Reinforcement Learning-based Quadrotor Control
نویسنده
چکیده
Analysis of quadrotor dynamics and control is conducted. A linearized quadrotor system is controlled using modern techniques. A MATLAB quadrotor control toolbox is presented for rapid visualization of system response. Waypoint-based trajectory control of a quadrotor is performed and appended to the MATLAB toolbox. Finally, an investigation of control using reinforcement learning is conducted.
منابع مشابه
Aggressive Optimal Control for Agile Flight with a Slung Load
A possible design method for learning motion control consists of using a model-based optimal control algorithm to initialize the policy of a sampling based reinforcement learning algorithm. In this paper, the initial control trajectory design is performed for a quadrotor with a cable-suspended load using the iterative LQG (iLQG) algorithm. The hybrid model of the quadrotor with the load is intr...
متن کاملAutonomous Quadrotor Control with Reinforcement Learning
Based on the same principles as a single-rotor helicopter, a quadrotor is a flying vehicle that is propelled by four horizontal blades surrounding a central chassis. Because of this vehicle’s symmetry and propulsion mechanism, a quadrotor is capable of simultaneously moving and steering by simple modulation of motor speeds [1]. This stability and relative simplicity makes quadrotors ideal for r...
متن کاملAdaptive Dynamic Programming Applied to a 6 DoF Quadrotor
This chapter discusses how the principles of Adaptive Dynamic Programming (ADP) can be applied to the control of a quadrotor helicopter platform flying in an uncontrolled environment and subjected to various disturbances and model uncertainties. ADP is based on reinforcement learning. The controller (actor) changes its control policy (action) based on stimuli received in response to its actions...
متن کاملA General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
The proven efficacy of learning-based control schemes strongly motivates their application to robotic systems operating in the physical world. However, guaranteeing correct operation during the learning process is currently an unresolved issue, which is of vital importance in safety-critical systems. We propose a general safety framework based on HamiltonJacobi reachability methods that can wor...
متن کاملSafe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret
Lifelong reinforcement learning provides a promising framework for developing versatile agents that can accumulate knowledge over a lifetime of experience and rapidly learn new tasks by building upon prior knowledge. However, current lifelong learning methods exhibit non-vanishing regret as the amount of experience increases, and include limitations that can lead to suboptimal or unsafe control...
متن کامل