Person:
Payan, Alexia P.

Permanent Link
https://hdl.handle.net/1853/71583
Associated Organization(s)
ORCID
ArchiveSpace Name Record

Filters

2021 - 2022 2
2
2
2
2
Reset filters

Settings
Author: Harris, Caleb M. ×

Publication Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Emergency Planning for Aerial Vehicles by Approximating Risk with Aerial Imagery and Geographic Data
    (Georgia Institute of Technology, 2022-01) Harris, Caleb M. ; Kim, Seulki ; Payan, Alexia P. ; Mavris, Dimitri N.
    Urban Air Mobility and Advanced Air Mobility require the certification of novel electrified, vertical takeoff and landing, and autonomous aerial vehicles. These vehicles will operate at lower altitudes, in more dense environments, and with limited recovery abilities. Therefore, emergency landing scenarios must be considered broadly to understand the risks in some situations of flight failures. This work provides a preflight planning tool to assist these vehicles when emergency landing is required in crowded environments by fusing geographic data about the population, geometric data from lidar scans, and semantic data about land cover from aerial imagery. The Pix2Pix Conditional GAN is trained on Washington D.C. datasets to predict eight classifications at a 1m resolution. The information from this detection phase is transformed into a costmap, or riskmap, to use in planning the path to the safest landing locations. Multiple combinations of the cost layers are investigated in three test scenarios. The Rapidly Exploring Random Tree (RRT) algorithm efficiently searches for an alternative path that minimizes risk during emergency landing. The tool is demonstrated through three scenarios in the D.C. area. The objective is that the tool allows for the safe operation of UAM and AAM vehicles through crowded regions by providing confidence to the local population and federal regulators.
  • Thumbnail Image
    Item
    Use of Machine Learning to Create a Database of Wires for Helicopter Wire Strike Prevention
    (Georgia Institute of Technology, 2021-01-04) Harris, Caleb M. ; Achour, Gabriel ; Payan, Alexia P. ; Mavris, Dimitri N.
    Rotorcraft collisions with wires and power lines have been a major cause of accidents over the past decades. They are rather difficult to predict and often result in fatalities. For this reason, there is a push to provide pilots with additional information regarding wires in the surrounding environment of the helicopter. However, the precise locations of power lines and other aerial wires are not available in any centralized database. This work proposes the development of a wire database in two phases. First, power line structures are detected from aerial imagery using deep learning techniques. Second, the complete power grid network is predicted using a centralized many-to-many graph search. The two-step framework produces an approximate medium-voltage grid stored as a set of connected line segments in GPS coordinates. Experiments are conducted in Washington D.C. using openly available datasets. Results show that utility pole locations can be predicted from satellite imagery using deep learning methods and a full grid network can be generated to a level of detail depending on computational power and available data for inference in the graph search. Even with limited computational resources and a noisy dataset, over a a fourth of the grid network is directly predicted within a range of seven meters, and the majority of the network is visually inferred from nearby detections. Moving forward, the goal is to apply the proposed framework to larger regions of the U.S., with rural and urban environments, to map all wires and cables that are a threat to rotorcraft safety.