A. Liu Cheng
Please Note
21 records found
1
In the Technical branch, Ambient Intelligence (AmI) was coined in the late 90s to describe a cohesive vision of a future digital living room, a built-environment whose computing hardware and software technology imbued its dwelling space with serviceable intelligence to the benefit of its occupant(s) [8]. Also salient in this branch was Ambient Assisted Living—or Active and Assisted Living—(AAL), which framed its inquiry around the promotion of quality of life as well as the prolongation of independence with respect to Activities of Daily Living (ADLs) [9] among the elderly via technical assistance [10].
In the Architectural branch, Cedric Price’s pioneering Generator Project and corresponding programs by John and Julia Frazer [11] in the late 70s, explored notions of interaction between human and non-human agents in the built-environment. In Price’s project, architecture was conceived as a set of interchangeable sub-systems integrated into a unifying computer system, which enabled a reconfigurability sensitive to function. Price and the Frazers intended for the system to suggest its own reconfigurations, denoting non-human agency.
The promise of solutions yielded by both AmI/AAL and IA/AA is limited by the rigid and increasingly outdated assumptions in their approaches. It is not possible, as they are and as they are currently developing, to combine AmI/AAL and IA/AA to yield a unified and cohesive approach. This is because the sophistication of a system will depend on that of its mutually complementing subsystems; and two or more subsystems may not mutually complement, sustain, and/or support one another properly if their levels of development and sophistication do not correspond [12]. That is: at present, the architectural does not correspond to the technically predominant AmI/AAL, while the technical does not correspond to the architecturally predominant IA/AA. Consequently, a different design-approach is required in order to enable comprehensively and cohesively intelligent built-environments with corresponding levels of technical and architectural sophistication. What could such an approach look like?
In this thesis, an alternative approach that conceives of the intelligent built-environment as a Cyber-Physical System (CPS) is presented and demonstrated. Under this approach, ICTs and Architectural considerations in conjunction instantiate intelligence fundamentally—i.e., unlike existing AmI/AAL or IA/AA approaches, the present approach subsumes enabling technologies into the very core of the built-environment, where a solution does not exist as such without either of its informational and physical constituents deliberately conceived for each other (if not formally, at least conceptually and operationally with respect to instantiated services).
In this thesis, the general potential and promise of the presented approach is illustrated via its application to a constrained use-case—i.e., that of intelligent built-environments for elderly assistance and care (also informally referred to as smart homes or environments). Twelve proof-of-concept demonstrators (see Chapter 5), each showcasing an intelligent product and/or a service—or combinations and sets thereof—integrated into the built-environment and/or its ecosystem, are developed. Eight established parameters (see Section 3.2)—four pertaining to Indoor Environmental Quality (IEQ) and four Quality of Life (QoL)—define the purpose and inform the design of each demonstrator’s setup and development within four types of demo environments (see Chapter 4)—two Physical (Hyperbody and Robotic Building) and two Virtual (Digital Twin and Non-descript). Each demonstrator, while presented as a discrete proof-of-concept, builds on the same core System Architecture, and are intended to be viewed as a collection of systems and services expressed within a same hypothetical environment. That is to say, all come together to represent the intelligent built-environment as CPS.
All demonstrators are functionally and physically developed and involve human participation to test and to validate both the feasibility and success of the concept. Success is determined if the developed products and services indeed provide added value to a user and/or occupant of the space—i.e., if they promote and contribute to well-being by assisting, facilitating, or enhancing. Accordingly, the tangible nature of the process and results promote—albeit in a limited scope—the presented approach in very real terms, and—hopefully—situate it as an alternative to existing modes of imbuing intelligence in the built-environment.
...
In the Technical branch, Ambient Intelligence (AmI) was coined in the late 90s to describe a cohesive vision of a future digital living room, a built-environment whose computing hardware and software technology imbued its dwelling space with serviceable intelligence to the benefit of its occupant(s) [8]. Also salient in this branch was Ambient Assisted Living—or Active and Assisted Living—(AAL), which framed its inquiry around the promotion of quality of life as well as the prolongation of independence with respect to Activities of Daily Living (ADLs) [9] among the elderly via technical assistance [10].
In the Architectural branch, Cedric Price’s pioneering Generator Project and corresponding programs by John and Julia Frazer [11] in the late 70s, explored notions of interaction between human and non-human agents in the built-environment. In Price’s project, architecture was conceived as a set of interchangeable sub-systems integrated into a unifying computer system, which enabled a reconfigurability sensitive to function. Price and the Frazers intended for the system to suggest its own reconfigurations, denoting non-human agency.
