Cooperative UAV Positioning With Human-Loop Request Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in efficiently managing human-on-the-loop interactions with multiple unmanned aerial vehicles (UAVs), leading to excessive concurrent requests and slowed processing due to limited human resources, which affects the overall performance and resilience of positioning systems.
Innovation Solution
A method and system utilizing a mean field game (MFG) framework to optimize human-on-the-loop interactions by determining initial distributions, policies, and tolerance values, with iterative updates of Q-functions and dual variables to manage UAV requests, ensuring efficient resource utilization and resilience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If each UAV requests human interactions based on self-evaluations to maximize its own probability of fulfilling the task, then individual UAV task fulfillment probability is improved, but excessive concurrent requests slow down human processing and reduce overall system productivity
Solution Approach 1:
The system implements feedback mechanisms where UAVs receive information about the current state of human processing and adjust their request timing accordingly. The human operator receives feedback about incoming requests and can prioritize or defer handling based on current workload, creating a closed-loop system that balances individual UAV needs with overall processing capacity.
Solution Approach 2:
Instead of continuous or simultaneous requests from all UAVs, the system employs periodic request patterns where UAVs are scheduled to request human interactions at different time intervals. This temporal distribution prevents request overload and allows the human operator to process requests at a manageable pace while still maintaining high task fulfillment probabilities for individual UAVs.
2Reliability
If human-on-the-loop control is implemented to enhance resilience of the positioning system, then system reliability is improved, but limited human resources create bottlenecks in processing multiple UAV requests
Solution Approach 1:
The system segments the human-on-the-loop control function into discrete, manageable request units for each UAV. Instead of managing all UAVs simultaneously as a monolithic system, each UAV's control requests are handled as separate, modular units that can be queued, prioritized, and processed individually, reducing the overall complexity of human resource management.
Solution Approach 2:
The system introduces an intermediary layer (the request management system) between the UAVs and the human operator. This intermediary automatically filters, prioritizes, and schedules requests before presenting them to the human operator, reducing the cognitive and operational complexity the human must manage while maintaining the benefits of human-on-the-loop control for system resilience.
3Area of stationary object
If multiple UAVs operate concurrently with independent request policies, then system coverage and operational capacity are improved, but coordination overhead and processing delays increase
Solution Approach 1:
The system merges the request management of multiple UAVs into a unified coordination framework. Instead of each UAV operating with completely independent request policies that may conflict or overlap, the system combines their requests into a single managed queue with shared prioritization rules, reducing coordination overhead and processing delays while maintaining comprehensive system coverage.
Data Source
AI summary
The present disclosure provides a method, a system and a storage medium of resilient human-on-the-loop range-only cooperative positioning of a plurality of unmanned aerial vehicles (UAVs). The method includes computing an initial exploitability using an initial distribution and an initial policy; performing a forward updating of a distribution of a portion of the plurality of UAVs, and performing a backward updating of a Q function of each UAV of the plurality of UAVs; for each time step, calculating a dual variable at an (i+1)-th iteration and calculating a policy at an (i+1)-th iteration; computing a ratio of an exploitability at the (i+1)-th iteration over the initial exploitability; and if the ratio is less than or equal to a pre-defined tolerance value, maintaining a policy at the i-th iteration; and if the ratio is greater than the pre-defined tolerance value, using the policy at the (i+1)-th iteration.