Dual Agent Learning Based Aerial Trajectory Tracking

TL;DR

This paper introduces a dual-agent reinforcement learning framework for UAV trajectory tracking in cluttered environments, achieving real-time performance and robustness without heavy environmental memory reliance.

Contribution

It proposes a novel dual-agent RL architecture that improves UAV trajectory tracking and obstacle avoidance in complex environments, surpassing traditional methods.

Findings

Enhanced trajectory tracking accuracy in simulations and real-world tests.

Improved obstacle avoidance capabilities in dynamic scenarios.

Demonstrated scalability with curriculum learning in complex environments.

Abstract

This paper presents a novel reinforcement learning framework for trajectory tracking of unmanned aerial vehicles in cluttered environments using a dual-agent architecture. Traditional optimization methods for trajectory tracking face significant computational challenges and lack robustness in dynamic environments. Our approach employs deep reinforcement learning (RL) to overcome these limitations, leveraging 3D pointcloud data to perceive the environment without relying on memory-intensive obstacle representations like occupancy grids. The proposed system features two RL agents: one for predicting UAV velocities to follow a reference trajectory and another for managing collision avoidance in the presence of obstacles. This architecture ensures real-time performance and adaptability to uncertainties. We demonstrate the efficacy of our approach through simulated and real-world experiments, highlighting improvements over state-of-the-art RL and optimization-based methods. Additionally, a curriculum learning paradigm is employed to scale the algorithms to more complex environments, ensuring robust trajectory tracking and obstacle avoidance in both static and dynamic scenarios.