University of Alabama in Huntsville (UAH) researchers have received three federal grants totaling nearly $650,000 from the National Science Foundation (NSF), Naval Surface Warfare Center, and Department of Energy to support diverse research involving each researcher. supported the project. Specific areas of expertise, learning-based control and its application in machine lifecycle management.
Dr. Abhimanyu Sahoo, assistant professor in the Department of Electrical and Computer Engineering at UAH, part of the University of Alabama System, will support three years of research for each funded project. This project includes an attempt to advance personal protective equipment (PPE) through smart technology. Powers networked collaborative control tasks in uncertain or dangerous environments such as ocean exploration and disaster management. and develop AI-powered autonomy for robotic inspection platforms to improve the sustainability of energy infrastructure.
Prioritize safety in hazardous environments
The project to fund research into smart PPE is funded by NSF for $178,937 and is scheduled to begin in October 2023 and run through September 2026. The project includes the establishment of a collaborative research experience site (REU) to provide interdisciplinary research to students. Experience in developing smart personal protective equipment (SmaPP). SmaPP advances a specific type of personal protective clothing that incorporates intelligent technology into his PPE that captures and monitors hazardous environmental data and the wearer’s location to ensure safety and response in high-risk work environments. Improve efficiency.
“The REU site provides undergraduate students with experience in addressing four fundamental challenges in the development of smart personal protective equipment,” Dr. Sahoo explains. “They are the development of new smart materials. Incident heat flux measurements on SmaPP surfaces. Intelligent wireless sensing technology for human vital signs, radiation monitoring, and human recognition of SmaPP. At the REU site, for 10 weeks each summer Over the course of the program, nine undergraduate students will participate in research activities related to the development of SmaPP.”
Dr. Abhimanyu Sahu, UAH Electrical and Computer Engineering.
The use of SmaPP requires the use of products called auxetic materials. An auxetic cell structure consists of a large number of unit cells arranged so that the entire structure expands when stretched and contracts when compressed. REU features a number of sample projects to explore SmaPP components. This includes strength and impact testing, and analysis of auxetic materials. Design optimization and prototype development of auxetic structures. Incident heat flux measurement on SmaPP surface. We are developing wireless sensors to monitor human vital signs and monitor radiation exposure and protective mask usage in campus environments.
“This integrated project provides undergraduate students with exposure to cutting-edge technology,” said Dr. Sahoo. “This will prepare the next generation of workforce for a future dominated by these intelligent systems. Research on smart PPE and adaptive clothing is rapidly expanding. Advances in materials science There is tremendous potential to create the next generation of PPE by leveraging , flexible and autonomous electronics, the Internet of Things (IoT), and artificial intelligence (AI). We promise to significantly improve the safety and efficiency of first responders, military personnel, and others operating in the environment.”
Supporting collaboration between ships, aircraft, and UAVs
The Naval Surface Warfare Center will be the funding agency for a project investigating intelligent control of networked autonomous heterogeneous agents (NAHA), which is essential for working in uncertain environments. This initiative will run from June 2023 to May 2026, and total grant funding to UAH will be $229,837.
“Networked, autonomous, heterogeneous agents performing collaborative tasks are ubiquitous in a variety of applications such as ocean exploration and disaster management,” Dr. Sahoo says. “To complete these tasks in an uncertain environment, NAHA requires large amounts of communication bandwidth over wireless channels and computing resources for learning and cooperative control. The advanced communications (data sharing) of NAHA threatens privacy and endangers the safety of NAHA as it executes its coordinated mission. Additionally, once a cyber-attack or failure is detected, it can be detected before it spreads to other agents. It is difficult to quickly isolate a compromised agent and restore even degraded behavior.”
Scientists report that tasks spanning large terrain, such as reconnaissance and exploration, will require the use of collaborative approaches with multiple agents such as robots, unmanned aerial vehicles (UAVs), or unmanned ground vehicles (UGVs). . Because the operating environment is unpredictable, agents have the ability to adapt and learn to navigate and perform efficiently. Critical to its operation is communication between agents, facilitating collaborative and decentralized control.
“Traditionally, much of the research in this area has centered on consensus-based control, which ensures that these agents adhere to desired positions and velocities while absorbing environmental knowledge,” the researchers said. says. “However, the effectiveness of such systems depends on uninterrupted communications. Failure or delay in communications can jeopardize mission success. This basic research has a wide range of applications. However, it is particularly relevant in naval situations where coordination between ships, aircraft, and UAVs is essential to accomplishing the mission.
“If the proposed research is successful, it will lead to innovative solutions. Going forward, we foresee a future in which autonomous, heterogeneous agents work together seamlessly under communication constraints. Agents are equipped with advanced learning capabilities that allow them to efficiently perform individual tasks even in the face of challenges such as unexpected communication breakdowns, agent malfunctions, and unpredictable environments. Masu.”
Harnessing the power of AI for robotic inspection vehicles
Dr. Sahoo’s third project was awarded $240,920 in federal funding from the Department of Energy to improve the autonomy of an AI-enabled robotic inspection platform to support the sustainability of the nation’s energy infrastructure. I did. The initiative has already begun and is scheduled to run from February 2023 to January 2026.
Robotic Visual Inspection (RVI) technology is being employed to inspect pipes, tanks, and other hard-to-access components critical to the energy sector, hydrogen production, transportation, and combustion processes, as well as carbon capture, utilization, and storage. I am.
“RVI ensures the integrity of these critical energy infrastructures, limits fugitive emissions, and ensures efficient operation,” the researchers said. “These technologies are crucial for the safety of human life, the reduction of emissions in the current energy value chain and enable a low-carbon energy transition for the sustainability of the energy sector. The state-of-the-art RVI technology employed still requires human intervention and expertise for operation, data collection, and analysis, which threatens human safety, requires long inspection times, and is prone to human error. There is a danger.”
The objective of this research is to develop an integrated AI-driven RVI platform with autonomous dynamic path planning and safe navigation capabilities for closed-loop data collection and real-time defect identification. This effort integrates deep learning-based defect identification models to perform dynamic and safe path and motion planning in real-time using multimodal data.
“Autonomous defect detection, navigation, data collection and processing algorithms increase the level of autonomy of the RVI platform while contributing to sustainability in the energy sector,” says Dr. Sahoo. “This technology represents a quantum leap forward in the field of automated component inspection and analysis enabled by robotics. We foresee inspection robots evolving beyond mere semi-autonomous operation in the near future. We imagine that these robots will have advanced learning capabilities that will allow them to operate fully autonomously. They will not only be adept at performing tasks independently, but also capable of handling unfamiliar It also has the agility to adapt and improve its capabilities based on real-time feedback from the environment. This continuous learning and adaptation will revolutionize the inspection of energy infrastructure in a low-carbon way, enabling even the most unpredictable This will ensure increased efficiency and accuracy even in difficult situations.”
