Abstract
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.
Performance Period: 09/01/2009 - 08/31/2012
Institution: University of Pittsburgh
Sponsor: National Science Foundation
Award Number: 0931595
Abstract
The objective of this research is to develop methods for the operation and design of cyber physical systems in general, and energy efficient buildings in particular. The approach is to use an integrated framework: create models of complex systems from data; then design the associated sensing-communication-computation-control system; and finally create distributed estimation and control algorithms, along with execution platforms to implement these algorithms. A special emphasis is placed on adaptation. In particular, buildings and their environments change with time, as does the way in which buildings are used. The system must be designed to detect and respond to such changes.
The proposed research brings together ideas from control theory, dynamical systems, stochastic processes, and embedded systems to address design and operation of complex cyber physical systems that were previously thought to be intractable. These approaches provide qualitative understanding of system behavior, algorithms for control, and their implementation in a networked execution platform. Insights gained by the application of model reduction and adaptation techniques will lead to significant developments in the underlying theory of modeling and control of complex systems.
The research is expected to directly impact US industry through the development of integrated software-hardware solutions for smart buildings. Collaborations with United Technologies Research Center are planned to enhance this impact. The techniques developed are expected to apply to other complex cyber-physical systems with uncertain dynamics, such as the electric power grid. The project will enhance engineering education through the introduction of cross-disciplinary courses.
Performance Period: 03/01/2010 - 02/28/2015
Institution: University of Illinois at Urbana-Champaign
Sponsor: National Science Foundation
Award Number: 0931416
Abstract
This project is developing techniques for secured real-time services for cyber-physical systems. In particular, the research is incorporating real-time traffic modeling techniques into the security service, consequently enhancing both system security and real-time capabilities in an adverse environment. While this proposed methodology has not yet been fully tested, it is potentially transformative. To defend against traffic analysis attacks, the research is developing algorithms that can effectively mask the actual operational modes of cyber-physical applications without compromising the guaranteed quality of service. This is achieved by using the traffic modeling theory, developed by the PIs, to precisely manage the network traffic at the right time and the right place. This traffic modeling theory can also help in develop efficient attack detection and suppression methods that can identify and restrain an attack in real-time. The proposed methods are expected to be more effective, efficient, and scalable than traditional methods.
Performance Period: 09/15/2010 - 08/31/2013
Institution: Temple University
Sponsor: National Science Foundation
Award Number: 1059127
Abstract
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.
Performance Period: 09/01/2009 - 08/31/2013
Institution: Washington University
Sponsor: National Science Foundation
Award Number: 0931820
Project URL
Project URL
Abstract
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.
Performance Period: 09/01/2009 - 08/31/2013
Institution: Carnegie Mellon University
Sponsor: National Science Foundation
Award Number: 0931999
Abstract
The objective of this research is to develop new models of computation for multi-robot systems. Algorithm execution proceeds in a cycle of communication, computation, and motion. Computation is inextricably linked to the physical configuration of the system. Current models cannot describe multi-robot systems at a level of abstraction that is both manageable and accurate. This project will combine ideas from distributed algorithms, computational geometry, and control theory to design new models for multi-robot systems that incorporate physical properties of the systems. The approach is to focus on the high-level problem of exploring an unknown environment while performing designated tasks, and the sub-problem of maintaining network connectivity. Key issues to be studied will include algorithmic techniques for handling ongoing discrete failures, and ways of understanding system capabilities as related to failure rates, geometric assumptions and physical parameters such as robot mobility and communication bandwidth. New metrics will be developed for error rates and robot mobility.
Intellectual merit arises from the combination of techniques from distributed algorithms, computational geometry, and control theory to develop and analyze algorithms for multi-robot systems. The project will develop a new class of algorithms and techniques for their rigorous analysis, not only under ideal conditions, but under a variety of error assumptions. The project will test theoretical ideas empirically, on three different multi-robot systems.
Broader impacts will include new algorithms for robot coordination, and rigorous understanding of the capabilities of different hardware platforms. Robots are an excellent outreach tool, and provide concrete examples of theory in action.
