Litcius/Paper detail

A Deep Reinforcement Learning Approach for Path Following on a Quadrotor

Bartomeu Rubí, Bernardo Morcego, Ramón Pérez

202030 citationsDOIOpen Access PDF

Abstract

This paper proposes the Deep Deterministic Policy Grandient (DDPG) reinforcement learning algorithm to solve the path following problem in a quadrotor vehicle. This agent is implemented using a separated control and guidance structure with an autopilot tracking the attitude and velocity commands. The DDPG agent is implemented in python and it is trained and tested in the RotorS-Gazebo environment, a realistic multirotor simulator integrated in ROS. Performance is compared with Adaptive NLGL, a geometric algorithm that implements an equivalent control structure. Results show how the DDPG agent is able to outperform the Adaptive NLGL approach while reducing its complexity.

Topics & Concepts

MultirotorReinforcement learningAutopilotPython (programming language)Computer sciencePath (computing)Control theory (sociology)Control engineeringTracking (education)Attitude controlArtificial intelligenceSimulationControl (management)EngineeringAerospace engineeringPedagogyOperating systemProgramming languagePsychologyRobotic Path Planning AlgorithmsGuidance and Control SystemsReinforcement Learning in Robotics
A Deep Reinforcement Learning Approach for Path Following on a Quadrotor | Litcius