The promise of solutions yielded by both AmI/AAL and IA/AA is limited by the rigid and increasingly outdated assumptions in their approaches. It is not possible, as they are and as they are currently developing, to combine AmI/AAL and IA/AA to yield a unified and cohesive approach. This is because the sophistication of a system will depend on that of its mutually complementing subsystems; and two or more subsystems may not mutually complement, sustain, and/or support one another properly if their levels of development and sophistication do not correspond [12]. That is: at present, the architectural does not correspond to the technically predominant AmI/AAL, while the technical does not correspond to the architecturally predominant IA/AA. Consequently, a different design-approach is required in order to enable comprehensively and cohesively intelligent built-environments with corresponding levels of technical and architectural sophistication. What could such an approach look like?
In this thesis, an alternative approach that conceives of the intelligent built-environment as a Cyber-Physical System (CPS) is presented and demonstrated. Under this approach, ICTs and Architectural considerations in conjunction instantiate intelligence fundamentally—i.e., unlike existing AmI/AAL or IA/AA approaches, the present approach subsumes enabling technologies into the very core of the built-environment, where a solution does not exist as such without either of its informational and physical constituents deliberately conceived for each other (if not formally, at least conceptually and operationally with respect to instantiated services).
In this thesis, the general potential and promise of the presented approach is illustrated via its application to a constrained use-case—i.e., that of intelligent built-environments for elderly assistance and care (also informally referred to as smart homes or environments). Twelve proof-of-concept demonstrators (see Chapter 5), each showcasing an intelligent product and/or a service—or combinations and sets thereof—integrated into the built-environment and/or its ecosystem, are developed. Eight established parameters (see Section 3.2)—four pertaining to Indoor Environmental Quality (IEQ) and four Quality of Life (QoL)—define the purpose and inform the design of each demonstrator’s setup and development within four types of demo environments (see Chapter 4)—two Physical (Hyperbody and Robotic Building) and two Virtual (Digital Twin and Non-descript). Each demonstrator, while presented as a discrete proof-of-concept, builds on the same core System Architecture, and are intended to be viewed as a collection of systems and services expressed within a same hypothetical environment. That is to say, all come together to represent the intelligent built-environment as CPS.
All demonstrators are functionally and physically developed and involve human participation to test and to validate both the feasibility and success of the concept. Success is determined if the developed products and services indeed provide added value to a user and/or occupant of the space—i.e., if they promote and contribute to well-being by assisting, facilitating, or enhancing. Accordingly, the tangible nature of the process and results promote—albeit in a limited scope—the presented approach in very real terms, and—hopefully—situate it as an alternative to existing modes of imbuing intelligence in the built-environment.
This paper describes the development of a Smart Sleeve control mechanism for Active Assisted Living. The Smart Sleeve is a physically worn sleeve that extends the user's control capability within his/her intelligent built-environment by enabling (1) direct actuation and/or (2) teleoperation via a virtual interface. With respect to the first, the user may point his/her sleeve-wearing arm towards a door or a window and actuate an opening or a shutting; or towards a light and effect its turning on and off as well as regulating its intensity; or even towards a particular region to initiate ventilation of it. With respect to the second, the user may engage actuations in systems beyond his/her field of vision by interacting with a virtual representation of the intelligent built-environment projected on any screen or surface. For example, the user is able to shut the kitchen's door from his/her bedroom by extending the Smart Sleeve towards the door of a virtual representation of the kitchen projected (via a standard projector and/or television monitor) on the bedroom's wall. In both cases, the Smart Sleeve recognizes the object which the user wishes to engage with-whether in the real or the virtual worlds-(a) by detecting the orientation of the extended arm via an Accelerometer / Gyroscope / Magnetometer sensor; and (b) by detecting a specific forearm muscle contraction via Electromyography caused by the closing and opening of the fist, which serves to select the object. Once the object is identified and selected with said muscle contraction, subsequent arm gestures effect a variety of possible actuations for a given object (e.g., a window may be opened / shut or dragged to differing degrees or aperture; a light's intensity may be increased or decreased, etc.). In cases of ambiguous selections, the user my use voice-commands to explicitly identify the desired object of selection. Furthermore, due to this voice-based recognition mechanism, which recognizes both spoken commands as well the identity of the speakers, different rights to actuation may be assigned to different users. The Smart Sleeve is yet another mechanism integrated into an on-going development of a highly intuitive Active and Assisted Living implementation and its features, ones explicitly designed to enhance user-experience as well as to promote user well-being via intuitive interactions between human and non-human agents within the intelligent built-environment.
