Many practical barriers continue to exist for a blind individual who strives to lead an independent and active life, despite decades of development of assistive technologies. This project addresses the following two most prominent challenges: (1) disparity in information-sharing among people with visual impairment and its limited understanding by the research community; and (2) lack of methods and tools for effectively addressing the disparity. The central idea is to engage visually-impaired people and their families and friends to directly contribute to a joint endeavor of enhancing information flow, increasing awareness, and improving efficiency of assistive practices, through employing social media and participatory Web. The research is focused on designing computational methodologies and developing tools that are necessary for building cyber-physical systems for a domain where the tight intertwining of physical and cyber systems plus active participation of the human users are the key to attaining the otherwise unlikely capabilities for improving the quality of living for people with special needs. The key approach is to develop a blind-specific cyber-physical system that supports social-media-based crowdsourcing. This enables visually-impaired people to form loosely-connected groups, actively contribute their information and knowledge, and ask/answer unique questions of special needs. Such a system has specific features required: i) blind-friendly (both the cyber components and the physical components); ii) able to provide constantly-updated information, as opposed to just static websites); iii) able to support the users? real-time query for information when mobile iv) able to provide information that is important to the users? daily living, and v) supports expandability and scalability of the CPS, e.g., being able to bridge to other existing social network sites or to expand the virtual community. Specific approaches include automatic direction inquiry, instant call-in/text-in system, community-specific data mining, information retrieval and behavior modeling, all aiming at providing the most useful information for the target user. Aiming at bridging a significant knowledge gap in addressing the challenge of disparity in information-sharing for people with special needs in the age of social media, the project contributes to the development of a deeper understanding of the principles and methodologies in building new cyber-physical systems that promote and support active participation of users of the system, which is especially important for special-need groups such as the visually impaired, the elderly, etc. The significant impact of the work on the society lies in its potential in empowering special-need groups to pursue active and independent living in the information era. The work?s immediate impact on education is two-fold: supporting the visually-impaired students in independent learning and study as well as training students to work on emerging domains of tightly-intertwined cyber and physical systems.

The objective of this research is to develop a comprehensive theoretical and experimental cyber-physical framework to enable intelligent human-environment interaction capabilities by a synergistic combination of computer vision and robotics. Specifically, the approach is applied to examine individualized remote rehabilitation with an intelligent, articulated, and adjustable lower limb orthotic brace to manage Knee Osteoarthritis, where a visual-sensing/dynamical-systems perspective is adopted to: (1) track and record patient/device interactions with internet-enabled commercial-off-the-shelf computer-vision-devices; (2) abstract the interactions into parametric and composable low-dimensional manifold representations; (3) link to quantitative biomechanical assessment of the individual patients; (4) facilitate development of individualized user models and exercise regimen; and (5) aid the progressive parametric refinement of exercises and adjustment of bracing devices. This research and its results will enable us to understand underlying human neuro-musculo-skeletal and locomotion principles by merging notions of quantitative data acquisition, and lower-order modeling coupled with individualized feedback. Beyond efficient representation, the quantitative visual models offer the potential to capture fundamental underlying physical, physiological, and behavioral mechanisms grounded on biomechanical assessments, and thereby afford insights into the generative hypotheses of human actions. Knee osteoarthritis is an important public health issue, because of high costs associated with treatments. The ability to leverage a quantitative paradigm, both in terms of diagnosis and prescription, to improve mobility and reduce pain in patients would be a significant benefit. Moreover, the home-based rehabilitation setting offers not only immense flexibility, but also access to a significantly greater portion of the patient population. The project is also integrated with extensive educational and outreach activities to serve a variety of communities.

