Decentralized UAV Movement Planning for Peer Conflict Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing unmanned vehicles (UVs) face challenges in avoiding collisions in shared airspace without centralized traffic management, particularly when communication with a UTM server is unavailable or impractical.
Innovation Solution
UVs employ decentralized movement planning through direct communication to determine and update movement plans using cost functions, considering individual priorities and capabilities to avoid conflicts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If decentralized movement planning is implemented between UVs, then conflict resolution capability is improved and UTM server dependency is reduced, but communication overhead and computational complexity increase
Solution Approach 1:
The system segments the centralized UTM server functionality into distributed components within each UV. Each UV independently executes cost function evaluations and movement plan negotiations, transforming a monolithic centralized system into modular autonomous units that resolve conflicts peer-to-peer.
Solution Approach 2:
UVs perform preliminary cost function evaluations and conflict assessments before finalizing movement plans. By pre-calculating cost values for different movement plan combinations and exchanging this information with other UVs, the system avoids last-minute conflict resolution and reduces real-time communication overhead.
2Measurement precision
If UVs exchange movement plans and cost values iteratively, then conflict resolution accuracy is improved, but time consumption and computational load increase
Solution Approach 1:
The system performs a limited number of iterative exchanges (e.g., 2-3 rounds) between UVs rather than exhaustive optimization. This partial action approach achieves sufficient conflict resolution accuracy for safety-critical applications without incurring prohibitive time delays, balancing precision with real-time operational constraints.
Solution Approach 2:
When UVs detect critical conflicts with high collision risk, the system rushes through the cost function evaluation and plan exchange process with reduced iterations. Non-critical conflicts undergo more thorough iterative optimization, allowing the system to prioritize time-sensitive conflict resolution scenarios.
3Productivity
If UVs use cost functions to evaluate movement plan combinations, then optimality of resolved conflicts is improved, but computational complexity increases
Solution Approach 1:
The cost function evaluates movement plans based on adjustable parameters such as energy consumption, time, distance, and safety margins. By changing these parameter weights dynamically based on operational context (e.g., prioritizing energy efficiency during low-traffic periods vs. speed during urgent deliveries), the system optimizes conflict resolution without requiring complex algorithms.
Solution Approach 2:
Each UV creates simplified copies or representations of other UVs' movement plans and cost structures to perform local evaluations. Instead of computing full multi-UV optimization problems, UVs use these copied models to estimate cost values for different plan combinations, significantly reducing computational complexity while maintaining solution quality.
Data Source
AI summary
A decentralized method for a first Unmanned Vehicle, UV, for avoiding a conflict with a second UV is provided. The method includes determining, based on a current movement plan of the first UV and a current movement plan of the second UV received from the second UV, whether a conflict with the second UV is likely to occur. If it is determined that a conflict with the second UV is likely to occur, the method further includes performing at least one iteration of the following steps: a) determining a candidate movement plan of the first UV and receiving, from the second UV, a candidate movement plan of the second UV; b) determining first cost values for different combinations of one of the current movement plan and the candidate movement plan of the first UV with one of the current movement plan and the candidate movement plan of the second UV using a first cost function; c) receiving, from the second UV, second cost values for the different combinations, wherein the second cost values are calculated by the second UV using a second cost function; d) combining the first cost values and the second cost values in order to determine third cost values for the different combinations; and e) updating the current movement plan of the first UV to the movement plan of the first UV that is included in the combination exhibiting the best third cost value among the different combinations.