This paper presents an adaptive rainwater-harvesting (RWH) system based on a rainwater-collecting unit that (1) ascertains baseline water-quality in its collected rainwater via Ph- and turbidity sensors, and (2) redistributes it to designated toilet-tanks and/or irrigation points. Each unit is integrated with an XBee S2B antenna to enable cost-effective and energy-efficient mesh capabilities for inter-unit communication when two or more units conform the system. Moreover, each unit is also an Internet-of-Things (IoT) device that transmits water-tank levels and sensor-data to a local supervising microcontroller (MCU) via Open Sound Control (OSC). This MCU is, in turn, capable of communication with a cloud-based data plotting / storing and remote-control platform - viz., Adafruit IO - via Message Queueing Telemetry Transport (MQTT). The interface with Adafruit IO enables a remote administrator (a) to monitor water-tank levels and sensor readings, and (b) to execute manual overrides in the system - for example, any or all of the units may be shut-down remotely. When only one unit conforms the system, its water-tank services the toilet-tanks and/or irrigation points connected to the unit. When two or more units conform the system, their water-tank outputs are physically linked, enabling any unit to contribute to the servicing of a variety of connected toilet-tanks and/or irrigation points. In both single or multi-unit configurations, water redistribution is impartial to any end-point at initialization, yet over time the system identifies which end-point(s) require(s) water with a higher frequency and selectively prioritizes servicing to it/them to guarantee prompt refill / supply. The present work is part of ongoing developments of features and services that attempt to imbue the builtenvironment with intelligence via Information and Communication Technologies (ICTs).
This paper details the development of an open-source eye- and gaze-tracking mechanism designed for open, scalable, and decentralized Active and Assisted Living (AAL) ecosystems built on Wireless Sensor and Actuator Networks (WSANs). Said mechanism is deliberately conceived as yet another service-feature in an on-going implementation of an extended intelligent built-environment framework, one motivated and informed by both Information and Communication Technologies (ICTs) as well as by emerging Architecture, Engineering, and Construction (AEC) considerations. It is nevertheless designed as a compatible and subsumable service-feature for existing above-characterized AAL frameworks. The eye- and gaze-tracking mechanism enables the user (1) to engage (i.e., open, shut, slide, turn-on/-off, etc.) with a variety of actuable objects and systems deployed within an intelligent built-environment via sight-enabled identification, selection, and confirmation; and (2) to extract and display personal identity information from recognized familiar faces viewed by the user. The first feature is intended principally (although not exclusively) for users with limited mobility, with the intention to support independence with respect to the control of remotely actuable mechanisms within the built-environment. The second feature is intended to compensate for loss of memory and/or visual acuity associated principally (although not exclusively) with the natural aging process. As with previously developed service-features, the present mechanism intends to increase the quality of life of its user(s) in an affordable, intuitive, and highly intelligent manner.
This paper details the development of an acoustically adaptive modular system capable of enhancing Speech Clarity (C50 Clarity Index) in specific locations within a space in near real-time. The mechanical component of the system consists of quadrilateral, truncated pyramidal modules that extend or retract perpendicularly to their base. This enables said modules (1) to change in the steepness of the sides of their frustum, which changes the way incoming sound waves are deflected/reflected/diffused by the surfaces of the pyramid; and (2) to reveal or to hide the absorbent material under each module, which enables a portion of incoming sound waves to be absorbed/dissipated in a controlled manner. The present setup considers a fragmentary implementation of six modules. The behavior of these modules is determined by two steps in the computational component of the system. First, the initial position of the modules is set via a model previously generated by an evolutionary solver, which identifies the optimal extension/retraction extent of each of the six modules to select for individual configurations that collectively ascertain the highest clarity in said specific locations. Second, a simulated receiver at the location in question measures the actual clarity attained and updates the model’s database with respect to the configuration’s corresponding clarity-value. Since the nature of acoustics is not exact, if the attained measurement is lower than the model’s prediction for said location under the best module-configuration, but higher than the second-best configuration for the same location, the modules remain at the initial configuration. However, if the attained values are lower, this step reconfigures the modules to instantiate the second—or third-, fourth-, etc.—best configuration and updates the model’s database with respect to the new optimal module-configuration value. These steps repeat each time the user moves to another specific location. The objective of the system is to contribute to the intelligent and intuitive Speech Clarity regulation of an inhabited space. This contributes to its Interior Environmental Quality, which promotes well-being and quality of life.
