| NSF Org: |
TI Translational Impacts |
| Recipient: |
|
| Initial Amendment Date: | September 21, 2015 |
| Latest Amendment Date: | June 9, 2016 |
| Award Number: | 1559718 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Barbara H. Kenny
TI Translational Impacts TIP Directorate for Technology, Innovation, and Partnerships |
| Start Date: | June 1, 2015 |
| End Date: | November 30, 2016 (Estimated) |
| Total Intended Award Amount: | $125,506.00 |
| Total Awarded Amount to Date: | $146,454.00 |
| Funds Obligated to Date: |
FY 2015 = $15,413.00 FY 2016 = $5,536.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
2600 CLIFTON AVE CINCINNATI OH US 45220-2872 (513)556-4358 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
OH US 45221-0222 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Accelerating Innovation Rsrch |
| Primary Program Source: |
01001617DB NSF RESEARCH & RELATED ACTIVIT 01001516DB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.084 |
ABSTRACT
This PFI: AIR Technology Translation project focuses on translating Unmanned Aerial Vehicle (UAV) technology to fill the need of generating real-time, accurate situational awareness during emergency situations, such as wildfires and structural fires. The project will result in the development of a prototype system consisting of a UAV and a ground station with associated software that can provide the firefighting "Incident Management Teams" with advanced situational awareness capabilities during wildfire and structural fire scenarios. This UAV based system has the following unique features: i) ease-of-use by firefighting professionals in managing UAV operations; ii) quick deployment; and iii) real-time acquisition and processing of information gathered by UAV in order to provide not only a current situational picture but also predictive ability in case of wildfires. These features provide advantages including reduced cost of operation and improved safety of lives and properties as compared with current methodologies such as manned aircraft based surveillance, satellite imageries, and manual lookout practices.
This project addresses a number of technology gaps as it translates from research discovery toward commercial application. For example, the conversion of data gathered from UAVs in the form of telemetry and streaming video into an intuitive form easily understandable by firefighters requires innovations in real-time video processing, spatio-temporal estimation, systematic combination of information from multiple sources, and information presentation and visualization. Similarly, intended use by firefighting professionals, who are not trained pilots, and other practical constraints require the UAV operations to be autonomous and algorithms to be computationally efficient.
The project engages partners from the University of Toledo Technology Transfer Office, Kayos Enterprise, Inc., West Virginia Division of Forestry, and the Cincinnati Fire Department to guide the commercialization process, augment the research capability, provide a testing environment, and offer an understanding of users' needs and perspectives in this technology translation effort from research discovery toward commercial reality.
The proposed UAV based technology is important because it puts tools in hands of wildfire and structural fire incident commanders so they can obtain improved situational awareness for making timely and informed decisions. This is expected to result in substantial cost savings, improved levels of safety, lower loss of life and property, and augmented preservation of the environment. With the imminent inclusion of UAVs in the national airspace, the technologies developed in this research have wide potential in a number of other civilian applications such as law enforcement, border patrol, and perimeter surveillance. This project provides training to future engineers, incident commanders, UAV operators and entrepreneurs who would lead this field of technology in years to come. In addition, the project will contribute to the U.S. competitiveness in the area of civilian UAV applications with potential economic impact within five to ten years.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
The project focused on developing a prototype of the Unmanned Aerial Vehicle (UAV) based incident command decision support system that would enable generation of accurate situational awareness during structural fires/wild-land fires. The prototype, consisting of ground station and a multi-rotor UAV platform with onboard sensing and communication facilities, would allow real-time UAV control, data processing, and visualization. From the fundamental engineering perspective, the project focused on: i) Development of intelligent data processing algorithms for situational awareness; and ii) Development of effective control and navigation algorithms. The major activities were: i) Fire and human detection for air support operations; ii) Extended Kalman Filter based quadrotor state estimation and video synchronization; iii) Geo-localization and tracking of targets for aerial operations; iv) System identification and controller optimization of a quadrotor UAV; v) Emergency response User Interface for multi-rotor UAVs; vi) Tilt rotor quadcopter fault-tolerant design; vii) Trajectory tracking and path planning of multiple UAVs in the National Airspace; and viii) Genetic Fuzzy flight controller for dynamic target landing of multi-rotor UAVs on moving platforms.
Intellectual Merit:
The intellectual merits associated with the major activities were: i) The research yielded fuzzy logic and Convolutional Neural Network algorithms for identifying fire pixels, and detecting and tracking humans from real-time video feed; ii) An Extended Kalman Filter (EKF) based estimation technique was developed that addressed the issues of time delays and missing data. The method exploited the dynamic model of the UAV to estimate the quadrotor states and synchronize the measurements obtained from different sensors such as Global Position System (GPS), Inertial Navigation System (INS), and cameras; iii) The project developed Extended Kalman Filter based approach to geo-localize and track a ground target (such as fire hot-spot or human) by fusing noisy information from camera, GPS and INS; iv) A frequency-domain system identification method for extraction of the bare-airframe dynamic model of a quadrotor UAV in hovering condition was developed that was used for rapid design of optimized control system for enhanced handling qualities and augmented safety; v) A Graphical User Interface (GUI) that addresses the needs of emergency responders was designed in order to facilitate easy management of the UAV operations and intuitive representation of the situational awareness; vi) A novel quadcopter was designed and fabricated that used tilting mechanism to improve maneuverability and fault tolerance. Detailed mathematical model was derived and the flight controller was developed; vii) Path planning algorithms were developed to obtain flight plans of multiple UAVs sharing airspace and engaged in respective missions based on both traditional methods such as Mixed Integer Linear Programming as well as meta-heuristic techniques such as Grey Wolf Optimization; and viii) A robust non-linear bio-inspired Genetic Fuzzy based control scheme was developed that allowed a UAV to land on a moving platform using onboard imaging.
Broader Impacts:
The UAV prototype developed as a part of this project will create a paradigm shift in generation of real-time situational awareness for not only firefighting but also many kinds of disaster response situations. Apart from firefighting, which was the focus area of this project, the results obtained from this research are being applied to package delivery, infrastructure assessment, traffic operations, and Unmanned Systems Traffic Management (UTM). The research involved training of seven graduate and eight undergraduate students. The project also organized a seminar entitled “UAVs for Emergency Responders” on Aug. 10, 2016 in collaboration with University of Cincinnati’s Fire Science Program that attracted 165 attendees from all over the country. The results have been disseminated to the communities of interest via presentations at conferences, journal paper publications, invention disclosures, and online media outlets.
Last Modified: 03/21/2017
Modified by: Manish Kumar
Please report errors in award information by writing to: awardsearch@nsf.gov.
