Development Dimension of Sustainable Design for Modern Artificial Intelligence

As a new AI paradigm, "extended intelligence" changes the level of understanding of information, thinking mode of caring about the world, expression form of intention and imagination, and action method of constructing meaning, which will inevitably lead to a new sustainable design paradigm [46⇓⇓-49]. Due to the scientific and complex thinking, data, calculation, and network attributes of seemingly one-dimensional artificial intelligence technology systems, the entire complex ecology of sustainable design is enhanced, and not just a single value [50,51]. The overall performance is in the four dimensions of sensation, thinking, simulacrum, and construction. Sensation is the upgrading of the cognition dimension, and the improvement is the ability of information acquisition and data processing. Thinking is the upgrading of the thought dimension, promoting the ability of knowledge production and analysis and decision-making. Simulacrum is the upgrading of the expression dimension, which promotes the ability of meaning and information transmission. Construction is the upgrading of the action dimension, enhancing the ability of design creation and meaning value generation.
New ways of thinking derived from new technologies and tools, as well as a series of new ideas, methods, and elements, enhance thinking, organization, and realization. Metaphysically, there is an inter-existence relationship about virtuality (immateriality) and reality (materiality) between sensation and construction, and an intergrowth relationship about quality (content) and appearance (form) between thinking and simulacrum. The integration of sustainable design and AI has been developed and upgraded in the dual dynamic relationship between the virtual and the real, and between quality and appearance (Figure 4). Sensation, thinking, simulacrum, and construction create the value meaning of sustainable design ascending on two levels and two dimensions. Sensation and construction act on the behavioral level, forming a cognition upgrade that relies on intelligent information acquisition, and an action upgrade that relies on active computing machines. Thinking and simulacrum work on the ideological level, forming a thought upgrade that relies on analysis and decision models, and relies on information transformation to present technical expression upgrades. Sensation and thinking form the process of attribute internalization, a cognition upgrade based on big data recognition technology, and a thought upgrade based on data processing technology. Simulacrum and construction are the processes of externalization of meaning, forming an expression upgrade that relies on interactive real-time simulation, and action upgrade that relies on independent creation and execution technology.
Figure 4 Basic properties and relationships of four-fold upgrade path

Full size|PPT slide

The impact of sustainable design changes driven by various AI technologies is multi-level, multi-point, and multi-faceted, acting on both vertical and horizontal areas. Specifically, the upgrading of the sensation dimension is mainly based on technologies such as data processing, databases, open-source information platforms, usage feedback platforms, smart wearable devices, human-machine collaboration systems, multi-type sensor integration, multi-information conversion, and autonomous decision-making. The upgrading of the thinking dimension is mainly based on technologies such as data processing, databases, knowledge representation, open-source information platforms, human-machine collaboration systems, remote operation participation, and autonomous decision-making. The upgrading of the simulacrum dimension is mainly based on technologies such as human-machine coordination systems, remote operation participation, multi-information conversion, panoramic simulation, information modeling systems, and autonomous decision-making. The upgrading of the construction dimension is mainly based on technologies such as data processing, databases, resource control platforms, smart wearable devices, human-machine collaboration systems, remote operation, performance mapping models, and autonomous decision-making. Sensation, thinking, simulacrum, and construction are not only four ascending directions, but also an overlapping and orderly cyclical development process. This not only affects connotation, but changes functional meanings. It not only empowers the program design, but also enhances the product function (Table 2). The four models influence each other to promote the evolution of sustainable design. The application of the new generation of AI technology in sustainable design practices from the aspects of the environment, society, and economy has shown the effect of design empowerment and value creation.
Table 2 Contents of four-fold upgrade path
Path-tech Technology factor
Basic power Key technology type
Sensation Information analysis and processing capabilities of multidimensional and broad-source data Big data intelligence, internet-based collective intelligence, cross-media intelligence, human-machine hybrid enhanced intelligence, autonomous intelligence
Thinking Computational, autonomous, and ubiquitous intelligent technology loading Big data intelligence, internet-based collective intelligence, human-machine hybrid enhanced intelligence, autonomous intelligence
Simulacrum Empowerment of interactive multi-mimicry models Cross-media intelligence, human-machine hybrid enhanced intelligence, autonomous intelligence
Construction Subjectivity upgrade succession around three systemic meanings Big data intelligence, internet-based collective intelligence, human-machine hybrid enhanced intelligence, autonomous intelligence
Path-effect Path characteristic Influence field
Representation Function Design field Product field
Sensation Deepening and broadening of cognition scope Expansion of awareness Question research, information collection Object perception, environmental perception
Thinking Renewal of thought structure Reshaping logic of thought Concept idea, design analysis Information processing, intelligent decisions
Simulacrum Multidimensional expression Enhancement of expressive ability Research expression, design expression Information transmission, man-computer interaction
Construction Actor dualization Increased effectiveness of action Project design, performance evaluation Function realization, meaning creation

