Inspection UAV Neural Navigation for Obstacles and GPS Drift
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional drones lack the ability to autonomously adapt to unplanned changes in their flight path, such as obstacles or GPS drift, and fail to react to anomalies in the environment, leading to inefficient and potentially unsafe inspection operations, especially in complex environments like large power stations.
Innovation Solution
The implementation of a neural network-based system, known as the Drone Inspection Neural Network (DINN), which analyzes real-time image frames and sensor data to navigate and inspect assets, and cooperates with High-Altitude Pseudosatellite (HAPS) platforms equipped with neural networks (HAPSNN) to adjust flight paths, avoid collisions, and optimize mission execution by communicating with air traffic management systems for real-time airspace authorizations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional drones follow preprogrammed flight paths with GPS waypoints, then navigation is simple and equipment is basic, but the drone cannot adapt to unplanned changes such as obstacles or GPS drift, leading to unsafe operations and inefficient inspections
Solution Approach 1:
The patent implements dynamic flight path adjustment by enabling the drone to compute revised flight paths in real-time based on detected obstacles and GPS drift conditions. The system transitions from static preprogrammed waypoints to dynamic adaptive navigation, where the flight path continuously adjusts to environmental conditions while maintaining mission objectives.
Solution Approach 2:
The system employs feedback mechanisms by continuously monitoring sensor data, obstacle detections, and GPS position information, then using this feedback to compute and execute revised flight paths. The drone processes real-time environmental information and adjusts its navigation accordingly, creating a closed-loop adaptive control system.
2Productivity
If drones are operated manually within line of sight, then the operator can react to unexpected conditions, but this requires personnel presence at each site and sustained close attention, reducing efficiency especially for large installations
Solution Approach 1:
The drone performs self-service by autonomously detecting obstacles, computing revised flight paths, and executing navigation adjustments without continuous human intervention. The system independently processes sensor data, identifies hazards, and modifies its flight plan, enabling unattended operation while maintaining safety and mission effectiveness.
Solution Approach 2:
The patent replaces manual mechanical control with automated computational systems. Instead of human operators visually monitoring and manually controlling the drone, the system uses onboard sensors, processors, and algorithms to autonomously navigate, detect obstacles, and adjust flight paths, substituting human cognitive and physical operations with automated electronic systems.
3Measurement precision
If drones closely approach assets for detailed inspection, then inspection quality improves, but the drone must maintain safe distance from obstacles and structure, creating conflicting navigation requirements
Solution Approach 1:
The system dynamically adjusts the drone's proximity to assets based on real-time obstacle detection and environmental conditions. The flight path computation balances inspection quality requirements with safety constraints, allowing close approach when safe and maintaining distance when hazards are present, creating a flexible adaptive navigation strategy.
Solution Approach 2:
The patent applies local quality by allowing different spatial zones to have different safety margins and approach characteristics. The drone computes revised flight paths that optimize inspection quality at specific asset locations while maintaining appropriate safety distances from obstacles in surrounding areas, creating localized navigation parameters tailored to each spatial context.
Data Source
AI summary
An unmanned aerial vehicle (UAV) or “drone” executes a neural network to assist with inspection, surveillance, reporting, and other missions. The drone inspection neural network may monitor, in real time, the data stream from a plurality of onboard sensors during navigation to an asset along a preprogrammed flight path and/or during its mission (e.g., as it scans and inspects an asset).