Aerial Landing Zone Heatmaps with Distance Transforms for Safe Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous aerial vehicles face challenges in identifying safe emergency landing zones in real-time, especially in unstructured terrains, due to the lack of reliable perception algorithms for dynamic objects and terrain depth information.
Innovation Solution
A system utilizing image-capture devices and processors to generate landing quality heatmaps, processed with computational geometry algorithms, identifies safe landing zones by clustering pixels/voxels and determining areas farthest from obstacles, integrating with inertial navigation for real-time guidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If perception algorithms are used to process dynamic object information from sensors in real-time, then safe landing zone identification capability is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent segments the perception pipeline into distinct modules: depth map generation from sensor data, landing quality heatmap generation, binary mask creation through thresholding, and connected component labeling. This modular segmentation allows each module to be optimized independently, reducing overall computational complexity while maintaining reliable safe landing zone identification through systematic processing of dynamic object information.
2Reliability
If dense depth information and semantic understanding are processed in real-time to identify safe landing zones, then landing safety is improved, but computational resource consumption increases
Solution Approach 1:
The patent extracts only the essential features needed for safe landing zone identification from the full sensor data stream. Instead of processing all raw sensor information, the system extracts depth map data and semantic features relevant to landing safety, converts them to landing quality heatmaps, and identifies safe zones through binary masking. This extraction approach maintains high landing safety while reducing computational resource consumption by focusing only on critical information.
3Measurement precision
If connected component labelling and distance transform algorithms are applied to landing quality heatmaps, then precision in identifying safe landing zones is improved, but processing time increases
Solution Approach 1:
The patent applies connected component labeling and distance transform algorithms as preliminary processing steps before final safe landing zone identification. By pre-processing the landing quality heatmap to create binary masks with labeled connected components and distance transforms, the system prepares optimized data structures that enable rapid and precise safe zone localization when needed, reducing real-time processing time while maintaining high measurement precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system for localization of a safe landing zone comprises at least one image-capture device onboard an aerial vehicle, and an onboard processor coupled to the image-capture device. The processor is operative to execute instructions to perform a method that comprises: receive, from the image-capture device, two or more overlapping images of a landscape underneath the aerial vehicle; generate, based on the overlapping images, a landing zone heatmap of the landscape; identify, based on the landing zone heatmap, one or more regions of the landscape having potential landing zones and obstacles; and determine a location of a safe landing zone using a distance transform of the one or more regions of the landscape. The location of the safe landing zone is in an area within one of the potential landing zones that is farthest from the obstacles. The location of the safe landing zone is then stored in a database.