Cluster&Disperse: a general air conflict resolution heuristic using unsupervised learning

2025-01-08

AI Summary

To address low efficiency and poor flexibility in resolving trajectory conflicts among aircraft in high-density airspace, this paper proposes an unsupervised learning–driven hierarchical heuristic framework. Methodologically, the first stage identifies conflict hotspots via unsupervised clustering; the second stage performs dynamic trajectory redistribution using a “cross-altitude-layer dispersion” strategy coupled with a socially inspired force model on the horizontal plane, followed by gradient-based optimization—integrated with aviation-convention–guided arc maneuvers and Radius-to-Fix path generation. The key contribution is a novel decoupled “clustering–dispersion” two-stage paradigm that enables flexible embedding of multiple operational constraints, overcoming the rigidity of traditional mixed-integer programming (MIP) approaches. Experiments demonstrate >99.7% conflict resolution rate with millisecond-level response time, significantly outperforming state-of-the-art algorithms while ensuring strong constraint compatibility and engineering deployability.

Technology Category

• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Search and Optimization: Heuristic Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We provide a general and malleable heuristic for the air conflict resolution problem. This heuristic is based on a new neighborhood structure for searching the solution space of trajectories and flight-levels. Using unsupervised learning, the core idea of our heuristic is to cluster the conflict points and disperse them in various flight levels. Our first algorithm is called Cluster&Disperse and in each iteration it assigns the most problematic flights in each cluster to another flight-level. In effect, we shuffle them between the flight-levels until we achieve a well-balanced configuration. The Cluster&Disperse algorithm then uses any horizontal plane conflict resolution algorithm as a subroutine to solve these well-balanced instances. Nevertheless, we develop a novel algorithm for the horizontal plane based on a similar idea. That is we cluster and disperse the conflict points spatially in the same flight level using the gradient descent and a social force. We use a novel maneuver making flights travel on an arc instead of a straight path which is based on the aviation routine of the Radius to Fix legs. Our algorithms can handle a high density of flights within a reasonable computation time. We put their performance in context with some notable algorithms from the literature. Being a general framework, a particular strength of the Cluster&Disperse is its malleability in allowing various constraints regarding the aircraft or the environment to be integrated with ease. This is in contrast to the models for instance based on mixed integer programming.

Problem

• Airborne Conflict Resolution
• Flight Path Optimization
• Air Traffic Management Efficiency

Innovation

• Clustering and Dispersion Algorithm
• Unsupervised Learning
• Airspace Conflict Resolution