4 Sensation: Cognition Expansion of Massive Data Information Architecture

The application of artificial intelligence technology in the direction of sensation in sustainable design not only expands the scope of objective cognition, but also deepens the degree of subjective cognition. It presents a trend of upgrading from pertinence to the whole environment, image-text type to data type, static acquisition to dynamic acquisition, physical perception to network sensing, and correctness to accuracy (Table 3). The combination or integration of various technologies (Web crawler, cloud platform, multi-point positioning, data calculation) and equipment (sensor, camera, smart wear) can independently obtain long-term, continuous, large-scale, and full-sample attributes, behaviors, and spatiotemporal data through information channels such as seeing, listening, smelling, touching, and knowing. It helps designers and designed objects to observe, perceive, and understand people and the environment more dimensionally and deeply. It can concentrate and reflect changes in human physiology, behavior, emotions, and other factors into a machine in an understandable and interactive manner [52⇓⇓-55]. The "data, algorithm" model in cognition is subverting the "physics, experience" model, making sustainable design move toward the characteristics of natural science. Cognition in sustainable design will expand in the direction of verticalization and heterogeneity, and shift to subdivision, multi-focus, composite, and global multi-level integration.
Table 3 Typical applications of five technology types in sensation upgrading dimension
Database (China ecological environment database):
a large amount of data information clarifies the characteristics of three system objects [56]		 Open-source information platform (Tezign DesignNet dataset):
a wide range of sustainable value cognitions are loaded through websites, emails, WeChat groups, and other channels [57]		 Smart wearable device (remote temperature measuring helmet):
smart auxiliary equipment makes information acquisition more real-time and efficient		 Multi-type sensor integration (ecological environment monitor):
forms overall cognition through integration of multiple types of information (remote)		 Autonomous decision-making (portable drone photogrammetry equipment):
system autonomously completes collection of high-precision objects and environmental data [58]
In the early stage of research and information collection, various intelligent cognitive technologies and devices have greatly shortened the time-consuming tasks of user observation, environmental analysis, and case acquisition, and have reduced personal understanding deviations, providing a more complete basis for value positioning and function deployment. DJI flying glasses use "camera + wearable" remote synchronization VR technology (Figure 5). The head-rotation sensor on the back of the glasses can control a pan/tilt/zoom (PTZ) camera to realize real-time transmission of the scene. At the same time, the glasses are connected to the network knowledge base, which can retrieve information at any time, so that it is easy to identify what is seen and to learn related information. This smart wearable man-machine collaboration device integrates a variety of sensing and open-source information technologies, allowing designers to obtain richer object data information.
Figure 5 Informative interface and application scenario of DJI flying glasses

Full size|PPT slide

Multi-connected product perception technology can more comprehensively perceive and monitor the environment and objects, providing intelligent support for real-time function output or adjustment. The urban smart home multifunctional variable space developed by the Urban Science Research Group of the Massachusetts Institute of Technology is equipped with more than 200 third-generation environmental sensors (TerMITes) (Figure 6), which are placed in parts and furniture and used to independently collect temperature and humidity, movement, ambient light, CO2, and other data with time and place markings. TerMITes automatically uploads data to a central database via low-power Wi-Fi, and fits multiple types of sensing technologies to obtain environmental characteristics and usage data, providing an effective basis for renovation and iterative design [59,60].
Figure 6 Urban smart home space and central data system equipped with TerMITes sensors

Full size|PPT slide

5 Thinking: Reshaped Thought Reflected by Rationality of Intelligent Technology

The application of artificial intelligence to thinking in sustainable design not only innovates regarding the structure of thought, but also reshapes the logic of the thought mode. It presents a trend of upgrading from logicality to computability, single subject to mixed subject, experience orientation to quality integration, three-system to three-space dimension, and professional knowledge to knowledge integration (Table 4). Based on knowledge graphs, independent analysis, decision-making accomplished by multiple datasets, open-source information systems, and human-computer collaboration technology, AI clarifies the patterns, trends, correlations, and other common phenomena and basic laws in the data through analysis, synthesis, conception, adjustment, and verification [61], and takes over a large amount of empirical and summative thinking work or functions, which can obtain more systematic, comparable, scientific, and reliable results. The deep integration of technology and concepts in related fields such as computer, system, and statistical science in design thought is changing the underlying logic of design under the framework of sustainable concepts. The context of sustainable AI+ thinking will redefine the content, paradigm, process, tools, and means of sustainable design.
Table 4 Typical applications of five technology types in thinking upgrade dimension.
Knowledge representation (user knowledge network graph):
use data information to self-organize sustainable knowledge graph		 Open-source information platform (LeNS global sustainable design knowledge network):
bring together group wisdom as a source of innovation for sustainable solutions [62]		 Human-machine collaboration system (Alibaba Cloud ET environment brain):
machine's accurate calculation and qualitative analysis of data is an important part of scientific research and judgment [63]		 Multi-information conversion (Velodynelidar traffic environment identification system):
make a more comprehensive judgment through comprehensive analysis of all environmental information [64]		 Autonomous decision-making (COVID-19 European regional tracker):
system independently completes information classification, analysis, and processing [65]
The algorithm model or multi-algorithm coupling can more effectively conduct learning, analysis, reasoning, decision-making, and management, making overall consideration of the whole process and whole life-cycle of form elements, energy consumption, ecological impact, and materials [66]. For example, multidimensional data processing and algorithm coupling technology based on networking and cloud platforms, using a backpropagation neural network (BPNN) and multi-objective evolutionary algorithm (MOEA) for multi-objective optimization calculations, can break through the bottleneck of time-consuming
algorithm models (Figure 7). Combining the correlation analysis of various neural network predicted and target values, it can effectively weigh the relationship between natural lighting, thermal comfort performance targets, and equipment energy consumption, and optimize and provide decision support for energy-saving designs.
Figure 7 Multi-performance autonomous analysis of coupling MOEA and BPNN.