Robotic devices are excellent candidates for delivering repetitive and intensive practice that can restore functional use of the upper limbs, even years after a stroke. Rehabilitation of the wrist and hand in particular are critical for recovery of function, since hands are the primary interface with the world. However, robotic devices that focus on hand rehabilitation are limited due to excessive cost, complexity, or limited functionality. A design and control strategy for such devices that bridges this gap is critical. The goals of the research effort are to analyze the properties and role of passive dynamics, defined by joint stiffness and damping, in the human hand and wrist during grasping and manipulation, and then mimic such properties in a wrist-hand exoskeleton for stroke rehabilitation. The project will culminate with device testing in collaboration with rehabilitation clinicians. A significant problem in robotic rehabilitation is how to provide assisted movement to the multiple degrees of freedom of the hand in order to restore motor coordination and function, with a system that is practical for deployment in a clinical environment. Armed with a clearer understanding of the mechanisms underlying passive dynamics and control of systems exhibiting such behavior, this project will inform the design of more effective wrist/hand rehabilitation devices that are feasible for clinical use. In addition, the proposed project will create a unique interdisciplinary environment enabling education, training, and co-advising of graduate students, undergraduate research, and significant and targeted outreach activities to underrepresented groups in science and engineering.

This project develops a framework for design automation of cyber-physical systems to augment human interaction with complex systems that integrate across computational and physical environments. As a design driver, the project develops a Body/Brain Computer Interface (BBCI) for the population of functionally locked-in individuals, who are unable to interact with the physical world through movement and speech. The BBCI will enable communication with other humans through expressive language generation and interaction with the environment through robotic manipulators. Utilizing advances in system-level design, this project develops a holistic framework for design and implementation of heterogeneous human-in-the-loop cyber-physical systems composed of physically distributed, networked components. It will advance BBCI technology by incorporating context aware inference and learning of task-specific human intent estimation in applications involving semi-autonomous robotic actuators and an efficient wireless communication framework. The results of this project are expected to significantly speed up the design of complex cyber-physical systems. By accelerating the path from idea to prototype, this work shortens the time frame of and cost of development for assistive technology to improve the quality-of-life for functionally locked-in individuals. This project establishes an open prototyping platform and a design framework for rapid exploration of other novel human-in-the-loop applications. The open platform will foster undergraduate involvement in cyber-physical systems research, building confidence and expertise. In addition, new activities at the Museum of Science in Boston will engage visitors to experiment with systematic design principles in context of a brain computer interface application, while offering learning opportunities about basic brain functions.

Robotic devices are excellent candidates for delivering repetitive and intensive practice that can restore functional use of the upper limbs, even years after a stroke. Rehabilitation of the wrist and hand in particular are critical for recovery of function, since hands are the primary interface with the world. However, robotic devices that focus on hand rehabilitation are limited due to excessive cost, complexity, or limited functionality. A design and control strategy for such devices that bridges this gap is critical. The goals of the research effort are to analyze the properties and role of passive dynamics, defined by joint stiffness and damping, in the human hand and wrist during grasping and manipulation, and then mimic such properties in a wrist-hand exoskeleton for stroke rehabilitation. The project will culminate with device testing in collaboration with rehabilitation clinicians. A significant problem in robotic rehabilitation is how to provide assisted movement to the multiple degrees of freedom of the hand in order to restore motor coordination and function, with a system that is practical for deployment in a clinical environment. Armed with a clearer understanding of the mechanisms underlying passive dynamics and control of systems exhibiting such behavior, this project will inform the design of more effective wrist/hand rehabilitation devices that are feasible for clinical use. In addition, the proposed project will create a unique interdisciplinary environment enabling education, training, and co-advising of graduate students, undergraduate research, and significant and targeted outreach activities to underrepresented groups in science and engineering.

