Equipment operation represents one of the most dangerous tasks on a construction sites and accidents related to such operation often result in death and property damage on the construction site and the surrounding area. Such accidents can also cause considerable delays and disruption, and negatively impact the efficiency of operations. This award will conduct research to improve the safety and efficiency of cranes by integrating advances in robotics, computer vision, and construction management. It will create tools for quick and easy planning of crane operations and incorporate them into a safe and efficient system that can monitor a crane's environment and provide control feedback to the crane and the operator. Resulting gains in safety and efficiency will reduce fatal and non-fatal crane accidents. Partnerships with industry will also ensure that these advances have a positive impact on construction practice, and can be extended broadly to smart infrastructure, intelligent manufacturing, surveillance, traffic monitoring, and other application areas. The research will involve undergraduates and includes outreach to K-12 students. The work is driven by the hypothesis that the monitoring and control of cranes can be performed autonomously using robotics and computer vision algorithms, and that detailed and continuous monitoring and control feedback can lead to improved planning and simulation of equipment operations. It will particularly focus on developing methods for (a) planning construction operations while accounting for safety hazards through simulation; (b) estimating and providing analytics on the state of the equipment; (c) monitoring equipment surrounding the crane operating environment, including detection of safety hazards, and proximity analysis to dynamic resources including materials, equipment, and workers; (d) controlling crane stability in real-time; and (e) providing feedback to the user and equipment operators in a "transparent cockpit" using visual and haptic cues. It will address the underlying research challenges by improving the efficiency and reliability of planning through failure effects analysis and creating methods for contact state estimation and equilibrium analysis; improving monitoring through model-driven and real-time 3D reconstruction techniques, context-driven object recognition, and forecasting motion trajectories of objects; enhancing reliability of control through dynamic crane models, measures of instability, and algorithms for finding optimal controls; and, finally, improving efficiency of feedback loops through methods for providing visual and haptic cues.

This research investigates a cyber-physical framework for scalable, long-term monitoring and maintenance of civil infrastructures. With growth of the world economy and its population, there has been an ever increasing dependency on larger and more complex networks of civil infrastructure as evident in the billions of dollars spent by the federal, state and local governments to either upgrade or repair transportation systems or utilities. Despite these large expenditures, the nation continues to suffer staggering consequences from infrastructural decay. Therefore, paramount to the concept of a smart city of the future is the concept of smart civil infrastructure that can self-monitor itself to predict any impending failures and in the cases of extreme events (e.g. earthquakes) identify portions that would require immediate repair, and prioritize areas for emergency response. A goal of this research project is to make significant progress towards this grand vision by investigating a framework of infrastructural Internet-of-Things (i-IoT) using a network of self-powered, embedded health monitoring sensors. The collaborative and interdisciplinary nature of this research would provide opportunities for unique outreach programs involving undergraduate and graduate students in technical areas, e.g., sensors, IoTs and structural health monitoring. The project would also provide avenues for disseminating the results of this research to stakeholders in the state governments and for translating the results of the research into field deployable prototypes. This research addresses different elements of the proposed i-IoT framework by bringing together expertise from three universities in the area of self-powered sensors, energy scavenging processors, structural health monitoring and earthquake engineering. At the fundamental level, the project involves investigating self-powered sensors that will require zero maintenance and can continuously operate over the useful lifespan of the structure without experiencing any downtime. The challenge in this regard is that sensors need to occupy a small enough volume such that an array of these devices could be easily embedded and can provide accurate spatial resolution in structural imaging. This research is also investigates techniques that would enable real time wireless collection of data from an array of self-powered sensors embedded inside a structure, without taking the structure out-of-service. The methods to be explored involve combining the physics of energy scavenging, transduction, rectification and logic computation to improve the system's energy-efficiency and reduce the system latency. At the algorithmic level the project explores novel structural failure prediction and structural forensic algorithms based on historical data collected from self-powered sensors embedded at different spatial locations. This includes kernel algorithms that can exploit the data to quickly identify the most vulnerable part of a structure after a man-made or a natural crisis (for example an earthquake). Finally, the technology translation plan for this research is to validate the proposed i-IoT framework in real-world deployment, which includes buildings, multi-span bridges and highways.

Scaling the Internet of Things (IoT) to billions and possibly trillions of "things" requires transformative advances in the science, technology, and engineering of cyber-physical systems (CPS), with none more pressing or challenging than the power problem. Consider that if every device in a 1 trillion IoT network had a battery that lasted for a full five years, over 500 million batteries would need to be changed every day. Clearly, a battery-powered IoT is not feasible at this scale due to both human resource logistics and environmental concerns. There is a need for a battery-less approach that dependably meets functionality requirements using energy harvested from the physical world. This project brings together experts in materials, devices, circuits, and systems to pursue a holistic approach to self-powered wireless devices deployed in real-world environments and IoT systems and applications. In addition, educational and outreach activities will help develop the workforce for this relatively new field with the holistic, materials-to-systems perspective that will be necessary to lead innovation in this space.A critical challenge that this project addresses is that both optimal device operation and energy harvester efficiency are heavily dependent on physical world dynamics, and thus, self-powered devices that are statically configured or that just respond to instantaneous conditions are unlikely to provide the dependability required for many IoT systems and applications. To address this fundamental and critically enabling challenge, data collections will be performed to study the physical world dynamics that impact device operation and harvester efficiency, such as ambient conditions, electromagnetic interference, and human behavior. This scientific study will lead to the development of dynamic models that will, in turn, be used to develop algorithms to dynamically configure devices and harvesters based not only on past and current conditions but also on predictions of future conditions. These algorithms will then be used to dynamically configure technological innovations in ultra-low power device operation and ultra-high efficiency energy harvesting to engineer and operate dependable self-powered things for the IoT.