Deep Neural Network-Based Aerial Transport in the Presence of Cooperative and Uncooperative UAS

2025-12-06

AI Summary

This work addresses decentralized robust cooperative transport and coverage in highly dynamic, partially observable airspace containing both cooperative and non-cooperative unmanned aerial systems (UAS). Method: We propose a hierarchical “mentor–apprentice” multi-agent architecture featuring a novel forward-weight scheduling mechanism and dynamic edge pruning strategy, enabling automatic isolation of non-cooperative agents and elastic graph restructuring under a fixed feedforward topology. A deep neural network models the time-varying communication graph, while sparse linear relations are leveraged to compute global target points, ensuring system stability and convergence. Results: Simulations demonstrate rapid convergence with ≤10% tracking error under full cooperation; under partial cooperation, performance degradation remains localized, confirming strong resilience, robustness, and scalability. The framework maintains stability despite adversarial or malfunctioning agents and scales effectively with agent count.

Technology Category

• Multiagent Systems: Teamwork
• Intelligent Robots: Multi-Robot Systems
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We present a resilient deep neural network (DNN) framework for decentralized transport and coverage using uncrewed aerial systems (UAS) operating in $mathbb{R}^n$. The proposed DNN-based mass-transport architecture constructs a layered inter-UAS communication graph from an initial formation, assigns time-varying communication weights through a forward scheduling mechanism that guides the team from the initial to the final configuration, and ensures stability and convergence of the resulting multi-agent transport dynamics. The framework is explicitly designed to remain robust in the presence of uncooperative agents that deviate from or refuse to follow the prescribed protocol. Our method preserves a fixed feed-forward topology but dynamically prunes edges to uncooperative agents, maintains convex, feedforward mentoring among cooperative agents, and computes global desired set points through a sparse linear relation consistent with leader references. The target set is abstracted by $N$ points that become final desired positions, enabling coverage-optimal transport while keeping computation low and guarantees intact. Extensive simulations demonstrate that, under full cooperation, all agents converge rapidly to the target zone with a 10% boundary margin and under partial cooperation with uncooperative agents, the system maintains high convergence among cooperative agents with performance degradation localized near the disruptions, evidencing graceful resilience and scalability. These results confirm that forward-weight scheduling, hierarchical mentor--mentee coordination, and on-the-fly DNN restructuring yield robust, provably stable UAS transport in realistic fault scenarios.

Problem

• Develops a resilient DNN framework for decentralized aerial transport and coverage using UAS.
• Ensures stability and convergence in multi-agent dynamics despite uncooperative agents.
• Achieves robust, scalable transport via dynamic communication and hierarchical coordination.

Innovation

• DNN-based mass-transport architecture with layered communication graphs
• Dynamic edge pruning for resilience against uncooperative agents
• Forward-weight scheduling and hierarchical coordination for stable convergence