James McLurkin
James McLurkin is an Assistant Professor at Rice University in the Department of Computer Science, and director of the Multi-Robot Systems Lab. Research interests include using distributed computational geometry for multi-robot configuration control, distributed perception, and complexity metrics that quantify the relationships between algorithm execution time, inter-robot communication bandwidth, and robot speed. Previous positions include lead research scientist at iRobot corporation, where McLurkin was the manager of the DARPA-funded Swarm project. Results included the design and construction of 112 robots and distributed configuration control algorithms, including robust software to search indoor environments. He holds a S.B. in Electrical Engineering with a Minor in Mechanical Engineering from M.I.T., a M.S. in Electrical Engineering from University of California, Berkeley, and a S.M. and Ph.D. in Computer Science from M.I.T.
Performance Period: 09/15/2010 - 08/31/2014
Institution: William Marsh Rice University
Sponsor: National Science Foundation
Award Number: 1035716
Abstract
The objective of this research is to develop new models of computation for multi-robot systems. Algorithm execution proceeds in a cycle of communication, computation, and motion. Computation is inextricably linked to the physical configuration of the system. Current models cannot describe multi-robot systems at a level of abstraction that is both manageable and accurate. This project will combine ideas from distributed algorithms, computational geometry, and control theory to design new models for multi-robot systems that incorporate physical properties of the systems. The approach is to focus on the high-level problem of exploring an unknown environment while performing designated tasks, and the sub-problem of maintaining network connectivity. Key issues to be studied will include algorithmic techniques for handling ongoing discrete failures, and ways of understanding system capabilities as related to failure rates, geometric assumptions and physical parameters such as robot mobility and communication bandwidth. New metrics will be developed for error rates and robot mobility.
Intellectual merit arises from the combination of techniques from distributed algorithms, computational geometry, and control theory to develop and analyze algorithms for multi-robot systems. The project will develop a new class of algorithms and techniques for their rigorous analysis, not only under ideal conditions, but under a variety of error assumptions. The project will test theoretical ideas empirically, on three different multi-robot systems.
Broader impacts will include new algorithms for robot coordination, and rigorous understanding of the capabilities of different hardware platforms. Robots are an excellent outreach tool, and provide concrete examples of theory in action.
Nancy Lynch
Biography
Nancy Lynch is the NEC Professor of Software Science and Engineering in the Department of Electrical Engineering and Computer Science at MIT. She heads the Theory of Distributed Systems research group in MIT's Computer Science and Artificial Intelligence Laboratory. She is also currently a Fellow at the Radcliffe Institute for Advanced Study.
Lynch received her B.S. degree in mathematics from Brooklyn College in 1968, and her PhD in mathematics from MIT in 1972. She has written numerous research articles about distributed algorithms and impossibility results, and about formal modeling and verification of distributed systems. Her best-known research contribution is the ``FLP'' impossibility result for distributed consensus in the presence of process failures, developed with Fischer
and Paterson in 1982. Lynch's other well-known research contributions include the I/O automata mathematical system modeling frameworks, with Tuttle, Vaandrager, Segala, and Kaynar. Her recent work is focused on
algorithms for mobile ad hoc networks.
Lynch has written books on ``Atomic Transactions'' (with Merritt, Weihl, and Fekete), on ``Distributed Algorithms'', and on ``The Theory of Timed I/O Automata'' (with Kaynar, Segala, and Vaandrager). She is an ACM Fellow, and a member of both the National Academy of Engineering and the American Academy of Arts and Sciences. She was co-winner of the first (2006) van Wijngaarden prize, and was awarded the 2007 Knuth Prize, the 2010 IEEE Emanuel Piore award, and
the 2012 Athena award. Lynch has supervised over 25 PhD students and over 50 Masters
students, as well as numerous postdoctoral research associates.
Performance Period: 09/15/2010 - 08/31/2013
Institution: Massachusetts Institute of Technology
Sponsor: National Science Foundation
Award Number: 1035199
Project URL
Project URL
Abstract
The objective of this inter-disciplinary research is to develop new technologies to transform the streets of a city into a hybrid transportation/communication system, called the Intelligent Road (iRoad), where autonomous wireless devices are co-located with traffic signals to form a wireless network that fuses real-time transportation data from all over the city to make a wide range of new applications possible. The approach is to build new capacities of quantitative bandwidth distribution, rate/delay assurance, and location-dependent security on a pervasive wireless platform through distributed queue management, adaptive rate control, and multi-layered trust. These new capacities lead to transformative changes in the way the transportation monitoring and control functions are designed and operated.
