Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter Control

TL;DR

A key objective is to analyze the effectiveness of the adaptive gain policy and compare it to the performance of a static gain control algorithm, where the Integral Squared Error and Integral Time Squared Error are used as metrics.

Abstract

The paper presents a technique using reinforcement learning (RL) to adapt the control gains of a quadcopter controller. Specifically, we employed Proximal Policy Optimization (PPO) to train a policy which adapts the gains of a cascaded feedback controller in-flight. The primary goal of this controller is to minimize tracking error while following a specified trajectory. The paper's key objective is to analyze the effectiveness of the adaptive gain policy and compare it to the performance of a static gain control algorithm, where the Integral Squared Error and Integral Time Squared Error are used as metrics. The results show that the adaptive gain scheme achieves over 40$\%$ decrease in tracking error as compared to the static gain controller.

Figures (5)

• Figure 2: Success rate monitored throughout the training process
• Figure 3: Values monitoring training progress
• Figure 4: Progression in performance throughout training
• Figure 5: Comparison of state trajectories
• Figure 6: Comparison of controller gains over time