A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot

Based on Maslow’s hierarchy of needs theory, we have proposed a novel machine learning algorithm that combines factors of the environment and its own needs to make decisions for different states of an agent. This means it can be applied to the gait generation of a quadruped robot, which needs to mak...

Full description

Bibliographic Details
Main Authors: Hanzhong Zhang, Jibin Yin, Haoyang Wang
Format: Article
Language:English
Published: MDPI AG 2022-09-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/22/19/7302
_version_ 1797476957718315008
author Hanzhong Zhang
Jibin Yin
Haoyang Wang
author_facet Hanzhong Zhang
Jibin Yin
Haoyang Wang
author_sort Hanzhong Zhang
collection DOAJ
description Based on Maslow’s hierarchy of needs theory, we have proposed a novel machine learning algorithm that combines factors of the environment and its own needs to make decisions for different states of an agent. This means it can be applied to the gait generation of a quadruped robot, which needs to make demand decisions. To evaluate the design, we created an experimental task in order to compare the needs learning algorithm with a reinforcement learning algorithm, which was also derived from psychological motivation theory. It was found that the needs learning algorithm outperformed the reinforcement learning in tasks that involved making decisions between different levels of needs. Finally, we applied the needs learning algorithm to the problem of stable gait generation of quadruped robot, and it had achieved good results in simulation and real robot.
first_indexed 2024-03-09T21:11:10Z
format Article
id doaj.art-785299d2186e46318cb6a6b4b2cf6db9
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-09T21:11:10Z
publishDate 2022-09-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-785299d2186e46318cb6a6b4b2cf6db92023-11-23T21:46:55ZengMDPI AGSensors1424-82202022-09-012219730210.3390/s22197302A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped RobotHanzhong Zhang0Jibin Yin1Haoyang Wang2Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650221, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650221, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650221, ChinaBased on Maslow’s hierarchy of needs theory, we have proposed a novel machine learning algorithm that combines factors of the environment and its own needs to make decisions for different states of an agent. This means it can be applied to the gait generation of a quadruped robot, which needs to make demand decisions. To evaluate the design, we created an experimental task in order to compare the needs learning algorithm with a reinforcement learning algorithm, which was also derived from psychological motivation theory. It was found that the needs learning algorithm outperformed the reinforcement learning in tasks that involved making decisions between different levels of needs. Finally, we applied the needs learning algorithm to the problem of stable gait generation of quadruped robot, and it had achieved good results in simulation and real robot.https://www.mdpi.com/1424-8220/22/19/7302machine learningMaslow’s hierarchy of needsdemand decision
spellingShingle Hanzhong Zhang
Jibin Yin
Haoyang Wang
A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot
Sensors
machine learning
Maslow’s hierarchy of needs
demand decision
title A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot
title_full A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot
title_fullStr A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot
title_full_unstemmed A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot
title_short A Needs Learning Algorithm Applied to Stable Gait Generation of Quadruped Robot
title_sort needs learning algorithm applied to stable gait generation of quadruped robot
topic machine learning
Maslow’s hierarchy of needs
demand decision
url https://www.mdpi.com/1424-8220/22/19/7302
work_keys_str_mv AT hanzhongzhang aneedslearningalgorithmappliedtostablegaitgenerationofquadrupedrobot
AT jibinyin aneedslearningalgorithmappliedtostablegaitgenerationofquadrupedrobot
AT haoyangwang aneedslearningalgorithmappliedtostablegaitgenerationofquadrupedrobot
AT hanzhongzhang needslearningalgorithmappliedtostablegaitgenerationofquadrupedrobot
AT jibinyin needslearningalgorithmappliedtostablegaitgenerationofquadrupedrobot
AT haoyangwang needslearningalgorithmappliedtostablegaitgenerationofquadrupedrobot