Vision-Based Cooperative MAV-Capturing-MAV

TL;DR

This work tackles the challenge of intercepting a moving, potentially non-cooperative MAV by proposing a vision-based, cooperative MCM pipeline. It integrates onboard visual perception, distributed state estimation, and an MPC-SO(3) pursuit controller across multiple pursuer MAVs, with a real-time net-capture decision enabled by a simplified flying-envelope model. Key contributions include the cooperative STT-based target estimation, a surround formation to maximize observability, and a computationally efficient net-motion approximation that triggers capture in real time. Validated through simulations and real-world experiments, the system achieves a 64.7% capture success rate on a 4 m/s target, illustrating practical applicability for safe dynamic interception in aerial environments.

Abstract

MAV-capturing-MAV (MCM) is one of the few effective methods for physically countering misused or malicious MAVs.This paper presents a vision-based cooperative MCM system, where multiple pursuer MAVs equipped with onboard vision systems detect, localize, and pursue a target MAV. To enhance robustness, a distributed state estimation and control framework enables the pursuer MAVs to autonomously coordinate their actions. Pursuer trajectories are optimized using Model Predictive Control (MPC) and executed via a low-level SO(3) controller, ensuring smooth and stable pursuit. Once the capture conditions are satisfied, the pursuer MAVs automatically deploy a flying net to intercept the target. These capture conditions are determined based on the predicted motion of the net. To enable real-time decision-making, we propose a lightweight computational method to approximate the net motion, avoiding the prohibitive cost of solving the full net dynamics. The effectiveness of the proposed system is validated through simulations and real-world experiments. In real-world tests, our approach successfully captures a moving target traveling at 4 meters per second with an acceleration of 1 meter per square second, achieving a success rate of 64.7 percent.

Figures (6)

• Figure 1: The cooperative MCM system is tracking a moving target MAV. The three black MAVs denote the pursuers. The white MAV denotes the target.
• Figure 2: The cooperative MCM system configuration.
• Figure 3: The formation of three cooperative MAVs pursuing a target MAV.
• Figure 4: (a) The net structure; (b) The net dynamics capture zone; (c) The capture area of a flying net can be divided into two convex subspaces.
• Figure 5: The simulation results of 4 pursuer MAVs cooperative tracking a target with circular motion.