Air Vehicle Navigation Using Crowd-Sourced 3D Obstacle Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current air vehicles face challenges in navigation and obstacle detection, particularly in complex environments, due to limitations in sensor data processing and real-time obstacle management, which can lead to inefficiencies and safety concerns.
Innovation Solution
A system that utilizes a network of air vehicles equipped with environmental sensors and edge processors to generate 3D models of their surroundings, crowd-source navigation data, and employ neural networks for obstacle detection and avoidance, enabling efficient and safe flight planning and execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If air vehicles use traditional sensor data processing methods, then device complexity is reduced, but navigation efficiency and obstacle detection capability deteriorate in complex environments
Solution Approach 1:
The system segments sensor data processing by deploying edge processors on individual vehicles to handle local navigation and obstacle detection, while centralized servers manage fleet-wide coordination and map building. This division allows each component to focus on specific tasks, improving overall navigation efficiency without requiring every vehicle to possess full processing capability.
Solution Approach 2:
The patent transitions from traditional 2D map representations to 3D environmental models by integrating data from multiple sensors (LIDAR, cameras, radar) and processing them through neural networks. This dimensional enhancement provides more comprehensive spatial awareness and obstacle detection capability in complex three-dimensional air environments.
2Reliability
If air vehicles employ comprehensive environmental sensing and real-time processing, then obstacle detection capability improves, but device complexity and energy consumption increase
Solution Approach 1:
Edge processors serve as intermediaries between raw sensor data and vehicle control systems. These processors pre-process sensor inputs, extract relevant features, and generate navigation commands, reducing the complexity burden on both sensor systems and vehicle control while maintaining high obstacle detection reliability through localized real-time processing.
Solution Approach 2:
The system implements continuous feedback loops where sensor data is processed in real-time, navigation decisions are executed, and outcomes are monitored. Neural networks learn from accumulated flight data and sensor feedback, continuously improving obstacle detection accuracy while adapting to reduce processing complexity for common scenarios.
3Ease of operation
If air vehicles operate autonomously with AI systems, then ease of operation improves, but reliability deteriorates due to accidents and missteps
Solution Approach 1:
Vehicles are equipped with autonomous navigation systems that independently process sensor data, make navigation decisions, and execute flight maneuvers without continuous human intervention. This self-service capability dramatically improves ease of operation while maintaining safety through multiple redundant systems and real-time monitoring.
Solution Approach 2:
The system merges multiple AI functions (obstacle detection, path planning, vehicle control) into an integrated navigation system. By combining these functions and sharing data across modules, the system achieves more reliable autonomous operation than isolated systems, as the combined system can compensate for individual module limitations and detect anomalies across the full operational context.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enhances navigation efficiency, reduces collision risks, and optimizes flight paths by providing real-time obstacle management and crowd-sourced data integration, improving overall air traffic control and vehicle safety.
Implementation Method 1
Based on LIDAR, radar, and camera images, the system can generate 3D models for navigation purposes
Implementation Method 2
Based on LIDAR, radar, and camera images, the system can generate 3D models for navigation purposes
Data Source
AI summary
Systems and methods are disclosed for transporting people using air vehicles.