Secure Control Systems for Autonomous Quadrotors against Cyber-Attacks

TL;DR

This study first designs an intelligent control system for autonomous quadrotors, then, it investigates the problems of optimal false data injection attack scheduling and countermeasure design for unmanned aerial vehicles.

Abstract

The problem of safety for robotic systems has been extensively studied. However, little attention has been given to security issues for three-dimensional systems, such as quadrotors. Malicious adversaries can compromise robot sensors and communication networks, causing incidents, achieving illegal objectives, or even injuring people. This study first designs an intelligent control system for autonomous quadrotors. Then, it investigates the problems of optimal false data injection attack scheduling and countermeasure design for unmanned aerial vehicles. Using a state-of-the-art deep learning-based approach, an optimal false data injection attack scheme is proposed to deteriorate a quadrotor's tracking performance with limited attack energy. Subsequently, an optimal tracking control strategy is learned to mitigate attacks and recover the quadrotor's tracking performance. We base our work on Agilicious, a state-of-the-art quadrotor recently deployed for autonomous settings. This paper is the first in the United Kingdom to deploy this quadrotor and implement reinforcement learning on its platform. Therefore, to promote easy reproducibility with minimal engineering overhead, we further provide (1) a comprehensive breakdown of this quadrotor, including software stacks and hardware alternatives; (2) a detailed reinforcement-learning framework to train autonomous controllers on Agilicious agents; and (3) a new open-source environment that builds upon PyFlyt for future reinforcement learning research on Agilicious platforms. Both simulated and real-world experiments are conducted to show the effectiveness of the proposed frameworks in section 5.2.

Figures (35)

• Figure 1: Quadrotor model with illustrated degrees of freedom. $F_i = k\cdot w^{2}_{i}$ is the force generated by motor $i$, and $mg$ is the force due to gravity. In a hovering state, $\sum_{i=1}^{4} F_i$ should balance $mg$.
• Figure 2: Simplified illustrations of Altitude (vertical), Yaw, Pitch and Roll motions. The front propeller is highlighted in green for convenience.
• Figure 3: Illustration of Euler Angles.
• Figure 4: Simplified interaction between an agent and its environment.
• Figure 5: Simplified illustration of an end-to-end deep reinforcement learning framework. Neural network architectures may vary according to the specific task.