HAPS Neural Network for Adaptive Drone Traffic and Flight Path Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current drones lack the ability to adapt to unplanned changes in their flight path, such as obstacles or GPS drift, and fail to react to anomalies in their environment, leading to potential collisions or data overcollection during asset inspection.
Innovation Solution
Implementing a neural network-based system, both on high-altitude pseudosatellite platforms (HAPSNN) and onboard drones (DINN), which enable real-time monitoring and adaptation of flight paths, allowing for safe navigation and efficient asset inspection by classifying and responding to environmental changes and anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional GPS navigation is used for drone flight paths, then the drone can follow preprogrammed routes, but the drone cannot adapt to GPS drift or unplanned environmental changes
Solution Approach 1:
The patent implements dynamic flight path adjustment by continuously monitoring GPS drift vectors and environmental conditions, then recalculating waypoints in real-time. The navigation system transitions from static preprogrammed routes to dynamic adaptive paths that respond to changing conditions, resolving the contradiction between adaptability and system complexity.
Solution Approach 2:
The system employs feedback mechanisms by continuously monitoring GPS position data, comparing actual position with planned position, detecting drift vectors, and using this feedback to trigger recalculation of flight paths. This closed-loop control enables adaptation to environmental changes while maintaining manageable system complexity through automated feedback processing.
2Measurement precision
If the drone follows a fixed preprogrammed flight path, then the flight plan is simple to execute, but the drone may take assets outside the field of view due to GPS drift
Solution Approach 1:
The system performs preliminary calculations of GPS drift vectors and potential path deviations before executing the flight. By pre-calculating correction factors and having recalculation algorithms ready, the system minimizes the time loss when path adjustments are needed while maintaining high waypoint accuracy through proactive drift compensation.
Solution Approach 2:
The patent dynamically changes navigation parameters such as waypoint coordinates, flight path angles, and timing based on detected GPS drift. By adjusting these parameters in real-time rather than following fixed values, the system maintains measurement precision while the automated parameter changes occur efficiently without significant time loss.
3Adaptability or versatility
If the drone uses onboard sensors to monitor the environment, then the drone can collect data about obstacles and assets, but the drone cannot react to unplanned changes or anomalies
Solution Approach 1:
The patent implements self-service by enabling the drone to autonomously process sensor data, detect anomalies, and trigger appropriate responses without external intervention. The system self-monitors sensor inputs, self-diagnoses environmental changes, and self-corrects flight paths, reducing the apparent complexity of sensor integration while improving adaptability to anomalies.
Solution Approach 2:
The system replaces complex mechanical sensor integration and manual response systems with automated electronic processing and algorithmic decision-making. By substituting mechanical complexity with software-based anomaly detection and response mechanisms, the system achieves high adaptability while managing overall system complexity through electronic automation.
4Reliability
If the drone operates in authorized airspace under FAA regulations, then the drone can receive airspace authorization, but the drone operator must maintain real-time communication with UTM systems
Solution Approach 1:
The patent applies self-service by enabling the autonomous vehicle to independently manage airspace authorization requests and maintain communication with UTM systems without requiring continuous operator intervention. The system automatically sends authorization requests, receives approvals, and maintains compliant communication, thereby ensuring reliable airspace authorization while significantly reducing the operator's communication burden.
Data Source
AI summary
A HAPS platform may execute a neural network (a “HAPSNN”) as it monitors air traffic; the neural network enables it to classify, predict, and resolve events in its airspace of coverage in real time as well as learn from new events that have never before been seen or detected. The HAPSNN-equipped HAPS platform may provide surveillance of nearly 100% of air traffic in its airspace of coverage, and the HAPSNN may process data received from a drone to facilitate safe and efficient drone operation within an airspace.