UAV Fleet Assignment Control Using Multi-Stage Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The underutilization of unmanned aerial vehicles (UAVs) in various missions is caused by unjustified assumptions about their capabilities and objectives, leading to complex scheduling and control challenges due to multiple participants with different objectives, capabilities, and needs, which existing systems fail to address effectively.
Innovation Solution
A multi-stage optimization platform that separates optimization variables by time and space, allowing for a computationally efficient joint consideration of different participants' objectives, using a two-stage approach to simplify and optimize UAV scheduling and control, focusing on customer and terminal variables first, followed by drone operator optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single-stage optimization approach is used to control UAV fleets, then the system can consider all variables simultaneously, but the computational complexity becomes intractable and optimization performance deteriorates
Solution Approach 1:
The patent divides the single-stage optimization problem into multiple sequential stages. Each stage optimizes a specific subset of variables (e.g., mission assignment, path planning, resource allocation) while keeping other variables fixed or simplified. This segmentation makes the computational problem tractable while still achieving comprehensive optimization through the sequence of stages.
2Adaptability or versatility
If multiple participants with different objectives are included in the optimization, then the system becomes more realistic and applicable, but the scheduling and control complexity increases significantly
Solution Approach 1:
The patent implements dynamic optimization where the system adapts to different participants' objectives and constraints in real-time. The optimization parameters, weights, and constraints are dynamically adjusted based on the specific mission requirements, participant capabilities, and environmental conditions, allowing flexible coordination without fixed rigid scheduling.
Solution Approach 2:
The system changes optimization parameters such as objective function weights, constraint thresholds, and priority levels to accommodate different participants' needs. By dynamically adjusting these parameters rather than using fixed scheduling rules, the system manages multi-participant complexity while maintaining adaptability to diverse objectives.
3Device complexity
If unjustified assumptions about UAV capabilities are made, then the optimization problem simplifies, but the system fails to achieve complete utilization of UAV fleets
Solution Approach 1:
The patent removes unnecessary assumptions about UAV capabilities and instead uses partial information initially, refining the optimization as more data becomes available. The system performs optimization with available information and iteratively improves utilization by incorporating additional capability details, rather than making excessive simplifying assumptions that limit productivity.
Data Source
AI summary
The present disclosure provides a system and a method for controlling a fleet of Unmanned Aerial Vehicles (UAVs) to perform a mission. The method comprises receiving request data for the mission, obtaining assignments corresponding to one or more UAVs of the fleet of UAVs, and obtaining assignment data corresponding to each assignment. The method further comprises determining an assignment for the one or more UAVs by performing a first stage of a multi-stage optimization subject to a first set of constraints and updating the first list of assignments by adding the determined assignment to the first list of assignments. The method further comprises determining a second list of assignments for the one or more UAVs by performing a second stage of the multi-stage optimization subject to a second set of constraints and controlling the one or more UAVs based on the second list of assignments.