Multi-UAV Recovery Routing for Conflict-Safe Cluster Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current UAV recovery technologies are inadequate for dynamic recovery of multiple UAVs in complex environments, particularly in miniaturized and clustered formations, where efficient and safe reuse is necessary to improve task efficiency and reduce costs.
Innovation Solution
A dynamic recovery method for UAVs that prioritizes their recovery by calculating a total cost function based on task completion, distance, obstacles, damage, and flight time, using an improved particle swarm optimization algorithm to determine the optimal recovery order and resolve conflicts, ensuring efficient and safe recycling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional recovery technologies (parachute, net, line, mechanical arm) are used for single UAV, then recovery is simple and reliable, but it cannot handle dynamic recovery of multiple UAVs in cluster formation
Solution Approach 1:
The patent implements dynamic recovery by allowing UAVs to autonomously adjust their recovery timing and routing decisions based on real-time task completion status, battery levels, and cluster formation requirements. The recovery system transitions from static predetermined sequences to dynamic adaptive decision-making, where each UAV independently determines when and how to recover based on current system state
Solution Approach 2:
Each UAV is equipped with autonomous decision-making capabilities to self-determine recovery timing and routing without external control. The UAVs independently evaluate their task completion status, battery levels, and cluster requirements to make recovery decisions, eliminating the need for complex centralized control systems
2Reliability
If UAVs are recovered immediately after task completion, then flight time is reduced and safety improved, but task completion efficiency decreases due to loss of operational UAVs
Solution Approach 1:
The patent implements preliminary routing actions by pre-planning multiple possible recovery routes and task assignment sequences before actual recovery occurs. The system pre-calculates optimal routing paths considering various scenarios such as battery levels, distance to recovery point, and potential obstacles, enabling rapid response when recovery decisions are made without compromising task efficiency
Solution Approach 2:
The system dynamically changes operational parameters such as routing paths, recovery timing, and task assignment priorities based on real-time conditions. Parameters like battery threshold for recovery, optimal route selection, and task reassignment timing are adjusted continuously to balance safety requirements with mission completion efficiency
3Loss of time
If UAVs fly back to recovery point in parallel, then recovery time is shortened, but conflict and collision risk increases
Solution Approach 1:
The patent segments the recovery process by dividing the cluster into multiple groups that follow different routing paths to the recovery point. Instead of all UAVs flying directly back in parallel, they are partitioned into sequential batches or assigned to alternative routes, reducing spatial and temporal concentration of recovery traffic while maintaining overall recovery efficiency
Solution Approach 2:
The system resolves conflicts by transitioning from two-dimensional horizontal routing decisions to three-dimensional spatial-temporal coordination. UAVs are assigned different altitudes, time windows, and routing dimensions to avoid conflicts, adding vertical and temporal dimensions to the routing problem beyond simple horizontal path planning
4Productivity
If complex cost function optimization is used to determine recovery order, then recovery efficiency is improved, but computational complexity and time increase
Solution Approach 1:
The patent replaces complex centralized optimization algorithms with distributed autonomous decision-making at the UAV level. Instead of a ground control station calculating optimal recovery sequences for all UAVs using complex cost functions, each UAV independently evaluates its own recovery readiness and makes routing decisions based on simple local rules and real-time communication with the cluster
Solution Approach 2:
The system uses simplified, lightweight cost evaluation functions rather than complex optimization models. Each UAV employs a simple scoring mechanism based on key parameters (battery level, distance to recovery point, task priority) that can be rapidly calculated and updated, replacing computationally intensive optimization algorithms with faster, approximation-based decision rules
Data Source
AI summary
The disclosure provides a dynamic recovery method and system for UAVs and storage medium. On the basis of obtaining the environmental information of UAVs, combined with different factors such as the following task quantity of each UAV, the distance from the current position of each UAV to the recovery point, current performance of each UAV, total cost function is constructed, and optimization is carried out through improved particle swarm optimization algorithm. Then on the premise of the lowest recovery cost, the priority of each UAV is obtained. For the ordered UAV, the route to the recovery point is determined. At the same time, it is necessary to consider conflict resolution of UAVs when encountering obstacles in the flight process, as well as the possible failure in line recovery. At this time, it is necessary to reorder some hovering UAVs to ensure flight safety of UAVs and robustness of the algorithm.