Localized Population Density Mapping for Safer UAV Flight Routes

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining safe flight routes for unmanned aerial vehicles (UAVs) over populated areas face challenges due to the limited reliability of population density data, especially in dense urban or suburban areas where land uses are varied, leading to suboptimal route calculations.

Innovation Solution

A system that subdivides a geographic region into base cells, adjusts population allocations based on accessible and inaccessible areas, and calculates adjustment factors for each cell considering ground features and activities, generating a population density map to select optimal flight routes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If population density data is calculated based on general census data at ground surface level, then the calculation process is simple, but the reliability and accuracy of population density data is limited, especially in dense urban or suburban areas with varied land uses

Engineering Contradiction:
Improvepopulation density data reliabilityVSAvoiddata processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the geographic region into multiple ground cells, each representing a specific ground surface area. For each ground cell, the system identifies and segments aerial images corresponding to that cell, then calculates population density independently for each cell based on detected ground features and activities. This segmentation approach enables localized accurate population density calculation while maintaining manageable processing complexity through systematic division of the overall region.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If population density is calculated for varying ground surfaces within a region, then the calculation covers all areas, but the accuracy becomes difficult to achieve and the data may be irrelevant to actual population densities of specific ground surfaces

Engineering Contradiction:
Improvepopulation density measurement accuracyVSAvoidroute determination efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent applies local quality by calculating population density specifically for each ground cell based on the actual ground features and activities detected in aerial images of that cell. Instead of applying a uniform population density calculation across the entire region, the system determines localized population densities that reflect the actual characteristics of each ground surface area, thereby improving measurement precision for route safety assessments.

Inventive Principle:
Principle #3Local quality

3Reliability

If routes are determined based on limited reliability population density data, then the route determination process is straightforward, but the routes selected may be suboptimal and less safe for UAV operations

Engineering Contradiction:
Improveflight route safetyVSAvoidpopulation density calculation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent performs preliminary action by calculating accurate population density data for each ground cell before determining the UAV flight route. The system processes aerial images, identifies ground features and activities, and establishes reliable population density measurements for all ground cells in advance. This preliminary population density assessment provides a solid foundation for subsequent route determination, ensuring that the selected flight paths are based on accurate safety information rather than estimated or averaged data.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11579611B1Predicting localized population densities for generating flight routes
Publication Date: 2023.02.14 AMAZON TECH INC
  • US11579611B1 patent drawing
  • US11579611B1 patent drawing
  • US11579611B1 patent drawing

AI summary

A population density map of a region is generated by dividing the region into cells and allocating a population of the region only to the cells that are accessible to people, or are believed to be populated. Each of the cells is classified based on one or more ground features of the cells, and an adjustment factor for each of the cells is determined based at least in part on the classifications. Equal shares of the population of the region are allocated to each of the cells that is accessible or populated, and the equal shares are multiplied by the adjustment factors determined for the respective ones of the cells to calculate a population for each of such cells.