Full size|PPT slide

The product's built-in intelligent programs can autonomously perform semantic analysis of input from the outside, judging a user's intentions, demand points, and changes in environmental elements, and feeding back decisions that can create functional value [67]. The Ida smart matching system using machine learning and pattern recognition can automatically recommend full-body clothing matching according to a user's dress preferences or scene requirements, improving the efficiency of clothing utilization [68] (Figure 8). At the same time, we can connect this system to a charity network platform, search for and match its needs, and donate needed clothing.
Figure 8 Ida smart matching system and application scenario.

Full size|PPT slide

6 Simulacrum: Increased Expressiveness of Multidimensional Modal Transformation

The application of artificial intelligence in the direction of simulacrum in sustainable design not only enriches expression methods in multiple dimensions, but also comprehensively enhances expression ability. It presents a trend of upgrading from segmented single-level to full life-cycle, unidirectional expression to real-time interaction, two-dimensional performance to multidimensional combination, materiality to immateriality, and software interface to simulation model (Table 5). Relying on information modeling, digital twins, speech synthesis, image generation, interactive display interfaces, and other technologies, visualized, clear, three-dimensional digital information and signals have information-presentation forms such as two-dimensional image expression, three-dimensional expression, four-dimensional dynamic expression, N-dimensional holographic expression, and N+-dimensional real-time feedback expression [69⇓-71]. They can achieve a full range of expressions from natural and social scales to individual factor scales, from ecological elements to human elements [72], and express intentions, states, and functions immediately and interactively in a variety of forms [73,74]. Multi-factor compound tradeoffs and multi-expression coupled predictive calculations can accurately display information content. The multi-modal information carrier as a medium will become an important link in the interaction between people, things, and the environment, enabling subject and object to quickly achieve the optimal path for the realization of target values.
Table 5 Typical applications of five technology types in simulacrum upgrading dimension.
Knowledge Representation (Meta AI Make-A-Video: a state-of-the-art AI system that generates videos from text):
display of structured meaning of life-cycle information [75,76]		 Resource control platform (environmental information communicator):
combines multiple information expression forms to obtain and convey important information		 Human-machine collaboration system (MIT man-machine interactive interface):
multisensory interactive interface enables people to instantly understand and adjust the adaptability of required functions [77]		 Panoramic simulation (Sony 360-degree cylindrical display):
multichannel dynamic virtual reality simulation greatly reduces cost of expression		 Information modeling system (MONA bionic device generated by image algorithm):
system automatically generates information or morphological models based on data [78]
The intelligent expression system can accurately simulate the form, performance, structure, and influencing factors in detail; achieve full-cycle, full-element, parameterized, multi-scenario, and interactive [79,80] design performance; and promote the integrated process transformation of sustainable design generation and evaluation. Desktop Metal's Live Parts software can use a biologically inspired AI model to quickly generate a three-dimensional shape with performance and structure information with less material consumption, and connect with a 3D printing system to independently generate physical object models based on structural constraints (Figure 9). Live Parts lowers the technical threshold, saves the cost of generation and conversion, and can quickly generate design models.
Figure 9 Live Parts automatic modeling software.

Full size|PPT slide

The intelligent communication system can effectively indicate the product’s functions, intentions, status, and environmental changes, which improves the product’s performance and multi-level user experience, while also strengthening the connection and interaction between smart products [81⇓-83]. For example, auxiliary expression products for ALS patients can integrate brain wave capture and machine learning technology, use voice and imaging technology as a user interface [84] (Figure 10), show the facial expressions and emotions of a patient with a holographic projection, and use speech-synthesis technology to broadcast what a patient wants to say. Flashing lights indicate a brain wave signal, or a situation such as emotional excitement, a need for accompaniment, or equipment failure, saving the use of screen equipment and allowing patients to communicate.
Figure 10 Auxiliary expression products and information simulation system for ALS patients.

Full size|PPT slide

7 Construction: Action Enhancement of Dual Subject Value Creation

The application of artificial intelligence technology to construction in sustainable design not only subdivides the subject of action in a binary manner, but also empowers the effectiveness of the subject's action. It presents a trend of upgrading from low to high efficiency, operability to autonomy, single subject to human-machine coordination, technical support to platform support, and linear operation to alternate generation (Table 6). Performance mapping algorithms, intelligent control platforms, autonomous mobile machines, human-machine mutual-aid devices, and smart wearable devices have made the machine a presence with subjectivity, instrumentality, and objectivity, which can complete self-organization generation and adaptive optimization. The subjective succession of three-system meaning generation is taking place, and the position of "actor" will inevitably exist in the superposition of human and non-human, and network and identity collection [85,86]. The dual agent concept is used for top-down sustainability concept orientation, and the biological mechanism concept is used for bottom-up three-system data orientation. A "biological mechanism" based on the collaboration and linkage of dual agents has established a new connection of "intention-function-value" in the generation of functional value [25]. The new “creative genes” in sustainable design can fully activate human and machine intelligence. Additionally, it can integrate empathy, creativity, responsibility, while also being able to benefit from the instrumental advantages of data, logic, and calculations, which can improve the quality and efficiency of design and function.
Table 6 Typical applications of five technology types in construction upgrading dimension.
Data processing (Alibaba garbage classification APP):
quickly form intelligent behaviors from sustainable knowledge of data		 Resource control platform (JD "Asia One" logistics center):
interconnected machines or programs generate automatic or semi-automatic interactive behavior		 Remote operation participation (MIT inFORM remote design device):
participate on-site in a non-physical, low-carbon way through machine carriers [87]		 Multi-information conversion (MOMA Prona smart streetlamp):
deploy and operate corresponding technical functions based on multiple environmental elements [88]		 Performance mapping model (wooden chair generated by GAN):
algorithm model can independently perform collaborative or assisted creation after learning sustainable cases [89]
Continuously iterating new algorithm models can complete more and more repetitive, computable, and physical design work, as well as preliminary design [90,91] and program evaluation [92,93]. The collaboration of algorithmic machines and humans improves design efficiency, allowing designers to return to the essence of creation [94,95]. For example, Conditional Generative Adversarial Nets (CGANs) can help designers deal with the performance of "structure-morphology" and other dual-element design problems [96,97]. After a CGAN algorithm learns, analyzes, and trains the design data and successful cases collected by the designer, it can automatically find the important characteristics of the environment, society, and economy, and their relationship with the form (Figure 11), and can quickly design a large number of sustainable solutions. The designer can select the best plan, and then deepen the creation and perfect the details.
Figure 11 Sustainable design process of designer and CGAN algorithm machine collaboration.

