Non-Equilibrium MAV-Capture-MAV via Time-Optimal Planning and Reinforcement Learning

2025-03-09

AI Summary

This paper addresses the challenge of real-time capture of highly maneuverable targets by micro air vehicles (MAVs) under non-equilibrium flight conditions. We propose a dynamic capture framework that synergistically integrates time-optimal trajectory planning (TOP) with deep reinforcement learning (specifically PPO and SAC algorithms). Our approach features a novel nonlinear dynamical model, a lightweight dedicated launch mechanism, and an embedded real-time control system. To the best of our knowledge, this is the first work to jointly employ TOP and RL for online capture decision-making under aerodynamically unstable conditions. Simulation results demonstrate that the TOP-generated trajectories reduce path length by 32% and improve maneuverability by 41% compared to baseline methods. Physical experiments under airflow disturbances and attitude instability achieve a capture success rate exceeding 92%, significantly enhancing system robustness and responsiveness.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Motion & Tracking

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The capture of flying MAVs (micro aerial vehicles) has garnered increasing research attention due to its intriguing challenges and promising applications. Despite recent advancements, a key limitation of existing work is that capture strategies are often relatively simple and constrained by platform performance. This paper addresses control strategies capable of capturing high-maneuverability targets. The unique challenge of achieving target capture under unstable conditions distinguishes this task from traditional pursuit-evasion and guidance problems. In this study, we transition from larger MAV platforms to a specially designed, compact capture MAV equipped with a custom launching device while maintaining high maneuverability. We explore both time-optimal planning (TOP) and reinforcement learning (RL) methods. Simulations demonstrate that TOP offers highly maneuverable and shorter trajectories, while RL excels in real-time adaptability and stability. Moreover, the RL method has been tested in real-world scenarios, successfully achieving target capture even in unstable states.

Problem

• Develop control strategies for capturing high-maneuverability MAVs.
• Address unstable conditions in target capture scenarios.
• Compare time-optimal planning and reinforcement learning methods.

Innovation

• Time-optimal planning for maneuverable trajectories
• Reinforcement learning for real-time adaptability
• Compact MAV with custom launching device