1-4 of 4 results
-
GUMP: General Urban Area Microclimate Predictions Tool
PI Kevin Adkins
CO-I Nickolas Macchiarella
CO-I National Aeronautics and Space Administration NASA
Hyperlocal weather predictions are often necessary in order to determine whether a particular sUAS route will be safe to fly. The General Urban area Microclimate Predictions tool (GUMP) seeks to provide such predictions through the use of machine learning (ML) models and computational fluid dynamics (CFD) simulations. The computed wind flow field is converted into an intuitive risk map for sUAS operators through the use of appropriate thresholds on wind velocities.
Adverse weather conditions, particularly, high winds, can have a highly adverse impact on small unmanned aircraft system (sUAS) operations. These conditions can vary significantly within a small area (particularly, in an urban environment); thus, hyperlocal weather predictions are often necessary in order to determine whether a particular sUAS route will be safe to fly. The General Urban area Microclimate Predictions tool (GUMP) seeks to provide such predictions through the use of machine learning (ML) models and computational fluid dynamics (CFD) simulations. Specifically, ML models are trained to ingest mesoscale forecasts from the National Oceanic and Atmospheric Administration (NOAA) and output refined forecasts for some specific location, typically, a weather station that serves as a source of ground truth data during training. At the same time, CFD simulations over 3D models of structures (e.g., buildings) are utilized to extend the refined forecast to other points within the area of interest surrounding the location. Because it is difficult to perform such simulations in real-time, they are executed offline under a wide range of boundary conditions, generating a broad set of resulting wind flow fields. During deployment, GUMP retrieves the wind flow field that is most consistent with the ML model’s forecast. The wind flow field can be converted into an intuitive risk map for sUAS operators through the use of appropriate thresholds on wind velocities. I addition to NASA, additional partners on this project are Intelligent Automation Inc. and AvMet.Categories: Faculty-Staff
-
UAV-based tools in forest environments
PI Scott Post
Measuring turbulent wind forces in forests to understand the forces on UAVs in flight, with a goal of being able to keep a UAV in position to mm tolerance.
Categories: Faculty-Staff
-
NSF REU Site: Swarms of Unmanned Aircraft Systems in the Age of AI/Machine Learning
PI Houbing Song
CO-I Richard Stansbury
Embry-Riddle Aeronautical University establishes a new Research Experiences for Undergraduates (REU) Site to engage participants in research in drone swarms. The emerging concept of drone swarms, which is defined as the ability of drones to autonomously make decisions based on shared information, creates new opportunities with major societal implications. However, future drone swarm applications and services pose new networking challenges. A resurgence of Artificial Intelligence and machine learning research presents a tremendous opportunity for addressing these networking challenges. There is an overwhelming need to foster a robust workforce with competencies to enable future drone swarm applications and services in the age of AI/machine learning.
The project establishes a new Research Experiences for Undergraduates (REU) Site with a focus on networking research for drone swarms in the age of AI/machine learning at Embry-Riddle Aeronautical University. The goals of the REU Site are: (1) attract undergraduate students to state-of-the-art drone swarm research, especially those from underrepresented groups, and from institutions with limited opportunities; (2) develop the research capacity of participants by guiding them to perform research on drone swarms; (3) grow the participants’ technical skills to enable a wide variety of beneficial applications of drone swarms; (4) promote the participants’ integrated AI/machine learning and drone swarm competencies; and (5) prepare participants with professional skills for careers. The focus of the REU Site is on the design, analysis and evaluation of innovative computing and networking technologies for future drone swarm applications and services. To be specific, research activities will be conducted in three focus areas, notably dynamic network management, network protocol design, and operationalizing AI/machine learning for drone swarms. Each year eight undergraduate students will participate in a ten-week summer REU program to perform networking research for drone swarms under the guidance of research mentors with rich experiences in AI/machine learning and drone swarms. This REU site is expected to foster workforce knowledge and skills about developing new computing and networking technologies for future drone swarm applications and services. This site is supported by the Department of Defense ASSURE program in partnership with the NSF REU program.
Categories: Faculty-Staff
-
Pilot’s Willingness to Operate in Unmanned Aircraft System Integrated Airspace
PI Lakshmi Vempati
PI Scott Winter
The interest in Unmanned Aircraft Systems (UAS) use for private, civil, and commercial purposes such as package delivery, inspection, surveillance, and passenger and cargo transport has gained considerable momentum. As UAS infiltrate the National Airspace System (NAS), there is a need to not only develop viable, safe, and secure solutions for the co-existence of manned and unmanned aircraft, but also determine public acceptance and pilot’s willingness to operate an aircraft in such an integrated environment. Currently there is little or no research on pilot’s perceptions on their willingness to operate an aircraft in UAS integrated airspace and airports.
The purpose of this study was to determine what effect the type of UAS integration, the type of UAS operations, and the airspace classification will have on pilot’s perspectives and willingness to operate an aircraft in UAS integrated airspace and airport environment. This study surveyed the eligible pilot population in hypothetical scenarios using convenience sampling to measure their willingness to operate an aircraft in UAS integrated airspace and airports using the Willingness to Pilot an Aircraft Scale, which has been shown to be valid and reliable by Rice, Winter, Capps, Trombley, Robbins, and Milner (2020). A mixed factorial design was used to study the interaction effects between the independent variables and the effects on the dependent variable, i.e., willingness to pilot an aircraft.
The results of the mixed analysis of variance (ANOVA) indicated a significant interaction between type of UAS integration and airspace classification. Overall willingness decreased with airspace and differences in willingness to pilot an aircraft were based on segregated and integrated operations. The average pilot’s willingness to pilot an aircraft score differed from the highest score being for Class B, decreasing with decreasing airspace classes, with the lowest being for Class G.
Analysis of pilot perspectives collected through open ended questions using text-mining techniques showed agreement with mixed ANOVA analysis that the primary factor in the pilot’s perception was airspace. Key concerns voiced by the pilots were situation awareness, risk and safety of operations, aircraft certification and airworthiness, and operator experience and regulatory conformance. The most positive sentiment was observed among pilots presented with the hypothetical scenario of fully autonomous UAS operations in a segregated environment. Findings from the study could aid regulators in developing better policies, procedures, integration solutions, improved training, and knowledge sharing.
Categories: Graduate
1-4 of 4 results