UAV Delivery Point Adjustment Using Semantic Obstacle Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) face challenges in safely delivering payloads due to obstacles in the delivery location, which can result in collisions and damage to the UAV, payload, or obstacles.
Innovation Solution
The UAV captures an image of the delivery location, determines a segmentation image to identify pixel areas associated with obstacles, and calculates a distance-to-obstacle image. Based on this information, the UAV selects a 'nudged' delivery point farther away from obstacles and positions itself above this point for safe payload delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the UAV delivers the payload directly to the target delivery point, then the delivery operation is simple and fast, but the UAV may collide with obstacles causing damage
Solution Approach 1:
The system performs preliminary actions by capturing an image of the delivery location, determining a segmentation image to identify obstacles, and calculating a distance-to-obstacle image before the actual delivery. This advance analysis allows the UAV to select a safe delivery point that avoids obstacles, thereby improving reliability without adding significant complexity to the delivery process.
2Reliability
If the UAV uses obstacle detection and segmentation imaging to select a safe delivery point, then the delivery safety is improved, but the processing time and computational complexity increase
Solution Approach 1:
The system applies segmentation by dividing the delivery location image into pixel areas with semantic classifications, creating a segmentation image that identifies obstacles. This segmentation approach efficiently processes the image data by categorizing different regions, enabling the UAV to quickly identify safe delivery points while maintaining delivery safety.
3Manufacturing precision
If the UAV positions itself above the nudged delivery point based on distance-to-obstacle image, then the payload delivery accuracy is improved, but the positioning complexity increases
Solution Approach 1:
The system replaces complex mechanical positioning adjustments with image processing and computational methods. By calculating the distance-to-obstacle image and selecting a nudged delivery point based on this data, the UAV achieves precise positioning without requiring complex mechanical positioning systems or manual adjustments.
Data Source
AI summary
A method includes capturing, by a sensor on an unmanned aerial vehicle (UAV), an image of a delivery location. The method further includes determining, based on the image of the delivery location, a segmentation image. The segmentation image segments the delivery location into a plurality of pixel areas with corresponding semantic classifications. The method also includes determining, based on the segmentation image, a distance-to-obstacle image of a delivery zone at the delivery location. The distance-to-obstacle image comprises a plurality of pixels, each pixel representing a distance in the segmentation image from a nearest pixel area with a semantic classification indicative of an obstacle in the delivery location. Additionally, the method includes selecting, based on the distance-to-obstacle image, a delivery point in the delivery zone. The method also includes positioning the UAV above the delivery point in the delivery zone for delivery of a payload.