Hierarchical UAV Swarm Path Planning for 4D Deconfliction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for 4D path planning for aircraft and UAVs are computationally infeasible at scales required for dense urban environments, particularly when dealing with multiple UAVs in proximity to each other, as they struggle to efficiently avoid collisions and near-misses while maintaining computational efficiency.
Innovation Solution
The implementation of hierarchical swarm-based 4D UAV path planning systems, which divide UAVs into swarms and decompose control into two logical levels: a swarm level and an individual UAV level, using two path planning algorithms to steer swarms and individual UAVs towards their destinations while avoiding conflicts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional 4D path planning techniques are applied to multiple UAVs, then collision avoidance is achieved, but computational complexity rises rapidly making it infeasible at scale
Solution Approach 1:
The system segments the UAV fleet into multiple swarms, where each swarm is controlled independently. This segmentation reduces the computational complexity by dividing the overall path planning problem into smaller, manageable sub-problems for each swarm, while still ensuring collision avoidance through inter-swarm deconfliction mechanisms.
Solution Approach 2:
The system introduces a hierarchical dimension to the control architecture, with swarm-level control operating at one level and individual UAV control operating at another level. This dimensional organization allows collision avoidance to be handled at the swarm level while individual UAVs focus on following swarm trajectories, significantly reducing computational burden.
2Reliability
If all UAVs are deconflicted individually, then collision avoidance is ensured, but unnecessary computations are performed on UAVs that are distant from one another
Solution Approach 1:
The system applies deconfliction computations locally at the swarm level rather than globally for all UAVs. Each swarm performs deconfliction only with other swarms in its proximity, and individual UAVs within a swarm follow the swarm's collectively determined trajectory. This local approach ensures collision avoidance while eliminating unnecessary computations for distant UAVs.
3Productivity
If hierarchical swarm-based control is implemented, then computational feasibility is improved, but system structure becomes more complex
Solution Approach 1:
The control structure is segmented into distinct functional layers: swarm-level deconfliction modules that handle inter-swarm coordination, and individual UAV control modules that execute swarm trajectories. This segmentation, while creating structural complexity, enables computational feasibility by distributing the control burden across multiple independent modules rather than requiring a monolithic control system.
Data Source
AI summary
Disclosed herein are systems and methods for path planning for UAVs. A set of UAVs is logically arranged into a plurality of swarms, each having a swarm-leader UAV. A first path planning algorithm is applied to determine navigation instructions to steer the swarm-leader UAVs towards respective destinations for the swarms and to deconflict the swarm-leader UAVs from one another. A set of second path planning algorithms is applied to determine navigation instructions to steer non-swarm-leader UAVs in each swarm toward their respective swarm leaders and to deconflict the UAVs from other UAVs in the swarm. Separate QUBO path planning algorithms may be used for the first path planning algorithm and the set of second path planning algorithms. If merging criteria for combining two swarms are met, a single QUBO may be used to control all non-swarm-leader UAVs in merged swarms.