This paper details a proof-of-concept development of an adaptive staircase system-type capable of user-specific mechanical reconfigurations actuated by facial-, object-, and voice-recognition. The system is described via two variation-prototypes - developed at Technology Readiness Level 4 - as instances of the same system-type. Accordingly, each prototype is informed by the same use-case considerations and requirements. Nevertheless, by means of their mechanical particulars, advantages and disadvantages specific to each variation are identified and explored. The present adaptive staircase system-type consists of two main components, one computational and the other mechanical. The computational component is built upon an inherited System Architecture previously developed and implemented by the authors. More specifically, the computational component uses Google's TensorFlow for facial-recognition; BerryNet for multi-object detection; and VoiceIt for voice-recognition. These three cloud-compatible, -based, or -dependent recognition mechanisms are used to ascertain the identity three user-types: (1) a person without perceivable physical disabilities; (2) a person reliant on a walking-cane; and (3) a person on a wheelchair. With the exception of the first case, the computational component proceeds to actuate mechanical transformations pertinent to each variety of disabilities depending on which user-type is identified. The objective of this implementations is to present an intuitive and automated vertical mobility solution capable of supporting users with varying degrees of reduced mobility.
This paper presents a context-Aware light-Tracking and-redirecting system guided by hand-gesture recognition. It is conceived as yet another mechanism within an ongoing development of a more intuitive and technically sophisticated Ambient Intelligence / Active and Assisted Living ecosystem. The detailed system consists of individual nodes that are strategically installed across regions of a building-envelope, which enables this latter to draw or deflect direct natural light into or away from specific locations within the built-environment as requested by the user(s) via recognized hand-gestures. Each node is capable of sending and receiving sensed-data continuously via ZigBee with one another as well as with microcontrollers embedded within the interior built-environment. Said microcontrollers are equipped with cameras via which four hand-gestures may be recognized. The first or initializing hand-gesture engages the system and enables it to recognize any of the remaining hand-gestures. The second redirects light towards the position of the detected hand-gesture, while the third redirects it away from said position. Finally, the fourth gesture turns the light-Tracking and-redirecting system off.
This paper presents the implementation of a facial-identity and-expression recognition mechanism that confirms or negates physical and/or computational actuations in an intelligent built-environment. Said mechanism is built via Google Brain's TensorFlow (as regards facial identity recognition) and Google Cloud Platform's Cloud Vision API (as regards facial gesture recognition); and it is integrated into the ongoing development of an intelligent built-environment framework, viz., Design-To-Robotic-Production &-Operation (D2RP&O), conceived at Delft University of Technology (TUD). The present work builds on the inherited technological ecosystem and technical functionality of the Design-To-Robotic-Operation (D2RO) component of said framework; and its implementation is validated via two scenarios (physical and computational). In the first scenario-and building on an inherited adaptive mechanism-if building-skin components perceive a rise in interior temperature levels, natural ventilation is promoted by increasing degrees of aperture. This measure is presently confirmed or negated by a corresponding facial expression on the part of the user in response to said reaction, which serves as an intuitive override / feedback mechanism to the intelligent building-skin mechanism's decision-making process. In the second scenario-and building on another inherited mechanism-if an accidental fall is detected and the user remains consciously or unconsciously collapsed, a series of automated emergency notifications (e.g., SMS, email, etc.) are sent to family and/or care-Takers by particular mechanisms in the intelligent built-environment. The precision of this measure and its execution are presently confirmed by (a) identity detection of the victim, and (b) recognition of a reflexive facial gesture of pain and/or displeasure. The work presented in this paper promotes a considered relationship between the architecture of the built-environment and the Information and Communication Technologies (ICTs) embedded and/or deployed.
