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

TL;DR

This work tackles decentralized transport and coverage of UAS in the presence of uncooperative agents by introducing a fault-resilient DNN-based framework with a fixed-depth, layered inter-UAS topology and forward-weight scheduling. It distinguishesNominal versus Actual DNNs, enabling edge pruning and mentor–mentee reconfiguration to maintain convex containment and stability under disturbances. Theoretical guarantees are provided for stability and convergence, and simulations show rapid target-coverage transport with graceful degradation when some agents are uncooperative. The approach offers scalable, low-complexity resilience for large multi-UAS teams in realistic fault scenarios and suggests avenues for online detection and broader 3D environments.

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.

Figures (8)

• Figure 1: Agent initial formation with cooperative agents in 2D motion space.
• Figure 2: Feed-forward DNN structure based on the initial configuration of agents shown in Figure \ref{['InitialFormation_Case1']}.
• Figure 3: An initial formation of an UAS team with $N=100$ UASs in a $2$-D motion space. The uncooperative UASs take part in the DNN structure but do not communicate with other UASs.
• Figure 4: Feed forward DNN structure based on the initial configuration of UASs shown in Figure \ref{['InitialFormation_Case2']}.
• Figure 5: UAS team transitional configuration at t = 10 s.

Theorems & Definitions (13)

• Definition 1
• Definition 2
• Remark 1
• Remark 2
• Remark 3
• Remark 4
• Remark 5
• Definition 3
• Definition 4
• Theorem 1: Uniqueness of global desired set–points