Full size|PPT slide

The main body of function value output of systematic intelligent products is no longer limited to static functions. Autonomous machines or programs are also the main bodies that carry out functions and create value, which make product functionality more diversified and allow it be realized independently [98,99]. The urban unmanned smart vehicle (PEV) system developed by the MIT Media Laboratory is uniformly controlled by an intelligent monitoring center, which can carry people during peak hours, and express parcels during idle hours (Figure 12). The method of big data analysis and forecasting allows a PEV to reach high-demand areas in advance to balance supply and avoid congestion. A cyclist can call through the mobile phone APP for the nearest PEV to come [100]. The PEV creates a safe, low-carbon, low-cost, shared, friendly travel mode that can increase urban vitality and interpersonal communication.
Figure 12 PEV multipurpose unmanned shared vehicle and its terminal management and control system.

Full size|PPT slide

8 Conclusion

The strong impact of artificial intelligence on sustainable design provides effective assistance in design, service, and operation. Under the complex background of an aging population, urbanization, virtualization, and normalization of the COVID-19 epidemic, sustainable design urgently requires growth points to consolidate the foundation of overall action capacity. Image processing, environmental perception, imaging technology, human-computer interaction, dynamic simulation, voice processing, remote control, data processing, machine decision-making, and other intelligent technologies have increasingly become the theoretical methods and application strategies for design innovation and function upgrading in sustainable design. As an agent, AI can simulate, replace, or cooperate with designers or products in an independent or semi-independent state. It has broad systematic and structured application prospects from many aspects.
In the process of AI to promote sustainable design, although problems of data quality [101,102], ethical safety [103⇓-105], and timeliness of experience [106] exist, they do not affect the gradual progress of AI technology along the four paths of sensation, thinking, simulacrum, and construction [107]. It is being developed as a basic technology of sustainable design, which can extend to the relationships between man and nature, man and society, man and self, and man and intelligence, giving sustainable design rich theoretical and practical capabilities. Interpreting the four-fold upgrade path of sensation, thinking, simulacrum, and construction will help to recognize the new environment, situation, and problems faced by sustainable design, and promote the benign integration of AI technology with sustainable design. The application of technology in the dimensions of cognition, thought, expression, and action should continue to adhere to the dialectical thinking of "flexibility" and "persistence, " develop a balance between nature, humanity, and intelligence, and create applicable, interpretable, sustainable, and intelligent design solutions.

