Motion Control in Multi-Rotor Aerial Robots Using Deep Reinforcement Learning

TL;DR

This paper presents a deep reinforcement learning framework, specifically TD3, for robust, real-time motion control of multi-rotor drones in additive manufacturing, outperforming traditional PID controllers under varying payloads.

Contribution

It introduces a DRL-based control policy for drones in AM tasks, demonstrating improved stability and adaptability over traditional methods in complex, dynamic environments.

Findings

TD3 outperforms DDPG in stability and accuracy.

The DRL framework adapts to payload variations.

Enhanced autonomous control for drone-based additive manufacturing.

Abstract

This paper investigates the application of Deep Reinforcement (DRL) Learning to address motion control challenges in drones for additive manufacturing (AM). Drone-based additive manufacturing promises flexible and autonomous material deposition in large-scale or hazardous environments. However, achieving robust real-time control of a multi-rotor aerial robot under varying payloads and potential disturbances remains challenging. Traditional controllers like PID often require frequent parameter re-tuning, limiting their applicability in dynamic scenarios. We propose a DRL framework that learns adaptable control policies for multi-rotor drones performing waypoint navigation in AM tasks. We compare Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3) within a curriculum learning scheme designed to handle increasing complexity. Our experiments show TD3 consistently balances training stability, accuracy, and success, particularly when mass variability is introduced. These findings provide a scalable path toward robust, autonomous drone control in additive manufacturing.