Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown Environments

With the development of robotics, robots are playing an increasingly critical role in complex tasks such as flexible manufacturing, physical human–robot interaction, and intelligent assembly. These tasks place higher demands on the force control performance of robots, particularly in scenarios where...

Full description

Saved in:
Bibliographic Details
Main Authors: Yikun Zhang, Jianjun Yao, Chen Qian
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Actuators
Subjects:
Online Access:https://www.mdpi.com/2076-0825/14/7/323
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714633698443264
author Yikun Zhang
Jianjun Yao
Chen Qian
author_facet Yikun Zhang
Jianjun Yao
Chen Qian
author_sort Yikun Zhang
collection DOAJ
description With the development of robotics, robots are playing an increasingly critical role in complex tasks such as flexible manufacturing, physical human–robot interaction, and intelligent assembly. These tasks place higher demands on the force control performance of robots, particularly in scenarios where the environment is unknown, making constant force control challenging. This study first analyzes the robot and its interaction model with the environment, highlighting the limitations of traditional force control methods in addressing unknown environmental stiffness. Based on this analysis, a variable admittance control strategy is proposed using the deep deterministic policy gradient algorithm, enabling the online tuning of admittance parameters through reinforcement learning. Furthermore, this strategy is integrated with a quaternion-based nonlinear model predictive control scheme, ensuring coordination between pose tracking and constant-force control and enhancing overall control performances. The experimental results demonstrate that the proposed method improves constant force control accuracy and task execution stability, validating the feasibility of the proposed approach.
format Article
id doaj-art-3642caaab478494b80e39aa24f0d4513
institution DOAJ
issn 2076-0825
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Actuators
spelling doaj-art-3642caaab478494b80e39aa24f0d45132025-08-20T03:13:39ZengMDPI AGActuators2076-08252025-06-0114732310.3390/act14070323Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown EnvironmentsYikun Zhang0Jianjun Yao1Chen Qian2College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin 150001, ChinaWith the development of robotics, robots are playing an increasingly critical role in complex tasks such as flexible manufacturing, physical human–robot interaction, and intelligent assembly. These tasks place higher demands on the force control performance of robots, particularly in scenarios where the environment is unknown, making constant force control challenging. This study first analyzes the robot and its interaction model with the environment, highlighting the limitations of traditional force control methods in addressing unknown environmental stiffness. Based on this analysis, a variable admittance control strategy is proposed using the deep deterministic policy gradient algorithm, enabling the online tuning of admittance parameters through reinforcement learning. Furthermore, this strategy is integrated with a quaternion-based nonlinear model predictive control scheme, ensuring coordination between pose tracking and constant-force control and enhancing overall control performances. The experimental results demonstrate that the proposed method improves constant force control accuracy and task execution stability, validating the feasibility of the proposed approach.https://www.mdpi.com/2076-0825/14/7/323contact force trackingvariable admittance controldeterministic policy gradient algorithmnonlinear model predictive control
spellingShingle Yikun Zhang
Jianjun Yao
Chen Qian
Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown Environments
Actuators
contact force tracking
variable admittance control
deterministic policy gradient algorithm
nonlinear model predictive control
title Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown Environments
title_full Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown Environments
title_fullStr Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown Environments
title_full_unstemmed Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown Environments
title_short Learning-Based Variable Admittance Control Combined with NMPC for Contact Force Tracking in Unknown Environments
title_sort learning based variable admittance control combined with nmpc for contact force tracking in unknown environments
topic contact force tracking
variable admittance control
deterministic policy gradient algorithm
nonlinear model predictive control
url https://www.mdpi.com/2076-0825/14/7/323
work_keys_str_mv AT yikunzhang learningbasedvariableadmittancecontrolcombinedwithnmpcforcontactforcetrackinginunknownenvironments
AT jianjunyao learningbasedvariableadmittancecontrolcombinedwithnmpcforcontactforcetrackinginunknownenvironments
AT chenqian learningbasedvariableadmittancecontrolcombinedwithnmpcforcontactforcetrackinginunknownenvironments