Comprehensive Risk-based Planning for Small Unmanned Aircraft System Rooftop Landing

Castagno, Jeremy D.; Ochoa, Cosme A.; Atkins, Ella M.

doi:10.1109/icuas.2018.8453483

Cited by 15 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These treatment options could be performed manually after a risk assessment is performed or could be accomplished by high-level automated planning algorithms. Intricate path-planning and decision-making methods could be used to plan optimal flight paths that take into account the acceptable risk of a given sUAS as has been previously demonstrated (Guglieri et al 2015;Castagno et al 2018;Primatesta et al 2019Primatesta et al , 2020. The details of how to adjust the proposed flight plan are highly dependent on the specific operation and therefore are not included in sWRM.…”

Section: E Treat Riskmentioning

confidence: 99%

Weather Hazard Risk Quantification for sUAS Safety Risk Management

Roseman

Argrow

2020

Journal of Atmospheric and Oceanic Technology

View full text Add to dashboard Cite

As the number of applications for small unmanned (i.e., remotely operated) aircraft systems (sUAS) continues to grow, comprehensive safety risk assessment studies are required to ensure their safe integration into the National Airspace System. One source of hazards for sUAS that has not been extensively addressed is adverse weather. A framework is presented for analyzing weather forecast data to provide sUAS operators with risk assessment information that they can use for making risk-aware decisions. The sUAS Weather Risk Model (sWRM) framework quantifies weather hazard risk for sUAS operations in rural to urban environments using weather forecast, population density, structure density, and sUAS data. sWRM is developed by following the safety risk management guidelines from the U.S. Federal Aviation Administration. Development of sWRM highlights a number of aerospace and meteorological research areas that must be addressed prior to weather risk models for sUAS becoming operational. Primary among these research areas is developing widely available finescale (<1 km) weather forecasts and conducting extensive sUAS flight-report studies to accurately estimate parameters of Bayesian belief network conditional probability tables used in the proposed framework. As a proof of concept, sWRM was applied over Boulder, Colorado, using the High-Resolution Rapid Refresh weather product. This initial demonstration of sWRM highlights the potential effectiveness of a detailed risk assessment model that takes into account high-resolution weather and environmental data.

show abstract

Section: E Treat Riskmentioning

confidence: 99%

Weather Hazard Risk Quantification for sUAS Safety Risk Management

Roseman

Argrow

2020

Journal of Atmospheric and Oceanic Technology

View full text Add to dashboard Cite

show abstract

“…Dashed lines indicate results where holes are included in the ground truth polygon. Each test was run 10 times with input point set sizes ranging from (2,4,8,16,32,64) thousand points with mean timing and error plotted. Confidence intervals are provided for execution timing, however they are almost imperceptible because the variance is low at this scale.…”

Section: A State Shapesmentioning

confidence: 99%

“…Unmanned Aerial Vehicles (UAVs) also need simplified representations of operating regions for navigation and landing [6], [7], particularly in complex urban regions. Surfaces such as flat rooftops can offer safe nearby landing zones once planarity/shape is determined [8], [9].…”

Section: Introductionmentioning

confidence: 99%

Polylidar -- Polygons from Triangular Meshes

Castagno,

Atkins

2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents Polylidar, an efficient algorithm to extract non-convex polygons from 2D point sets. Polylidar is able to extract multiple disjoint polygons and capture interior holes. The algorithm begins by triangulating the point set and filtering triangles by user configurable parameters such as triangle edge length. Next, connected triangles are extracted into triangular meshes representing the shape of the point set.The key to Polylidar's speed, and the main contribution of this paper, is in efficiently transforming each triangular mesh into a concave polygon. This paper describes Polylidar and provides benchmarks to comparatively evaluate its speed and accuracy. Results show good accuracy and ∼ 4 times speedup compared to other concave polygon extraction methods.

show abstract

“…Systematic characterization of building roof architecture and slope offers a new dimension to traditional terrain data. These data could be used to rapidly identify building change or damage from the air, to improve in-flight localization capabilities in GPS-denied areas, and to inform small Unmanned Aircraft Systems (UAS) of alternative ditching sites, a problem previously investigated by the authors [ 1 , 2 ]. Databases such as OpenStreetMap (OSM) [ 3 ] provide limited roof information, but such data have been manually entered to-date thus is sparse.…”

Section: Introductionmentioning

confidence: 99%

“…We show that combining datasets from both small and large cities leads to a more generalized model and improves performance. Figure 1 provides an overview of the data processing pipeline and illustrates a UAS localization and contingency landing use case [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Roof Shape Classification from LiDAR and Satellite Image Data Fusion Using Supervised Learning

Castagno

Atkins

2018

Sensors

Self Cite

View full text Add to dashboard Cite

Geographic information systems (GIS) provide accurate maps of terrain, roads, waterways, and building footprints and heights. Aircraft, particularly small unmanned aircraft systems (UAS), can exploit this and additional information such as building roof structure to improve navigation accuracy and safely perform contingency landings particularly in urban regions. However, building roof structure is not fully provided in maps. This paper proposes a method to automatically label building roof shape from publicly available GIS data. Satellite imagery and airborne LiDAR data are processed and manually labeled to create a diverse annotated roof image dataset for small to large urban cities. Multiple convolutional neural network (CNN) architectures are trained and tested, with the best performing networks providing a condensed feature set for support vector machine and decision tree classifiers. Satellite image and LiDAR data fusion is shown to provide greater classification accuracy than using either data type alone. Model confidence thresholds are adjusted leading to significant increases in models precision. Networks trained from roof data in Witten, Germany and Manhattan (New York City) are evaluated on independent data from these cities and Ann Arbor, Michigan.

show abstract

Comprehensive Risk-based Planning for Small Unmanned Aircraft System Rooftop Landing

Cited by 15 publications

References 14 publications

Weather Hazard Risk Quantification for sUAS Safety Risk Management

Weather Hazard Risk Quantification for sUAS Safety Risk Management

Polylidar -- Polygons from Triangular Meshes

Roof Shape Classification from LiDAR and Satellite Image Data Fusion Using Supervised Learning

Contact Info

Product

Resources

About