References

Publishing order | Descend order by publishing year | Descend order by cited within
[1]
Zhu W.; Chen H.; Tian S.; Wang H. Artificial intelligence: new blue ocean from a scientific dream—analysis and countermeasures of the development situation of AI industry. Science & Technology Progress and Policy 2016, 33, 66-70.
本文引用 [1]
[2]
Gao Y. Humanistic theories and methods for sustainable architecture; Southeast University Press: Nanjing, China, China, 2021; pp. 23-24.
本文引用 [1]
[3]
The future of the past: Fuller, Alexander and Negroponte.Available online: https://zhuanlan.zhihu.com/p/26611850 (accessed on 26 Oct. 2022).
https://zhuanlan.zhihu.com/p/26611850
本文引用 [1]
[4]
Cai L.; Fan L.; Lai W.; Long Y.; Wang P.; Xin X. Definition, application and influence of artificial intelligence on design industries. Landscape Architecture Frontiers 2018, 6, 56-63.
本文引用 [1]
[5]
Pan Y. The human world is changing from two-dimensional space to three-dimensional space. China Information Weekly 2019, 11, 7.
本文引用 [2]
[6]
Sovrano F.; Sapienza S.; Palmirani M.; Vitali F. Metrics, Explainability and the European AI Act Proposal. J 2022, 5, 126-138.
本文引用 [1]
[7]
Guo Y. Artificial intelligence and home design. Packaging Engineering 2017, 38, 12-15.
本文引用 [1]
[8]
Wang W.; Li Q.; Liu D. Challenges and countermeasures of green development in the era of artificial intelligence. Journal of Xi'an University of Finance and Economics 2020, 33, 30-36.
本文引用 [1]
[9]
Jiang P.; Cao L.; Ni G. The prospect of AI-driven urban planning reform in the new era. Planners 2018, 34, 5-12.
本文引用 [1]
[10]
Wu F.; Lu C.; Zhu M. et al. Towards a new generation of artificial intelligence in China. Nat Mach Intell 2020, 2, 312-316.
本文引用 [1]
[11]
Kshetri N. Artificial Intelligence in Developing Countries. IT Professional 2020, 22, 63-68.
本文引用 [1]
[12]
Li B.; Chai X.; Hou B.; Zhang L.; Zhou J.; Liu Y. New Generation Artificial Intelligence-Driven Intelligent Manufacturing (NGAIIM). 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/ SCALCOM/UIC/ATC/CBDCom/IOP/SCI) 2018, 1864-1869.
本文引用 [1]
[13]
Wu C.; Zhang T. Intelligent unmanned systems: important achievements and applications of new generation artificial intelligence. Front Inform Technol Electron Eng 2020, 21, 649-651.
本文引用 [1]
[14]
Ismail L.; Buyya R. Artificial Intelligence Applications and Self-Learning 6G Networks for Smart Cities Digital Ecosystems: Taxonomy, Challenges, and Future Directions. Sensors 2022, 22, 5750.
本文引用 [1]
[15]
Saghiri A.M.; Vahidipour S.M.; Jabbarpour M.R.; Sookhak M.; Forestiero A. A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions. Appl. Sci. 2022, 12, 4054.
本文引用 [1]
[16]
Manuel C. The rise of the network societ; Social Science Academic Press: Beijing, China, 2001; pp. 441-450.
本文引用 [1]
[17]
The history, present situation, and future of artificial intelligence. Available online: http://www.qstheory.cn/dukan/qs/2019-02/16/c_1124114625.htm (accessed on 25 Oct. 2022).
http://www.qstheory.cn/dukan/qs/2019-02/16/c_1124114625.htm
本文引用 [1]
[18]
Lee K. A Systematic Review on Social Sustainability of Artificial Intelligence in Product Design. Sustainability 2021, 13, 2668.
本文引用 [1]
[19]
Zhong Y. Artificial intelligence: concept, approach and opportunity. Chinese Science Bulletin 2017, 62, 2473-2479.
本文引用 [1]
[20]
Bhardwaj A.; Kishore S.; Pandey D.K. Artificial Intelligence in Biological Sciences. Life 2022, 12, 1430.
本文引用 [1]
[21]
Fan L. From universality computation to universality imagination:a catalog on design & artificial intelligence; Tongji University Press: Shanghai, China, 2009; pp. 6.
本文引用 [1]
[22]
Cüce H.; Özçelik D. Application of Machine Learning (ML) and Artificial Intelligence (AI)-Based Tools for Modelling and Enhancing Sustainable Optimization of the Classical/Photo-Fenton Processes for the Landfill Leachate Treatment. Sustainability 2022, 14, 11261.
本文引用 [1]
[23]
Li F.; Yu G.; Mu C.; Xue Q.; Tseng S.-P.; Wang T. A Personal Growth System Supporting the Sustainable Development of Students Based on Intelligent Graph Element Technology. Sustainability 2022, 14, 7196.
本文引用 [1]
[24]
Villegas-Ch. W.; Jaramillo-Alcázar, A.; Mera-Navarrete A.. Assistance System for the Teaching of Natural Numbers to Preschool Children with the Use of Artificial Intelligence Algorithms. Future Internet 2022, 14, 266.
本文引用 [1]
[25]
Tao F. A New Harmonisation of Art and Technology: Philosophic Interpretations of Artificial Intelligence Art. Critical Arts 2022, 36, 110-125.
本文引用 [2]
[26]
Huang X.; Belongie S. Arbitrary style transfer in real-time with adaptive instance normalization. 2017 IEEE international conference on computer vision, Venice, Italy, 22-29 October 2017.
本文引用 [1]
[27]
Interactive sketching of urban procedural models.Available online: https://hal.archives-ouvertes.fr/hal-01378388 (accessed on 25 Oct. 2022).
https://hal.archives-ouvertes.fr/hal-01378388
本文引用 [1]
[28]