This project aims to develop a computational framework and a physical platform for enabling dense networks of micro-robotic swarms for medical applications. The approach relies on a new stochastic framework for design and analysis of dense networks, as well as new fabrication and characterization methods for building and understanding bacteria propelled micro-robotic swarms. This project enhances the CPS science beyond passive networks of millimeter-scale bio-implantable devices with active networks of micro-robotic swarms that could be more effective in combating various critical diseases with minimal impact on the human body. Three major research objectives are proposed in this project: 1) Statistical physics inspired approach to the modeling and analysis of dense networks of swarms: The theory envisioned for characterizing the dynamics of dense networks of swarms aims at achieving ?beyond Turing? computation via dense networks, designing autonomous reliable communication protocols for dense networks, and estimating and controlling their performance; 2) Fabrication and steering of swarms of bacteria propelled swimming micro-robots: Large numbers of both chemotactic and magnetotactic bacteria integrated micro-robotic bodies will be fabricated using self-assembly and micro/nano-fabrication methods. Chemotaxis and magnetotaxis will be respectively used as passive and active steering mechanisms for navigating the swarms of micro-robots in small spaces to perform specified tasks; 3) Characterization of the behavior and control of bacteria propelled micro-robotic swarms: To validate and fine tune the proposed computational models, the motion and behavior of single and large numbers of bacteria propelled micro-robots will be characterized using optical and other microscopy methods. Intellectual Merit: The research breakthrough proposed herein consists of building a new physical platform for micro-robotic swarms by using attached bacteria as on-board actuators and chemotaxis and magnetotaxis as passive and active steering control methods, and developing a new computational dense network framework for designing and analyzing such stochastic micro-robotic swarms. The statistical computational framework to be developed in this study will improve understanding of swarming behavior and control of large numbers of bacteria propelled micro-robots. This framework offers an integrated approach towards CPS design that is meant to operate under uncertainty conditions, yet be able to succeed in performing a specified task through self-organization and collective behavior. This bottom-top approach is meant to improve the theoretical foundations of the current computational models of CPS. Broader Impacts: The resulting computational framework and the physical platform could be adapted to a wide range of different stochastic dense network systems ranging from migration of cancer cell populations or dynamics of virus populations to immune system support and modeling. The proposed swarms of bacteria integrated micro-robots have potential future applications in health-care for the diagnosis of diseases and targeted drug delivery inside the stagnant or low velocity fluids of the human body or the medical diagnosis inside lab-on-a-chip microfluidic devices. Such health-care applications could improve the welfare of our society. To foster learning and training of next generation CPS workforce, the PIs plan to emphasize a cross-disciplinary approach to teaching topics that are usually offered in disjoint tracks. The PIs will integrate the CPS research activities in this study into their newly developed courses, and they will also teach one of these courses jointly. As a joint international educational activity, a three-day Summer School will be held alternately in US and Europe every year on various CPS topics related to our project. This will help building a strong international CPS community and training US and European students in CPS topics. The PIs will present the research results of this project to children, K-12 students, K-12 teachers, IEEE and ACM student members, and college students inside and outside of USA through public lectures. This project and the Sloan Foundation will support underrepresented and minority graduate students in the project. Moreover, underrepresented minority undergraduate students will be trained through the CMU ICES summer outreach program called The SURE Thing and the NSF REU program.

This project integrates digital microfluidics with thin-film photodetectors and control software to realize DNA target sensing using fluorescence. This cyberphysical vision is being realized through tight coupling between physical components, the microfluidic platform and miniaturized sensors, and cyber components, software for control, decision-making, and adaptation. Such a level of integration, decision, and controlled reconfigurability is a significant step forward in clinical diagnostics using digital microfluidic biochips. Topics being investigated include: (i) silicon-based digital microfluidics and integration of optical sensors; (ii) closed-loop operation and run-time optimization under software control; (iii) decision-tree architectures, adaptive reconfiguration, and error recovery. A complete testbed is being developed for nucleic acid identification on a fabricated chip with detection sites. Cyberphysical system integration will transform biochip use, in the same way as compilers and operating systems revolutionized computing, and design automation revolutionized chip design. Benefits to society include the potential to transform personalized medicine, home diagnostics, and portable diagnostics. Integration of digital microfluidics, optical sensing, and software control has the potential to create systems that can be used by any person, regardless of sample preparation skill. One example is the identification of bacterial DNA associated with bacterial blood infection (sepsis), which results in death if not diagnosed early (this is in the top 10 causes of death in the US). Students are being trained through a Senior Design course to understand the design

