UAV Visual Landing-Site Selection Under Navigation Signal Failure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) face challenges in automatically identifying and navigating to a suitable landing location, especially when conventional navigation systems are compromised due to factors like inclement weather or electromagnetic interference.
Innovation Solution
The system captures overlapping images of the landscape, generates a depth map to identify flat regions, assigns a landing zone quality score using machine-learning models, and automatically navigates the UAV to the most suitable location based on these scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional navigation systems are used for UAV landing, then navigation reliability is maintained under normal conditions, but the system becomes vulnerable to failure when compromised by inclement weather or electromagnetic interference
Solution Approach 1:
The patent introduces an intermediary visual-based navigation system that processes images from cameras to create depth maps and identify landing zones. This intermediary system bridges the gap when primary navigation systems fail due to weather or electromagnetic interference, providing an alternative pathway for safe landing without direct reliance on compromised conventional systems
Solution Approach 2:
The system changes the operational parameters of navigation by switching from electromagnetic signal-based navigation (GPS, radio) to visual-based navigation using image processing. This parameter change involves transitioning from signal-dependent operations to optical field-based operations, making the system adaptable to conditions where electromagnetic signals are compromised
2Ease of operation
If automated landing systems are implemented, then ease of operation is improved with minimal human intervention, but device complexity increases due to additional sensors and processing requirements
Solution Approach 1:
The patent applies multi-functionality by using the same image capture devices and processing circuitry for multiple purposes: navigation, obstacle detection, landing zone identification, and depth mapping. This universal approach allows automated landing functionality to be integrated into existing UAV systems without requiring entirely separate dedicated components, thereby managing complexity while enhancing ease of operation
Solution Approach 2:
The system enables self-service automated landing by equipping the UAV with onboard image capture devices and processing circuitry that autonomously identify suitable landing zones and guide the landing process without human intervention. The UAV serves itself by independently processing visual information to determine landing safety and execute the landing maneuver
3Reliability
If depth maps and quality scoring systems are used to identify suitable landing zones, then landing safety is improved, but loss of time increases due to additional image processing requirements
Solution Approach 1:
The system applies partial action by focusing image processing efforts on identifying key landing zone characteristics rather than analyzing every detail of the entire field of view. The processing circuitry concentrates computational resources on detecting depth variations and quality metrics in regions most critical for safe landing, rather than performing exhaustive analysis of all captured image data
Solution Approach 2:
The patent implements preliminary action by pre-processing images to extract depth information and identify potential landing zones before the actual landing decision is made. Depth maps are generated in advance during the approach phase, allowing the system to evaluate multiple candidate locations and prepare quality scores beforehand, reducing critical processing time at the moment of landing execution
Data Source
AI summary
An unmanned aerial vehicle (UAV) navigation system is configured to automatically identify a suitable UAV landing site, for example, in forced-landing (e.g., emergency) scenarios. In some examples, the system receives two or more overlapping images depicting a landscape underneath an airborne unmanned aerial vehicle (UAV); generates, based on the two or more overlapping images, a depth map for the landscape; identifies, based on the depth map, regions of the landscape having a depth variance below a threshold value; determines, for each of the regions of the landscape having a depth variance below the threshold value, a landing zone quality score indicative of the depth variance and a semantic type of the region of the landscape; identifies, based on the landing zone quality scores, a suitable location for landing the UAV; and causes the UAV to automatically navigate toward and land on the suitable location.