Palette-Based Photo Recoloring, ResearchGate. Available online: https://www.researchgate.net/publication/283663304_Palette-based_Photo_Recoloring (accessed on 26 Oct. 2022).
https://www.researchgate.net/publication/283663304_Palette-based_Photo_Recoloring
本文引用 [1]
[29]
Lin X.-F.; Chen L.; Chan K.K.; Peng S.; Chen X.; Xie S.; Liu J.; Hu Q. Teachers’ Perceptions of Teaching Sustainable Artificial Intelligence: A Design Frame Perspective. Sustainability 2022, 14, 7811.
本文引用 [1]
[30]
Yang Q. The cause, type and essence of interactive experience. In Design research 2014; Zhou, Q.; People’s Publishing; People’s Publishing: Beijing, 2015; pp. 193-201.
本文引用 [1]
[31]
2018 Design and Artificial Intelligence Report. Available online: https://www.tezign.com/designer/#/share/case/vjg2xhpkc/26578?_k=3t0v4f (accessed on 26 Oct. 2022).
https://www.tezign.com/designer/#/share/case/vjg2xhpkc/26578?_k=3t0v4f
本文引用 [1]
[32]
Xue Z. AI changing design:a survival manual for designers in the era of artificial intelligence; Tongji University Press: Shanghai, China, 2019; pp. 51.
本文引用 [1]
[33]
Yin Y.; Chen H.; Zhao H. The application of artificial intelligence in art design. Packaging Engineering 2020, 41, 252-261.
本文引用 [1]
[34]
Lahsen M. Should AI be Designed to Save Us From Ourselves?: Artificial Intelligence for Sustainability. IEEE Technology and Society Magazine 2020, 39, 60-67.
本文引用 [1]
[35]
Zhang Y. Research transformation of humanities and social sciences driven by artificial intelligence. Journal of University of Jinan (Social Science Edition) 2019, 29, 20-28+157.
本文引用 [1]
[36]
Relich M.; Nielsen I.; Gola A. Reducing the Total Product Cost at the Product Design Stage. Appl. Sci. 2022, 12, 1921.
本文引用 [1]
[37]
Fukumura Y.E.; Gray J.M.; Lucas G.M.; Becerik-Gerber B.; Roll S.C. Worker Perspectives on Incorporating Artificial Intelligence into Office Workspaces: Implications for the Future of Office Work. Int. J. Environ. Res. Public Health 2021, 18, 1690.
本文引用 [1]
[38]
Ghosh A.; Chakraborty D.; Law A. Artificial intelligence in Internet of things. CAAI Transactions on Intelligence Technology 2018, 3, 208-218.
[39]
Mulgan G. Artificial intelligence and collective intelligence: the emergence of a new field. AI & Soc 2018, 33, 631-632.
[40]
Wu C.; Zhang T. Intelligent unmanned systems: important achievements and applications of new generation artificial intelligence. Front Inform Technol Electron Eng 2020, 21, 649-651.
[41]
Yau K.-L.A.; Lee H.J.; Chong Y.W.; Ling M.H.; Syed A.R. et al. Augmented Intelligence: Surveys of Literature and Expert Opinion to Understand Relations Between Human Intelligence and Artificial Intelligence. IEEE Access 2021, 9, 136744-136761.
[42]
Pan Y. Artificial intelligence 2.0 and educational development. Chinese Journal of Distance Education 2018, 2, 5-8+44+79.
[43]
Liz Gutiérrez A.M. A new world? Virtual reality, augmented reality, artificial intelligence, enhanced humanity, the Internet of Things. Arbor 2020, 196, a572.
[44]
Michelucci P.; Dicknson L.J. The power of crowds. Science 2016, 351, 32-33.
[45]
Tencent Research Institute; Internet Law Research Center of China Academy of Information Technology; Tencent AI Lab Artificial intelligence; China Renmin University Press: Beijing, China, 2017; pp. 24-26. ISBN: 9787300250502
本文引用 [1]
[46]
Kim J.; Seo D.; Moon J.; Kim J.; Kim H.; Jeong J. Design and Implementation of an HCPS-Based PCB Smart Factory System for Next-Generation Intelligent Manufacturing. Appl. Sci. 2022, 12, 7645.
本文引用 [1]
[47]
Li Q.; Xue Z.; Wu Y.; Zeng X. The Status Quo and Prospect of Sustainable Development of Smart Clothing. Sustainability 2022, 14, 990.
本文引用 [1]
[48]
Fraga-Lamas P.; Lopes S.I.; Fernández-Caramés T.M. Green IoT and Edge AI as Key Technological Enablers for a Sustainable Digital Transition towards a Smart Circular Economy: An Industry 5.0 Use Case. Sensors 2021, 21, 5745.
本文引用 [1]
[49]
Yan X.; Yan J. Design and Implementation of Interactive Platform for Operation and Maintenance of Multimedia Information System Based on Artificial Intelligence and Big Data. Computational Intelligence and Neuroscience 2022, 2022, 1-9.
本文引用 [1]
[50]
Liu S.X.; Zhang M.; Bont C. The holistic frame of designing smart, connected products: A systematic literature review and expert interview. The Design Journal 2022, 25, 334-352.
本文引用 [1]
[51]
Rosário A.T.; Dias J.C. Sustainability and the Digital Transition: A Literature Review. Sustainability 2022, 14, 4072.
本文引用 [1]
[52]
Wu Q. Innovative design thinking in the era of artificial intelligence. Art & Design 2019, 11, 18-21.
本文引用 [1]
[53]
Bahreini K.; Nadolski R.; Westera W. Towards multimodal emotion recognition in e-learning environments. Interactive Learning Environments 2016, 24, 590-605.
本文引用 [1]
[54]
Wang Y.; Zeng Z.; Li Q.; Deng Y. A Complete Reinforcement-Learning-Based Framework for Urban-Safety Perception. ISPRS Int. J. Geo-Inf. 2022, 11, 465.
本文引用 [1]
[55]
Duan L.-T.; Lawo M.; Wang Z.-G.; Wang H.-Y. Human Lower Limb Motion Capture and Recognition Based on Smartphones. Sensors 2022, 22, 5273.