The objective of this research is to develop a cyber-physical system composed of accelerometers and novel machine learning algorithms to analyze data in the context of a set of driving health care applications. The approach is to develop novel machine learning algorithms for temporal segmentation, classification, and detection of subtle elements of human motion. These techniques will allow quantification of human motion and improved full-time monitoring and assessment of medical conditions using a lightweight wearable system. The scientific contribution of this research is in advancing machine learning and human sensing in support of improved medical diagnoses and treatment monitoring by (i) modeling human activity and symptoms through sensor data analysis, (ii) integrating and fusing information from several accelerometers to monitor in real-time, (iii) validating the efficacy of the automated detection through assessments applying the state of the art in diagnostic evaluation, (iv) developing novel machine learning methods for temporal segmentation, classification, and discovery of multiple temporal patterns that discriminate between temporal signals, and (v) providing quality measures to characterize subtle human motion. These algorithms will advance machine learning in the area of unsupervised and semisupervised learning. The driving applications for this research are job coaching for people with cognitive disabilities, tele-rehabilitation for knee osteo-arthritis, assessing variability in balance and gait as an indicator of health of older adults, and measures for assessing Parkinson's patients. This research is highly interdisciplinary and will train graduate students for careers in developing technological innovations in health and monitoring systems.

The objective of this research is to develop a trustworthy and high-performance neural-machine interface (NMI) that accurately determines a user?s locomotion mode in real-time for neural-controlled artificial legs. The proposed approach is to design the NMI by integrating a new pattern recognition strategy with a high-performance computing embedded system. This project tackles the challenges of accurate interpretation of information from the neuromuscular system, a physical system, using appropriate computation in a cyber system to process the information in real-time. The neural-machine interface consists of multiple sensors that reliably monitor the neural and mechanical information and a set of new algorithms that can fuse and coordinate the highly dynamic information for accurate identification of user intent. The algorithm is to be implemented on a high-performance graphic processing unit (GPU) to meet real-time requirements. This project has the potential to enable the design of neural-controlled artificial legs and may initiate a new direction for research in and the design of prosthetic leg systems. Innovations in this domain have the potential to improve the quality of life of leg amputees, including soldiers with limb amputations. The proposed approaches seek to permit cyber systems to cope with physical uncertainty and dynamics, a common challenge in cyber-physical systems, and to pave a way for applying high-performance computing in biomedical engineering. Besides providing comprehensive training to undergraduate and graduate students, the investigators plan to introduce community college students to cyber-physical systems concepts in an interactive and engaging manner.

The objective of this research is to develop a cyber-physical system composed of accelerometers and novel machine learning algorithms to analyze data in the context of a set of driving health care applications. The approach is to develop novel machine learning algorithms for temporal segmentation, classification, and detection of subtle elements of human motion. These techniques will allow quantification of human motion and improved full-time monitoring and assessment of medical conditions using a lightweight wearable system. The scientific contribution of this research is in advancing machine learning and human sensing in support of improved medical diagnoses and treatment monitoring by (i) modeling human activity and symptoms through sensor data analysis, (ii) integrating and fusing information from several accelerometers to monitor in real-time, (iii) validating the efficacy of the automated detection through assessments applying the state of the art in diagnostic evaluation, (iv) developing novel machine learning methods for temporal segmentation, classification, and discovery of multiple temporal patterns that discriminate between temporal signals, and (v) providing quality measures to characterize subtle human motion. These algorithms will advance machine learning in the area of unsupervised and semisupervised learning. The driving applications for this research are job coaching for people with cognitive disabilities, tele-rehabilitation for knee osteo-arthritis, assessing variability in balance and gait as an indicator of health of older adults, and measures for assessing Parkinson's patients. This research is highly interdisciplinary and will train graduate students for careers in developing technological innovations in health and monitoring systems.