Many technical challenges faced by the iRoad system are open problems. New theories/protocols developed in this project will support sophisticated bandwidth management, quality of service, multi-layered trust, and information fusion in a demanding environment where critical transportation functions are implemented. Solving these fundamental problems advances the state of the art in both wireless technologies and transportation engineering. The research outcome is likely to be broadly applicable in other wireless systems.
The economic and societal impact of the iRoad system is tremendous at a time when the country is modernizing its ailing transportation infrastructure. It provides a pervasive communication infrastructure and engineering framework to build new applications such as real-time traffic map, online best-route query, intelligent fuel-efficient vehicles, etc. The research results will be disseminated through course materials, academic publication, industry connection, and presentations at the local transportation department.
Performance Period: 09/01/2009 - 08/31/2013
Institution: University of Florida
Sponsor: National Science Foundation
Award Number: 0931969
Project URL
Project URL
Abstract
The objective of this research is to develop truly intelligent, automated driving through a new paradigm that tightly integrates probabilistic perception and deterministic planning in a formal, verifiable framework. The interdisciplinary approach utilizes three interlinked tasks. Representations develops new techniques for constructing and maintaining representations of a dynamic environment to facilitate higher-level planning. Anticipation and Motion Planning develops methods to anticipate changes in the environment and use them as part of the planning process. Verifiable Task Planning develops theory and techniques for providing probabilistic guarantees for high-level behaviors. Ingrained in the approach is the synergy between theory and experiment using an in house, fully equipped vehicle.
The recent Urban Challenge showed the current brittleness of autonomous driving, where small perception mistakes would propagate into planners, causing near misses and small accidents; Fundamentally, there is a mismatch between probabilistic perception and deterministic planning, leading to "reactive" rather than "intelligent" behaviors. The proposed research directly addresses this by developing a single, unified theory of perception and planning for intelligent cyber-physical systems.
Near term, this research could be used to develop advanced safety systems in cars. The elderly and physically impaired would benefit from inexpensive, advanced automation in cars. Far term, the advanced intelligence could lead to automated vehicles for applications such as cooperative search and rescue. The research program will educate students through interdisciplinary courses in computer science and mechanical engineering, and experiential learning projects. Results will be disseminated to the community including under-represented colleges and universities.
Performance Period: 09/01/2009 - 08/31/2013
Institution: Cornell University
Sponsor: National Science Foundation
Award Number: 0931686
Project URL
Abstract
The objective of this research is to investigate how to replace human decision-making with computational intelligence at a scale not possible before and in applications such as manufacturing, transportation, power-systems and bio-sensors. The approach is to build upon recent contributions in algorithmic motion planning, sensor networks and other fields so as to identify general solutions for planning and coordination in networks of cyber-physical systems.
The intellectual merit of the project lies in defining a planning framework, which integrates simulation to utilize its predictive capabilities, and focuses on safety issues in real-time planning problems. The framework is extended to asynchronous coordination by utilizing distributed constraint optimization protocols and dealing with inconsistent state estimates among networked agents. Thus, the project addresses the frequent lack of well-behaved mathematical models for complex systems, the challenges of dynamic and partially-observable environments, and the difficulties in synchronizing and maintaining a unified, global world state estimate for multiple devices over a large-scale network.
The broader impact involves the development and dissemination of new algorithms and open-source software. Research outcomes will be integrated to teaching efforts and undergraduate students will be involved in research. Underrepresented groups will be encouraged to participate, along with students from the Davidson Academy of Nevada, a free public high school for gifted students. At a societal level, this project will contribute towards achieving flexible manufacturing floors, automating the transportation infrastructure, autonomously delivering drugs to patients and mitigating cascading failures of the power network. Collaboration with domain experts will assist in realizing this impact.
Performance Period: 09/01/2009 - 08/31/2013
Institution: University of Nevada
Sponsor: National Science Foundation
Award Number: 0932423
Project URL