This paper extends the development of a responsive built-environment capable of expressing intelligence with respect to both ICTs and Adaptive Architecture. The present implementation is built with mutually informing Design-to-Robotic-Production &-Operation (D2RP&O) strategies and methods developed at Delft University of Technology (TUD). With respect to D2RP, a responsive stage built with deliberately differentiated and function-specific components is revisited and modified. With respect to D2RO, a partially meshed, self-healing, and highly heterogeneous Wireless Sensor and Actuator Network (WSAN) is expanded to integrate proprietary-yet-free cloud-based services. This WSAN is equipped with Machine Learning (ML) mechanisms based on Support Vector Machine (SVM) classifiers for Human Activity Recognition (HAR). The frequency and/or absence of certain activities, in conjunction with processed data streamed from environment-embedded sensing mechanisms, trigger actuations in the built-environment in order to mitigate fatigue, encourage activity / interactivity; and to promote general well-being in the user. A voice-enabled mechanism based on Amazon®’s Alexa Voice Service (AVS) is integrated into the ecosystem to connect the built-environment with services and resources in the World Wide Web (WWW). Furthermore, a notifications mechanism based on Google®’s Gmail
This paper presents the integration of an Internet of Things wearable device as a personal interfacing node in an intelligent built-environment framework, which is informed by Design-to-Robotic-Production and -Operation principles developed at Delft University of Technology. The device enables the user to act as an active node in the built-environment's underlying Wireless Sensor and Actuator Network, thereby permitting a more immediate and intuitive relationship between the user and his/her environment, where this latter is integrated with physical / computational adaptive systems and services. Two main resulting advantages are identified and illustrated. On the one hand, the device's sensors provide personal (i.e., body temperature / humidity, physical activity) as well as immediate environmental (i.e., personal-space air-quality) data to the built-environment's embedded / ambulant systems. Moreover, rotaries on the device enable the user to override automatically established illumination and ventilation settings in order to accommodate user-preferences. On the other hand, the built-environment's systems provide notifications and feedback with respect to their status to the device, thereby raising user-awareness of the state of his/her surroundings and corresponding interior environmental conditions. In this manner, the user becomes a context-aware node in a Cyber-Physical System. The present work promotes a considered relationship between the architecture of the built-environment and the Information and Communication Technologies embedded and/or deployed therein in order to develop highly effective alternatives to existing Ambient Intelligence solutions.
Scaffolding assembly constitutes a potentially dangerous and time-consuming task within the construction process. In most industrialized nations, said assembly is the process in which most of the causalities of the Construction Industry happen, especially in projects characterized by high complexity and restricted operation space. The repetitiveness of the profile elements and of the assembly operations may open the possibility for automating the scaffolding construction process, which is however a difficult task due to the unstructured environment of construction sites and the implied strong collaboration of human and machine agents. As a possible automation solution, the startup KEWAZO proposes a novel robotic scaffolding assembly system. The solution focuses on the development of small-sized robotic climbing modules controlled as an integrated system. This paper focuses on the development of the robotic gripper of said modular system. The gripper system is validated through static analysis and the construction of a fully functional prototype. Furthermore, the system is integrated with a voice identification / authentication and control mechanism that enables it to recognize a variety of human identities and to engage with verbal commands according to the authority and privileges assigned to each individual.
Two core considerations inform this assessment. The first asserts that such paradigms produce spaces and programmatic distributions in terms of discrete, precisely delimited, and artificially ordered static partitions. The second asserts that said paradigms preclude (at best) or exclude (at worst) discussions of technological intelligence from the early stages of the design process, thereby negating the possibility of imbuing the built-environment with inherent intelligence. The rigidity expressed in the first consideration, and the disregard for technological intelligence expressed in the second, produce very low-resolution and -adaptability architectures. As a result, occupants are compelled to conform to their built-environment rather than the expected vice versa, as it is fundamentally incapable of actively, reactively, and interactively promoting
their well-being. In this paper, two key positions (i.e., high resolution space and high resolution intelligence) motivated by the above considerations are promoted as part of a fundamentally different design paradigm, one expressly geared towards personalization, interaction, and intelligence in a parametrically fluid and self-adapting built-environment capable of intuitive physical, spatial, and computational feedback-loops. ...
Two core considerations inform this assessment. The first asserts that such paradigms produce spaces and programmatic distributions in terms of discrete, precisely delimited, and artificially ordered static partitions. The second asserts that said paradigms preclude (at best) or exclude (at worst) discussions of technological intelligence from the early stages of the design process, thereby negating the possibility of imbuing the built-environment with inherent intelligence. The rigidity expressed in the first consideration, and the disregard for technological intelligence expressed in the second, produce very low-resolution and -adaptability architectures. As a result, occupants are compelled to conform to their built-environment rather than the expected vice versa, as it is fundamentally incapable of actively, reactively, and interactively promoting
their well-being. In this paper, two key positions (i.e., high resolution space and high resolution intelligence) motivated by the above considerations are promoted as part of a fundamentally different design paradigm, one expressly geared towards personalization, interaction, and intelligence in a parametrically fluid and self-adapting built-environment capable of intuitive physical, spatial, and computational feedback-loops.