本文引用 [1]
[56]
China Environment Protection Database.Available online: http://hbk.cei.cn/aspx/default.aspx (accessed on 26 Oct. 2022).
http://hbk.cei.cn/aspx/default.aspx
本文引用 [1]
[57]
DesignNet.Available online: https://design-net.org (accessed on 27 Oct. 2022).
https://design-net.org
本文引用 [1]
[58]
Sun C.; Han Y.S.; Ren H. A study on architectural computational design oriented toward artificial intelligence, Architectural Journal 2018, 9, 98-104.
本文引用 [1]
[59]
TerMITes.Available online: https://www.media.mit.edu/projects/termites/overview/ (accessed on 26 Oct. 2022).
https://www.media.mit.edu/projects/termites/overview/
本文引用 [1]
[60]
MIT CityHome is a Gesture-Controlled Home in A Box.Available online: https://www.thecoolist.com/mit-cityhome-high-tech-furniture/mit-cityhome-modular-gesture-controlled-living-console-3 (accessed on 26 Oct. 2022).
https://www.thecoolist.com/mit-cityhome-high-tech-furniture/mit-cityhome-modular-gesture-controlled-living-console-3
本文引用 [1]
[61]
Design thinking for AI: sustainable AI solution design.Available online: https://www.cuelogic.com/blog/design-thinking-for-ai (accessed on 26 Oct. 2022).
https://www.cuelogic.com/blog/design-thinking-for-ai
本文引用 [1]
[62]
Learn Sustainability by Design for All. Available online: http://lenscn.net/search?advanced=true (accessed on 26 Oct. 2022).
http://lenscn.net/search?advanced=true
本文引用 [1]
[63]
"City Brain" Makes Hangzhou Smarter.Available online: http://gzw.zj.gov.cn/art/2021/10/11/art_1229565209_23350.html (accessed on 26 Oct. 2022).
http://gzw.zj.gov.cn/art/2021/10/11/art_1229565209_23350.html
本文引用 [1]
[64]
The World’s Most Advanced Sensor.Available online: https://velodynelidar.com/products/alpha-prime/ (accessed on 26 Oct. 2022).
https://velodynelidar.com/products/alpha-prime/
本文引用 [1]
[65]
Naqvi A. COVID-19 European regional tracker. Sci Data 2021, 8, 181.
本文引用 [1]
[66]
Jang K.; Kim J.-W.; Ju K.-B.; An Y.-K. Infrastructure BIM Platform for Lifecycle Management. Appl. Sci. 2021, 11, 10310.
本文引用 [1]
[67]
Shu Q.; Liu H. Application of Artificial Intelligence Computing in the Universal Design of Aging and Healthy Housing. Computational Intelligence and Neuroscience 2022, 2022, 1-7.
本文引用 [1]
[68]
Relying on the new retail development, Ida has become a marketing tool in the new era. Available online: https://www.sohu.com/a/310286127_491871 (accessed on 26 Oct. 2022).
https://www.sohu.com/a/310286127_491871
本文引用 [1]
[69]
Lee J.H.; Yang E.; Sun Z.Y. Using an Immersive Virtual Reality Design Tool to Support Cognitive Action and Creativity: Educational Insights from Fashion Designers. The Design Journal 2021, 24, 503-524.
本文引用 [1]
[70]
Mozo A.; Karamchandani A.; Gómez-Canaval S.; Sanz M.; Moreno J.I.; Pastor A. B5GEMINI: AI-Driven Network Digital Twin. Sensors 2022, 22, 4106.
本文引用 [1]
[71]
Marelli D.; Bianco S.; Ciocca G. Designing an AI-Based Virtual Try-On Web Application. Sensors 2022, 22, 3832.
本文引用 [1]
[72]
Ospina-Bohórquez A.; Rodríguez-González S.; Vergara-Rodríguez D. On the Synergy between Virtual Reality and Multi-Agent Systems. Sustainability 2021, 13, 4326.
本文引用 [1]
[73]
Nutter D.; Payton V. Collective Memories of Shared Space and Experience in the Creation and Inhabitation of Virtual Studio. The International Journal of Art & Design Education 2021, 40, 773-783.
本文引用 [1]
[74]
Şen G.; Şener B. Experience prototyping through virtual reality head-mounted displays: Design appraisals of automotive user interfaces, The Design Journal 2022, 25, 807-827.
本文引用 [1]
[75]
Meta AI.Available online: https://makeavideo.studio/ (accessed on 24 Sept. 2022).
https://makeavideo.studio/
本文引用 [1]
[76]
Make-A-Video: Text-to-Video Generation without Text-Video Data.Available online: https://arxiv.org/abs/2209.14792 (accessed on 26 Oct. 2022).
https://arxiv.org/abs/2209.14792
本文引用 [1]
[77]
FP CityScope.Available online: https://www.media.mit.edu/projects/finding-places/overview/ (accessed on 26 Oct. 2022).
https://www.media.mit.edu/projects/finding-places/overview/
本文引用 [1]
[78]
Zhao C.Artificial intelligence: cognitive boundary and collaborative innovation: the 5th art and science international exhibition. Art & Design 2019, 11, 38-49.
本文引用 [1]
[79]
Huo K.; Ramani K.Window-shaping: 3D design ideation by creating on, borrowing from, and looking at the physical world. Tangible and embedded interaction 2017, Yokohama, Japan, 20-23 March, 2017.
本文引用 [1]
[80]
Chevalier C.; Kiefer C. What Does Augmented Reality Mean as a Medium of Expression for Computational Artists?. Leonardo 2020, 53, 263-267.
本文引用 [1]
[81]
Predrag K.; Nikolic; Cheok A.D. InnerBody: Using Interactive and Multisensory Interfaces to Design Behavioral Change. Leonardo 2020, 53, 128-134.
本文引用 [1]
[82]
Desnoyers-Stewart J.; Stepanova E.R.; Riecke B.E.; Pennefather P. Body RemiXer: Extending Bodies to Stimulate Social Connection in an Immersive Installation. Leonardo 2020, 53, 394-400.
本文引用 [1]
[83]
