Swarm Intelligence for Adaptive UAV Fleet Scheduling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing logistics systems for UAV delivery face challenges in flexibility and efficiency, particularly in scheduling and adapting to real-time changes, leading to latency and suboptimal utilization of UAV fleets.

Innovation Solution

Implementing swarm intelligence and interactive ordering systems that allow decentralized coordination and adaptive scheduling of UAV fleets based on location-specific pricing and user orders, enabling flexible and robust utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If centralized planning is used to maximize UAV utilization, then fleet utilization efficiency is improved, but system flexibility and adaptability to real-time changes deteriorates

Engineering Contradiction:

Improvefleet utilization efficiencyVSAvoidsystem flexibility

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system segments the centralized scheduling function into distributed autonomous decision-making units at each UAV and delivery location. Each UAV and location independently evaluates and executes delivery decisions based on local conditions, eliminating the need for centralized real-time coordination while maintaining high utilization through decentralized optimization

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system implements dynamic, real-time decision-making capabilities at each UAV and delivery location, allowing immediate adaptation to changing conditions such as new delivery requests, UAV availability, and location-specific constraints. This dynamic local decision-making replaces static centralized planning, enabling both high utilization and flexibility simultaneously

Inventive Principle:

Principle #15Dynamics

2Loss of time

If short time span scheduling is used to mitigate latency, then real-time adaptability is improved, but optimization quality deteriorates

Engineering Contradiction:

Improvescheduling latencyVSAvoidoptimization quality

Core Design Contradiction:

Loss of timeVSProductivity

Solution Approach 1:

The system pre-computes and stores delivery cost matrices for all possible delivery locations and UAV combinations offline, capturing complex optimization considerations in advance. During real-time operation, the system only needs to query these pre-computed matrices and apply simple selection logic, achieving both rapid response and high optimization quality without latency

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system prepares comprehensive delivery cost matrices that incorporate various constraints and optimization criteria before real-time scheduling needs to occur. These pre-prepared matrices act as a cushion that allows the system to make high-quality decisions rapidly during real-time operation without needing to perform complex optimizations under time pressure

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

3Productivity

If centralized control structure is used to coordinate UAV fleet, then scheduling optimization is improved, but system complexity and computational requirements deteriorates

Engineering Contradiction:

Improvescheduling optimizationVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system divides the complex scheduling optimization problem into independent segments handled by each UAV and delivery location. Each segment autonomously evaluates local delivery opportunities using pre-computed cost matrices, eliminating the need for complex centralized coordination while maintaining optimization quality through distributed decision-making

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Each UAV and delivery location serves itself by independently evaluating delivery opportunities and making scheduling decisions based on local conditions and pre-computed cost data. This self-service approach eliminates complex inter-communication and coordination requirements, reducing system complexity while maintaining optimization effectiveness

Inventive Principle:

Principle #25Self-service

Data Source

PatentEP3886012B1Improved utilization of a fleet of unmanned aerial vehicles for delivery of goods

Publication Date: 2025.10.01 SONY GROUP CORP

Figure 1
Figure 2~3A
Figure 3B~3C

AI summary

A scheduling device performs a method of scheduling transports by a fleet of unmanned aerial vehicles, UAVs, to enable improved utilization of the fleet. The method comprises computing (111), for the fleet, aggregated cost data, ACM, that associates utilization cost with distributed sub-regions within a geographic region, the utilization cost of a respective sub-region representing an estimated cost for directing at least one of the UAVs to the respective sub-region. The method further comprises receiving (112) a query indicative of one or more potential locations for pick-up or delivery of a payload, determining (113), based on the ACM, a transportation price for at least one potential location; and presenting (114) the transportation price for the at least one potential location. The scheduling device thereby provides an interactive ordering system that enables utilization of the fleet to be automatically optimized by swarm intelligence.