Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged Robots

Hydraulic legged robots, with advantages such as high load capacity and power density, have become a strategic driving force in advancing intelligent mobile platform technologies. However, their high energy consumption significantly limits long-duration endurance and efficient operational performanc...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinbo She, Xiang Feng, Bao Xu, Linyang Chen, Yuan Wang, Ning Liu, Wenpeng Zou, Guoliang Ma, Bin Yu, Kaixian Ba
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/10/6/403
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156278165274624
author Jinbo She
Xiang Feng
Bao Xu
Linyang Chen
Yuan Wang
Ning Liu
Wenpeng Zou
Guoliang Ma
Bin Yu
Kaixian Ba
author_facet Jinbo She
Xiang Feng
Bao Xu
Linyang Chen
Yuan Wang
Ning Liu
Wenpeng Zou
Guoliang Ma
Bin Yu
Kaixian Ba
author_sort Jinbo She
collection DOAJ
description Hydraulic legged robots, with advantages such as high load capacity and power density, have become a strategic driving force in advancing intelligent mobile platform technologies. However, their high energy consumption significantly limits long-duration endurance and efficient operational performance. In this paper, inspired by the excellent autonomous energy-efficient consciousness of mammals endowed by natural evolution, a bionic energy-efficient inverse kinematics method based on neural networks (EIKNN) is proposed for the energy-efficient motion planning of hydraulic legged robots with redundant degrees of freedom (RDOFs). Firstly, the dynamic programming (DP) algorithm is used to solve the optimal joint configuration with minimum energy loss as the goal, and the training data set is generated. Subsequently, the inverse kinematic model of the leg with minimum energy loss is learned based on neural network (NN) simulation of the autonomous energy-efficient consciousness endowed to mammals by natural evolution. Finally, extensive comparative experiments validate the effectiveness and superiority of the proposed method. This method not only significantly reduces energy dissipation in hydraulic legged robots but also lays a crucial foundation for advancing hydraulic legged robot technology toward high efficiency, environmental sustainability, and long-term developmental viability.
format Article
id doaj-art-58fbf853ee1549b78fbf63e847501e3e
institution OA Journals
issn 2313-7673
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-58fbf853ee1549b78fbf63e847501e3e2025-08-20T02:24:37ZengMDPI AGBiomimetics2313-76732025-06-0110640310.3390/biomimetics10060403Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged RobotsJinbo She0Xiang Feng1Bao Xu2Linyang Chen3Yuan Wang4Ning Liu5Wenpeng Zou6Guoliang Ma7Bin Yu8Kaixian Ba9School of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mechanical Engineering, Yanshan University, Qinhuangdao 066004, ChinaHydraulic legged robots, with advantages such as high load capacity and power density, have become a strategic driving force in advancing intelligent mobile platform technologies. However, their high energy consumption significantly limits long-duration endurance and efficient operational performance. In this paper, inspired by the excellent autonomous energy-efficient consciousness of mammals endowed by natural evolution, a bionic energy-efficient inverse kinematics method based on neural networks (EIKNN) is proposed for the energy-efficient motion planning of hydraulic legged robots with redundant degrees of freedom (RDOFs). Firstly, the dynamic programming (DP) algorithm is used to solve the optimal joint configuration with minimum energy loss as the goal, and the training data set is generated. Subsequently, the inverse kinematic model of the leg with minimum energy loss is learned based on neural network (NN) simulation of the autonomous energy-efficient consciousness endowed to mammals by natural evolution. Finally, extensive comparative experiments validate the effectiveness and superiority of the proposed method. This method not only significantly reduces energy dissipation in hydraulic legged robots but also lays a crucial foundation for advancing hydraulic legged robot technology toward high efficiency, environmental sustainability, and long-term developmental viability.https://www.mdpi.com/2313-7673/10/6/403hydraulic legged robotredundant degree of freedom (RDOF)energy-savinginverse kinematicsneural network (NN)
spellingShingle Jinbo She
Xiang Feng
Bao Xu
Linyang Chen
Yuan Wang
Ning Liu
Wenpeng Zou
Guoliang Ma
Bin Yu
Kaixian Ba
Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged Robots
Biomimetics
hydraulic legged robot
redundant degree of freedom (RDOF)
energy-saving
inverse kinematics
neural network (NN)
title Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged Robots
title_full Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged Robots
title_fullStr Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged Robots
title_full_unstemmed Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged Robots
title_short Bionic Energy-Efficient Inverse Kinematics Method Based on Neural Networks for the Legs of Hydraulic Legged Robots
title_sort bionic energy efficient inverse kinematics method based on neural networks for the legs of hydraulic legged robots
topic hydraulic legged robot
redundant degree of freedom (RDOF)
energy-saving
inverse kinematics
neural network (NN)
url https://www.mdpi.com/2313-7673/10/6/403
work_keys_str_mv AT jinboshe bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT xiangfeng bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT baoxu bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT linyangchen bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT yuanwang bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT ningliu bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT wenpengzou bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT guoliangma bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT binyu bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots
AT kaixianba bionicenergyefficientinversekinematicsmethodbasedonneuralnetworksforthelegsofhydraulicleggedrobots