Marcolin F. Affective Virtual Reality: How to Design Artificial Experiences Impacting Human Emotions. IEEE Computer Graphics and Applications 2021, 41, 171-178.
本文引用 [1]
[84]
Accenture technology vision.Available online: https://www.urenio.org/2017/04/11/accenture-technology-vision-2017/ (accessed on 27 Oct. 2022).
https://www.urenio.org/2017/04/11/accenture-technology-vision-2017/
本文引用 [1]
[85]
Lu D. Design in the era of artificial intelligence from the perspective of post-humanism, Art Observation 2017, 10, 18-19.
本文引用 [1]
[86]
Baibarac C.; Petrescu D.; Langley P. Prototyping open digital tools for urban commoning, CoDesign 2021, 17, 83-100.
本文引用 [1]
[87]
Kinect-Driven Interface Turns 3D Shapes and Movements into Reality. Available online: https://mashable.com/2013/11/12/mit-inform-kinect/ (accessed on 24 Sept. 2022).
https://mashable.com/2013/11/12/mit-inform-kinect/
本文引用 [1]
[88]
Prona intelligent lighting.Available online: http://www.designmoma.com/industrial/show-516.html (accessed on 26 Oct. 2022).
http://www.designmoma.com/industrial/show-516.html
本文引用 [1]
[89]
Xu X.; Liu J.; Yan Y.; Yang J.M. Development of intelligent design method and its theoretical trend, Packaging Engineering 2020, 41, 10-19.
本文引用 [1]
[90]
Elgammal A.; Liu B.; Elhoseiny M. CAN: creative adversarial networks, generating “art” by learning about styles and deviating from style norms. The eighth international conference on computational creativity (ICCC), Atlanta, America, 20-22 June 2017.
本文引用 [1]
[91]
Li Y. Artificial Neural Network Model for Indoor Decoration Intelligence Calculation and Automation Design, Computational Intelligence and Neuroscience 2022, 2022, 1-13.
本文引用 [1]
[92]
Wang Y.; Yu S.; Chen D.; Chu J.; Liu Z.; Wang J.; Ma N. Artificial intelligence design decision making model based on deep learning. Computer Integrated Manufacturing Systems 2019, 25, 2467-2475.
本文引用 [1]
[93]
Lee K. A Systematic Review on Social Sustainability of Artificial Intelligence in Product Design. Sustainability 2021, 13, 2668.
本文引用 [1]
[94]
Weiler J.; Ingalls T.; Kuznetsov S. Lithobox: Exploring Hybrid Crafting Practices through a Collaboration across Digital Fabrication and Fine Arts. Leonardo 2022, 55, 230-234.
本文引用 [1]
[95]
Dwyer N.O.; Johnson N.; Bates E.; Pagés R.; Ondřej J.; Amplianitis K.; Monaghan D.; Smolic A. Samuel Beckett in Virtual Reality: Exploring Narrative Using Free Viewpoint Video. Leonardo 2021, 54, 166-171.
本文引用 [1]
[96]
Chen L.; Wang P.; Dong H.; Shi F.; Han J.; Guo Y.; Childs PRN.; Xiao J.; Wu C. An artificial intelligence based data-driven approach for design ideation. Journal of visual communication & image representation 2019, 61, 10-22.
本文引用 [1]
[97]
Bahng H.; Yoo S.; Cho W. Coloring with words: guiding image colorization through text-based palette generation. ECCV 2018:European Conference on Computer Vision, Munich, Germany, 8-14 September 2018.
本文引用 [1]
[98]
Eirale A.; Martini M.; Tagliavini L.; Gandini D.; Chiaberge M.; Quaglia G. Marvin: An Innovative Omni-Directional Robotic Assistant for Domestic Environments. Sensors 2022, 22, 5261.
本文引用 [1]
[99]
Dzedzickis A.; Subačiūtė-Žemaitienė J.; Šutinys E.; Samukaitė-Bubnienė U.; Bučinskas V. Advanced Applications of Industrial Robotics: New Trends and Possibilities. Appl. Sci. 2022, 12, 135.
本文引用 [1]
[100]
Persuasive Electric Vehicle (PEV).Available online: https://www.media.mit.edu/projects/pev/overview/ (accessed on 26 Oct. 2022).
https://www.media.mit.edu/projects/pev/overview/
本文引用 [1]
[101]
Regona M.; Yigitcanlar T.; Xia B.; Li R.Y.M. Opportunities and Adoption Challenges of AI in the Construction Industry: A PRISMA Review. J. Open Innov. Technol. Mark. Complex. 2022, 8, 45.
本文引用 [1]
[102]
Shahzad M.; Shafiq M.T.; Douglas D.; Kassem M. Digital Twins in Built Environments: An Investigation of the Characteristics, Applications, and Challenges. Buildings 2022, 12, 120.
本文引用 [1]
[103]
Xu W. User-centered design (Ⅳ): human-centered artificial intelligence. Chinese Journal of Applied Psychology 2019, 25, 291-305.
本文引用 [1]
[104]
Wang L.; Zhang K.How Ethical Design of Artificial Intelligences Systems Is Possible in a Transcultural Perspective. Proceedings 2022, 81, 102.
本文引用 [1]
[105]
Mantini A. Technological Sustainability and Artificial Intelligence Algor-ethics. Sustainability 2022, 14, 3215.
本文引用 [1]
[106]
Scott, C-K. The Teleological Nature of Digital Aesthetics - the New Aesthetic in Advance of Artificial Intelligence. AM Journal of Art and Media Studies 2019, 20, 105-112.
本文引用 [1]
[107]
Luusua A.; Ylipulli J.Artificial Intelligence and Risk in Design. DIS' 20: Proceedings of the 2020 ACM Designing Interactive Systems Conference, Eindhoven, Netherlands, 6-10 July 2020, 1235-1244.
本文引用 [1]
PDF(1873 KB)

238

Accesses

0

Citation

Detail
Sections
Recommended

  • Street Address：
    The 9th Floor, No. 1 Southern Building, Neobay, No. 951 Jianchuan Road,Minhang District, Shanghai, China

    Phone：86-21-34205008-0

    Fax：86-21-34205008-0

Copyright International Journal of Design Science    沪交ICP备20220189

/

〈 〉