scholarly journals Neural Network Based Contact Force Control Algorithm for Walking Robots

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 287
Author(s):  
Byeongjin Kim ◽  
Soohyun Kim
Keyword(s):  
Neural Network ◽  
Contact Force ◽  
Force Control ◽  
Control Algorithm ◽  
Position Control ◽  
Linear Quadratic Regulator ◽  
Walking Robots ◽  
Test Model ◽  
Linear Quadratic ◽  
Contact Force Control

Walking algorithms using push-off improve moving efficiency and disturbance rejection performance. However, the algorithm based on classical contact force control requires an exact model or a Force/Torque sensor. This paper proposes a novel contact force control algorithm based on neural networks. The proposed model is adapted to a linear quadratic regulator for position control and balance. The results demonstrate that this neural network-based model can accurately generate force and effectively reduce errors without requiring a sensor. The effectiveness of the algorithm is assessed with the realistic test model. Compared to the Jacobian-based calculation, our algorithm significantly improves the accuracy of the force control. One step simulation was used to analyze the robustness of the algorithm. In summary, this walking control algorithm generates a push-off force with precision and enables it to reject disturbance rapidly.

An improved linear quadratic regulator control method through convolutional neural network–based vibration identification

2020 ◽  
pp. 107754632093375
Author(s):  
Xinzheng Lu ◽  
Wenjie Liao ◽  
Wei Huang ◽  
Yongjia Xu ◽  
Xingyu Chen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Control Algorithm ◽  
Control Method ◽  
Wavelet Coefficient ◽  
Linear Quadratic Regulator ◽  
Optimal Parameters ◽  
Linear Quadratic ◽  
Negative Effects ◽  
Environmental Vibration

An efficient vibration control can reduce negative effects induced by environmental vibrations and thereby improve the performance of precision instruments and the qualities of manufacture. The performance of the widely used linear quadratic regulator control algorithm, a classical active control methodology, depends on the parameters of the control algorithm. Consequently, a set of fixed parameters cannot satisfy the demand for controlling various types of environmental vibrations. Therefore, this study proposes a vibration identification method based on a convolutional neural network. This method helps to optimize the linear quadratic regulator algorithm by selecting corresponding optimal parameters according to the identification results, thereby achieving the objective of optimal control subjected to various types of vibration inputs. Specifically, environmental vibration signals are collected, and the preliminary features of the vibrations (i.e. wavelet coefficient matrices or images) are adopted as input samples for the convolutional neural network. A genetic algorithm is used to optimize the parameters of the linear quadratic regulator algorithm for each type of vibration; subsequently, the trained convolutional neural network model with the best performance is used to identify the vibration and select the corresponding optimal parameters of the linear quadratic regulator algorithm under different types of vibration inputs. Case studies show that the performance of the improved linear quadratic regulator control method is significantly better than that of the conventional linear quadratic regulator algorithm with fixed parameters.

Research on Contact Force Control in Process of Aspheric Surface Polish

2012 ◽  
Vol 621 ◽  
pp. 216-222
Author(s):  
Jie Qiong Lin ◽  
Tong Huan Ran ◽  
Li Feng
Keyword(s):  
Contact Force ◽  
Force Control ◽  
Position Control ◽  
Control Method ◽  
Free Form ◽  
Force Output ◽  
Compliant Control ◽  
Free Form Surface ◽  
Polishing Tool ◽  
Contact Force Control

Contact force control is one of the key technologies of polishing aspheric optical parts, and keeping a stable polishing contact force on the basis of accurate position control is an important condition to obtain high quality aspheric. The paper bases on ideal surface, decouples the contact force that between polishing tool and workpiece in each direction of the drive shaft in process of polish. Then get output force of all sports shaft. Finally, realize the polishing contact force control that take the position as a control goals, and take constant force output as a constraints. Simulation results show that the control method can achieve constant contact force output in the processing of polishing free-form surface, which provide a new idea to research the compliant control of polishing free-form surface.

Robotic constant force grinding control based on grinding model and iterative algorithm

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Meng Xiao ◽  
Tie Zhang ◽  
Yanbiao Zou ◽  
Shouyan Chen
Keyword(s):  
Iterative Algorithm ◽  
Contact Force ◽  
Force Control ◽  
Control Algorithm ◽  
Position Control ◽  
Normal Force ◽  
Rbf Neural Network ◽  
Processing Stage ◽  
Content Type ◽  
The Impact

Purpose The purpose of this paper is to propose a robot constant grinding force control algorithm for the impact stage and processing stage of robotic grinding. Design/methodology/approach The robot constant grinding force control algorithm is based on a grinding model and iterative algorithm. During the impact stage, active disturbance rejection control is used to plan the robotic reference contact force, and the robot speed is adjusted according to the error between the robot’s real contact force and the robot’s reference contact force. In the processing stage, an RBF neural network is used to construct a model with the robot's position offset displacement and controlled output, and the increment of control parameters is estimated according to the RBF neural network model. The error of contact force and expected force converges gradually by iterating the control parameters online continuously. Findings The experimental results show that the normal force overshoot of the robot based on the grinding model and iterative algorithm is small, and the processing convergence speed is fast. The error between the normal force and the expected force is mostly within ±3 N. The normal force based on the force control algorithm is more stable than the normal force based on position control, and the surface roughness of the processed workpiece has also been improved, the Ra value compared with position control has been reduced by 24.2%. Originality/value As the proposed approach obtains a constant effect in the impact stage and processing stage of robot grinding and verified by the experiment, this approach can be used for robot grinding for improved machining accuracy.

