Hierarchical Reinforcement Learning Based Self-balancing Algorithm for Two-wheeled Robots
نویسندگان
چکیده
منابع مشابه
Hierarchical Reinforcement Learning Based Self-balancing Algorithm for Two-wheeled Robots
Abstract: Self-balancing control is the basis for applications of two-wheeled robots. In order to improve the self-balancing of twowheeled robots, we propose a hierarchical reinforcement learning algorithm for controlling the balance of two-wheeled robots. After describing the subgoals of hierarchical reinforcement learning, we extract features for subgoals, define a feature value vector and it...
متن کاملTwo-wheeled self-balancing autonomous robot
Two-wheeled balancing robots based on inverted pendulum configuration which relies upon dynamic balancing systems for balancing and maneuvering. The idea of a mobile inverted pendulum robot has focused in recent years and has attracted interest from control system researchers worldwide, research on a two-wheel inverted pendulum, which commonly known as the self-balancing robot. In this, the DC ...
متن کاملTwo Wheeled Robot Self Balancing Control Research
According to movement balancing and position control problem of Self Balancing Two Wheeled Robot, a method based on H∞ Robust Control was proposed. We apply it onto the MIMO nonlinear model of robot, and simulated it in the MATLAB environment The simulation results shows that the robot can be balanced in fixed position well by this method, and also it have the ability to anti interference.
متن کاملImplementation of Two Wheeled Self Balancing Platform
---------------------------------------------------------------------***--------------------------------------------------------Abstract The Self balancing robot is based on the inverted pendulum concept. In this concept an inverted pendulum is positioned on a cart and the cart is allowed to move on the horizontal axis and the pendulum is required to stand upright . This type of case is that of...
متن کاملHierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Open Electrical & Electronic Engineering Journal
سال: 2016
ISSN: 1874-1290
DOI: 10.2174/1874129001610010069