Unmanned Aircraft Traffic Management via Vertical Lane Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing use of unmanned aircraft (UAs) in residential and commercial areas poses a risk of collisions and requires effective air traffic management to ensure safe operation and optimize throughput.
Innovation Solution
A computer-implemented method and system that utilizes machine learning, specifically reinforcement learning, to manage UAs in a predefined airspace by defining vertical travel lanes based on existing roadway infrastructure, assigning UAs to these lanes based on their flight paths, and optimizing their routes to minimize travel time and prevent collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If UAs operate in residential and commercial areas without structured traffic management, then operational flexibility is maintained, but collision risk increases
Solution Approach 1:
The airspace is segmented into multiple vertical travel lanes stacked above roadway corridors. Each lane operates at a different altitude range, creating organized channels for UA traffic. This segmentation allows multiple UAs to operate simultaneously in the same geographic area without collision by assigning them to different vertical lanes.
Solution Approach 2:
The system adds a vertical dimension to traditional two-dimensional roadway traffic management. By creating stacked vertical lanes above ground-level roadways, the system transforms flat traffic patterns into three-dimensional flight paths, enabling increased UA throughput while maintaining separation between aircraft.
2Productivity
If reinforcement learning is used to optimize UA routes in real-time, then throughput is improved, but computational complexity increases
Solution Approach 1:
The system pre-defines vertical travel lanes and altitude ranges based on roadway infrastructure before UA operations begin. This preliminary structuring of the airspace eliminates the need for real-time complex path calculations, allowing reinforcement learning to focus only on assigning UAs to appropriate pre-established lanes rather than calculating entire flight paths from scratch.
Solution Approach 2:
The vertical lane structure acts as an intermediary between the complex reinforcement learning algorithm and the physical UA operations. Instead of the algorithm directly controlling continuous flight paths, it assigns UAs to discrete vertical lanes, simplifying the decision space while maintaining optimization capabilities.
Data Source
AI summary
Aspects of the invention include receiving, by a processor, airspace data associated with a predefined airspace, obtaining roadway data associated with the predefined airspace, determining a set of air travel channels within the predefined airspace based on the roadway data, defining a set of travel lanes within the set of air travel channels, wherein each travel lane in the set of travel lanes comprises an altitude range, receiving unmanned aircraft (UA) data associated with a set of UAs within the predefined airspace, wherein the UA data comprises one or more flight paths for each UA in the set of UAs, and assigning each UA in the set of UAs to a travel lane in the set of travel lanes based on the one or more flight paths.