The objective of this research is the development of methods and software that will allow robots to detect and localize objects using Active Vision and develop descriptions of their visual appearance in terms of shape primitives. The approach is bio inspired and consists of three novel components. First, the robot will actively search the space of interest using an attention mechanism consisting of filters tuned to the appearance of objects. Second, an anthropomorphic segmentation mechanism will be used. The robot will fixate at a point within the attended area and segment the surface containing the fixation point, using contours and depth information from motion and stereo. Finally, a description of the segmented object, in terms of the contours of its visible surfaces and a qualitative description of their 3D shape will be developed. The intellectual merit of the proposed approach comes from the bio-inspired design and the interaction of visual learning with advanced behavior. The availability of filters will allow the triggering of contextual models that work in a top-down fashion meeting at some point the bottom-up low-level processes. Thus, the approach defines, for the first time, the meeting point where perception happens. The broader impacts of the proposed effort stem from the general usability of the proposed components. Adding top-down attention and segmentation capabilities to robots that can navigate and manipulate, will enable many technologies, for example household robots or assistive robots for the care of the elders, or robots in manufacturing, space exploration and education.

The objective of this research is to develop algorithms and software for treatment planning in intensity modulated radiation therapy under assumption of tumor and healthy organs motion. The current approach to addressing tumor motion in radiation therapy is to treat it as a problem and not as a therapeutic opportunity. However, it is possible that during tumor and healthy organs motion the tumor is better exposed for treatment, allowing for the prescribed dose treatment of the tumor (target) while reducing the exposure of healthy organs to radiation. The approach is to treat tumor and healthy organs motion as an opportunity to improve the treatment outcome, rather than as an obstacle that needs to be overcome. Intellectual Merit: The leading intellectual merit of this proposal is to develop treatment planning and delivery algorithms for motion-optimized intensity modulated radiation therapy that exploit differential organ motion to provide a dose distribution that surpasses the static case. This work will show that the proposed motion-optimized IMRT treatment planning paradigm provides superior dose distributions when compared to current state-of-the art motion management protocols. Broader Impact: Successful completion of the project will mark a major step for clinical applications of intensity modulated radiation therapy and will help to improve the quality of life of many cancer patients. The results could be integrated within existing devices and could be used for training of students and practitioners. The visualization software for dose accumulation could be used to train medical students in radiation therapy treatment planning.

The objective of this research is to develop algorithms and software for treatment planning in intensity modulated radiation therapy under assumption of tumor and healthy organs motion. The current approach to addressing tumor motion in radiation therapy is to treat it as a problem and not as a therapeutic opportunity. However, it is possible that during tumor and healthy organs motion the tumor is better exposed for treatment, allowing for the prescribed dose treatment of the tumor (target) while reducing the exposure of healthy organs to radiation. The approach is to treat tumor and healthy organs motion as an opportunity to improve the treatment outcome, rather than as an obstacle that needs to be overcome. Intellectual Merit: The leading intellectual merit of this proposal is to develop treatment planning and delivery algorithms for motion-optimized intensity modulated radiation therapy that exploit differential organ motion to provide a dose distribution that surpasses the static case. This work will show that the proposed motion-optimized IMRT treatment planning paradigm provides superior dose distributions when compared to current state-of-the art motion management protocols. Broader Impact: Successful completion of the project will mark a major step for clinical applications of intensity modulated radiation therapy and will help to improve the quality of life of many cancer patients. The results could be integrated within existing devices and could be used for training of students and practitioners. The visualization software for dose accumulation could be used to train medical students in radiation therapy treatment planning.

The objectives of this research are to design a heterogeneous network of embedded systems so that faults can be quickly detected and isolated and to develop on-line and off-line fault diagnosis and prognosis methods. Our approach is to develop functional dependency models between the failure modes and the concomitant monitoring mechanisms, which form the basis for failure modes, effects and criticality analysis, design for testability, diagnostic inference, and the remaining useful life estimation of (hardware) components. Over the last few years, the electronic explosion in automotive vehicles and other application domains has significantly increased the complexity, heterogeneity, and interconnectedness of embedded systems. To address the cross-subsystem malfunction phenomena in such networked systems, it is essential to develop a common methodology that: (i) identifies the potential failure modes associated with software, hardware, and hardware-software interfaces; (ii) generates functional dependencies between the failure modes and tests; (iii) provides an on-line/off-line diagnosis system; (iv) computes the remaining useful life estimates of components based on the diagnosis; and (iv) validates the diagnostic and prognostic inference methods via fault injection prior to deployment in the field. The development of functional dependency models and diagnostic inference from these models to aid in online and remote diagnosis and prognosis of embedded systems is a potentially novel aspect of this effort. This project seeks to improve the competitiveness of the U.S. automotive industry by enhancing vehicle reliability, performance and safety, and by improving customer satisfaction. Other representative applications include aerospace systems, electrification of transportation, medical equipment, and communication and power networks, to name a few.

This objective of this proposal is to improve the management of the air traffic system, a cyber-physical system where the need for a tight connection between the computational algorithms and the physical system is critical to safe, reliable and efficient performance. The approach is based on an adaptive multiagent coordination algorithm with a particular emphasis on the systematic selection of the agents, their actions and the agents' reward functions. The intellectual merit lies in addressing the agent coordination problem in a physical setting by shifting the focus from "how to learn" to "what to learn." This paradigm shift allows a separation between the learning algorithms used by agents, and the reward functions used to tie those learning systems into system performance. By exploring agent reward functions that implicitly model agent interactions based on feedback from the real world, this work aims to build cyber-physical systems where an agent that learns to optimize its own reward leads to the optimization of the system objective function. The broader impact is in providing new air traffic flow management algorithms that will significantly reduce air traffic congestion. The potential impact cannot only be measured in currency ($41B loss in 2007) but in terms of improved experience by all travelers, providing a significant benefit to society. In addition, the PIs will use this project to train graduate and undergraduate students (i) by developing new courses in multiagent learning for transportation systems; and (ii) by providing summer internship opportunities at NASA Ames Research Center.

This objective of this proposal is to improve the management of the air traffic system, a cyber-physical system where the need for a tight connection between the computational algorithms and the physical system is critical to safe, reliable and efficient performance. The approach is based on an adaptive multi-agent coordination algorithm with a particular emphasis on the systematic selection of the agents, their actions and the agents' reward functions. The intellectual merit lies in addressing the agent coordination problem in a physical setting by shifting the focus from ``how to learn" to ``what to learn." This paradigm shift allows a separation between the learning algorithms used by agents, and the reward functions used to tie those learning systems into system performance. By exploring agent reward functions that implicitly model agent interactions based on feedback from the real world, this work aims to build cyber-physical systems where an agent that learns to optimize its own reward leads to the optimization of the system objective function. The broader impact is in providing new air traffic flow management algorithms that will significantly reduce air traffic congestion. The potential impact cannot only be measured in currency ($41B loss in 2007) but in terms of improved experience by all travelers, providing a significant benefit to society. In addition, the PIs will use this project to train graduate and undergraduate students (i) by developing new courses in multi-agent learning for transportation systems; and (ii) by providing summer internship opportunities at NASA Ames Research Center.