Using Reinforcement Learning to Achieve Two Wheeled Self Balancing Control
碩士 === 國立雲林科技大學 === 資訊工程系 === 104 === The non-linear, unstable system of the two-wheeled self-balancing robot has made it a popular research topic in the past decade. This paper presents an adaptive balance control method using reinforcement learning to give the robot the ability to adapt to environ...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/41975132362114541357 |
Summary: | 碩士 === 國立雲林科技大學 === 資訊工程系 === 104 === The non-linear, unstable system of the two-wheeled self-balancing robot has made it a popular research topic in the past decade. This paper presents an adaptive balance control method using reinforcement learning to give the robot the ability to adapt to environmental changes. The Q-Learning method in reinforcement learning was used, and an experimental model robot equipped with a set of angular velocity detection and inclination detection sensors was designed to verify this method. The experimental results demonstrate that this method can allow the two-wheeled robot to maintain good balance.
|
---|