UAV Delivery Zone Selection Using 3D Point Clouds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Uncrewed aerial vehicles (UAVs) face challenges in determining safe delivery points that avoid obstacles, as existing obstacle detection methods from two-dimensional images are inadequate and lack access to updated maps and satellite imagery, making it difficult to navigate and descend safely.
Innovation Solution
UAVs use three-dimensional segmented point clouds with semantic classifications to identify delivery points that satisfy conditions for safe descent, avoiding obstacles by determining a lateral distance away from classified areas, and transmit these points to a server device for storage and retrieval during missions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If UAVs use two-dimensional image-based obstacle detection methods, then the system complexity is low, but the measurement precision and reliability of obstacle detection are insufficient
Solution Approach 1:
The patent transitions from two-dimensional image-based obstacle detection to three-dimensional point cloud analysis. By capturing depth information and spatial coordinates, the system creates a 3D representation of the environment, enabling precise measurement of obstacle locations, heights, and distances. This dimensional upgrade directly resolves the contradiction by providing superior measurement precision while maintaining manageable system complexity through software-based processing.
Solution Approach 2:
The patent introduces a segmented point cloud as an intermediary data structure between raw sensor data and obstacle detection results. The point cloud segments the environment into distinct regions (ground, obstacles, delivery zones) with semantic classifications, serving as a mediator that transforms complex sensor data into actionable spatial information. This intermediary layer enhances detection precision while organizing the complexity into manageable processing stages.
2Reliability
If UAVs lack access to updated maps and satellite imagery, then the ease of operation is maintained, but the reliability of navigation and delivery point selection deteriorates
Solution Approach 1:
The patent performs preliminary survey flights to capture and store three-dimensional point cloud data of delivery locations before actual payload delivery missions. This advance reconnaissance creates a digital map of the environment, including obstacle locations and safe delivery zones. By performing this action in advance, the system ensures reliable navigation during actual missions without requiring complex real-time map updates or external satellite imagery during operation.
Solution Approach 2:
The patent creates a digital copy of the physical environment through three-dimensional point cloud reconstruction. This virtual model includes segmented spatial data with semantic classifications that replicates the real-world delivery location. The copied environment data stored on the server enables reliable navigation and delivery point selection during missions without requiring the UAV to access external maps or satellite imagery in real-time, maintaining operational simplicity.
3Reliability
If UAVs perform comprehensive environmental surveying to identify safe delivery points, then the reliability of payload delivery improves, but the time required for survey and data processing increases
Solution Approach 1:
The patent performs comprehensive environmental surveying and stores the three-dimensional point cloud data on a server before actual delivery missions. By completing the time-consuming survey and data processing in advance, the system ensures reliable payload delivery during missions without incurring time delays. The pre-processed spatial data with segmented delivery zones is readily available for rapid retrieval and use during actual operations.
Solution Approach 2:
The patent creates and stores a digital copy of the surveyed environment on a server, including segmented point cloud data with identified safe delivery zones. This copied spatial information is preserved and can be rapidly retrieved during delivery missions without requiring repeated surveying. The pre-captured environmental model enables fast decision-making during missions while the comprehensive survey was performed in advance when time was available.
Data Source
AI summary
A method includes navigating, by a UAV, to a delivery location in an environment; capturing, by at least one sensor on the UAV, sensor data representative of the delivery location; determining, based on the sensor data, a segmented point cloud of the delivery location, wherein the segmented point cloud defines a plurality of point cloud areas with corresponding semantic classifications; determining, based on the segmented point cloud, that a pre-selected delivery point at the delivery location satisfies a condition indicating that a descent path through a cylinder, the cylinder being centered above the pre-selected delivery point and having a radius of a particular lateral distance, does not intersect with any point cloud areas having semantic classifications indicative of an obstacle at the delivery location; and based on determining that the pre-selected delivery point satisfies the condition, initiating, by the UAV, a payload delivery operation towards the pre-selected delivery point.