General contact force control algorithm in double-sided incremental forming

CIRP Annals ◽  
2018 ◽  
Vol 67 (1) ◽  
pp. 381-384 ◽  
Author(s):  
Huaqing Ren ◽  
Fuhua Li ◽  
Newell Moser ◽  
Dohyun Leem ◽  
Tiemin Li ◽  
...  
Keyword(s):  
Contact Force ◽  
Force Control ◽  
Control Algorithm ◽  
Incremental Forming ◽  
Contact Force Control

Fuzzy neural network control algorithm for asymmetric building structure with active tuned mass damper

2020 ◽  
Vol 26 (21-22) ◽  
pp. 2037-2049
Author(s):  
Xiao Yan ◽  
Zhao-Dong Xu ◽  
Qing-Xuan Shi
Keyword(s):  
Neural Network ◽  
Control System ◽  
Fuzzy Neural Network ◽  
Linear Quadratic Regulator ◽  
Tuned Mass Damper ◽  
Linear Quadratic ◽  
Mass Damper ◽  
Fuzzy Neural ◽  
Neural Network Algorithm ◽  
Damper Control

Asymmetric structures experience torsional effects when subjected to seismic excitation. The resulting rotation will further aggravate the damage of the structure. A mathematical model is developed to study the translation and rotation response of the structure during seismic excitation. The motion equations of the structures which cover the translation and rotation are obtained by the theoretical derivations and calculations. Through the simulated computation, the translation and rotation response of the structure with the uncontrolled system, the tuned mass damper control system, and active tuned mass damper control system using linear quadratic regulator algorithm are compared to verify the effectiveness of the proposed active control system. In addition, the linear quadratic regulator and fuzzy neural network algorithm are used to the active tuned mass damper control system as a contrast group to study the response of the structure with different active control method. It can be concluded that the structure response has a significant reduction by using active tuned mass damper control system. Furthermore, it can be also found that fuzzy neural network algorithm can replace the linear quadratic regulator algorithm in an active control system. Because fuzzy neural network algorithm can control the process on an uncertain mathematical model, it has more potential in practical applications than the linear quadratic regulator control method.

Contact Stability and Contact Safety of a Magnetic Resonance Imaging-Guided Robotic Catheter Under Heart Surface Motion

2021 ◽  
Vol 143 (7) ◽  
Author(s):  
Ran Hao ◽  
E. Erdem Tuna ◽  
M. Cenk Çavuşoğlu
Keyword(s):  
Contact Force ◽  
Force Control ◽  
Motion Prediction ◽  
Resonance Imaging ◽  
Contact Stability ◽  
Heart Motion ◽  
Control Scheme ◽  
Control Schemes ◽  
Position Feedback ◽  
Contact Force Control

Abstract Contact force quality is one of the most critical factors for safe and effective lesion formation during catheter based atrial fibrillation ablation procedures. In this paper, the contact stability and contact safety of a novel magnetic resonance imaging (MRI)-actuated robotic cardiac ablation catheter subject to surface motion disturbances are studied. First, a quasi-static contact force optimization algorithm, which calculates the actuation needed to achieve a desired contact force at an instantaneous tissue surface configuration is introduced. This algorithm is then generalized using a least-squares formulation to optimize the contact stability and safety over a prediction horizon for a given estimated heart motion trajectory. Four contact force control schemes are proposed based on these algorithms. The first proposed force control scheme employs instantaneous heart position feedback. The second control scheme applies a constant actuation level using a quasi-periodic heart motion prediction. The third and the last contact force control schemes employ a generalized adaptive filter-based heart motion prediction, where the former uses the predicted instantaneous position feedback, and the latter is a receding horizon controller. The performance of the proposed control schemes is compared and evaluated in a simulation environment.

Comparison of Control Methods for Two-Link Planar Flexible Manipulator

2017 ◽  
Author(s):  
Joseph Bowkett ◽  
Rudranarayan Mukherjee
Keyword(s):  
Position Control ◽  
Linear Quadratic Regulator ◽  
Flexible Manipulator ◽  
Linear Quadratic ◽  
Large Space ◽  
Loop Control ◽  
Command Shaping ◽  
Aerospace Applications ◽  
Control Command ◽  
Low Stiffness

While the majority of terrestrial multi-link manipulators can be considered in a purely kinematic sense due to their high stiffness, the launch mass restrictions of aerospace applications such as in-orbit assembly of large space structures result in low stiffness links being employed, meaning dynamics can no longer be ignored. This paper seeks to investigate the suitability of several different open and closed loop control techniques for application to the problem of end effector position control with minimal vibration for a low stiffness space based manipulator. Simulations of a representative planar problem with two flexible links are used to measure performance and sensitivity to parameter variation of: model predictive control, command shaping, and command shaping with linear quadratic regulator (LQR) feedback. An experimental testbed is then used to validate simulation results for the recommended command shaped controller.

Sign in / Sign up

Export Citation Format

Share Document