Robotic Curved Surface Tracking with a Neural Network for Angle Identification and Constant Force Control based on Reinforcement Learning

2020 ◽  
Vol 21 (5) ◽  
pp. 869-882 ◽  
Author(s):  
Tie Zhang ◽  
Meng Xiao ◽  
Yan-biao Zou ◽  
Jia-dong Xiao ◽  
Shou-yan Chen
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Force Control ◽  
Curved Surface ◽  
Constant Force ◽  
Surface Tracking

scholarly journals Constant Force PID Control for Robotic Manipulator Based on Fuzzy Neural Network Algorithm

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Zhu Dachang ◽  
Du Baolin ◽  
Zhu Puchen ◽  
Chen Shouyan
Keyword(s):  
Neural Network ◽  
Trajectory Tracking ◽  
Force Control ◽  
Pid Controller ◽  
Fuzzy Neural Network ◽  
Robotic Manipulator ◽  
Constant Force ◽  
Network Algorithm ◽  
Fuzzy Neural ◽  
Neural Network Algorithm

The increased demand for robotic manipulator has driven the development of industrial manufacturing. In particular, the trajectory tracking and contact constant force control of the robotic manipulator for the working environment under contact condition has become popular because of its high precision and quality operation. However, the two factors are opposite, that is to say, to maintain constant force control, it is necessary to make limited adjustment to the trajectory. It is difficult for the traditional PID controller because of the complexity parameters and nonlinear characteristics. In order to overcome this issue, a PID controller based on fuzzy neural network algorithm is developed in this paper for tracking the trajectory and contact constant force simultaneously. Firstly, the kinetic and potential energy is calculated, and the Lagrange function is constructed for a two-link robotic manipulator. Furthermore, a precise dynamic model is built for analyzing. Secondly, fuzzy neural network algorithm is proposed, and two kinds of turning parameters are derived for trajectory tracking and contact constant force control. Finally, numerical simulation results are reported to demonstrate the effectiveness of the proposed method.

Location- and Person-Independent Activity Recognition with WiFi, Deep Neural Networks, and Reinforcement Learning

2021 ◽  
Vol 2 (1) ◽  
pp. 1-25
Author(s):  
Yongsen Ma ◽  
Sheheryar Arshad ◽  
Swetha Muniraju ◽  
Eric Torkildson ◽  
Enrico Rantala ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reinforcement Learning ◽  
Activity Recognition ◽  
Deep Neural Networks ◽  
State Machine ◽  
Recognition Algorithm ◽  
The State ◽  
Neural Architecture ◽  
Learning Agent

In recent years, Channel State Information (CSI) measured by WiFi is widely used for human activity recognition. In this article, we propose a deep learning design for location- and person-independent activity recognition with WiFi. The proposed design consists of three Deep Neural Networks (DNNs): a 2D Convolutional Neural Network (CNN) as the recognition algorithm, a 1D CNN as the state machine, and a reinforcement learning agent for neural architecture search. The recognition algorithm learns location- and person-independent features from different perspectives of CSI data. The state machine learns temporal dependency information from history classification results. The reinforcement learning agent optimizes the neural architecture of the recognition algorithm using a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The proposed design is evaluated in a lab environment with different WiFi device locations, antenna orientations, sitting/standing/walking locations/orientations, and multiple persons. The proposed design has 97% average accuracy when testing devices and persons are not seen during training. The proposed design is also evaluated by two public datasets with accuracy of 80% and 83%. The proposed design needs very little human efforts for ground truth labeling, feature engineering, signal processing, and tuning of learning parameters and hyperparameters.

scholarly journals Robust Quadrotor Control through Reinforcement Learning with Disturbance Compensation

2021 ◽  
Vol 11 (7) ◽  
pp. 3257
Author(s):  
Chen-Huan Pi ◽  
Wei-Yuan Ye ◽  
Stone Cheng
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Control Strategy ◽  
External Disturbance ◽  
Control Agent ◽  
Network Control ◽  
Outdoor Environment ◽  
Disturbance Compensation ◽  
Tracking Accuracy ◽  
Control Scheme

In this paper, a novel control strategy is presented for reinforcement learning with disturbance compensation to solve the problem of quadrotor positioning under external disturbance. The proposed control scheme applies a trained neural-network-based reinforcement learning agent to control the quadrotor, and its output is directly mapped to four actuators in an end-to-end manner. The proposed control scheme constructs a disturbance observer to estimate the external forces exerted on the three axes of the quadrotor, such as wind gusts in an outdoor environment. By introducing an interference compensator into the neural network control agent, the tracking accuracy and robustness were significantly increased in indoor and outdoor experiments. The experimental results indicate that the proposed control strategy is highly robust to external disturbances. In the experiments, compensation improved control accuracy and reduced positioning error by 75%. To the best of our knowledge, this study is the first to achieve quadrotor positioning control through low-level reinforcement learning by using a global positioning system in an outdoor environment.

scholarly journals An Improved PID Controller for the Compliant Constant-Force Actuator Based on BP Neural Network and Smith Predictor

2021 ◽  
Vol 11 (6) ◽  
pp. 2685
Author(s):  
Guojin Pei ◽  
Ming Yu ◽  
Yaohui Xu ◽  
Cui Ma ◽  
Houhu Lai ◽  
...  
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Pid Control ◽  
Pid Controller ◽  
Experimental Validation ◽  
Control Method ◽  
Smith Predictor ◽  
Constant Force ◽  
Matlab Simulation ◽  
Adjustment Time

A compliant constant-force actuator based on the cylinder is an important tool for the contact operation of robots. Due to the nonlinearity and time delay of the pneumatic system, the traditional proportional–integral–derivative (PID) method for constant force control does not work so well. In this paper, an improved PID control method combining a backpropagation (BP) neural network and the Smith predictor is proposed. Through MATLAB simulation and experimental validation, the results show that the proposed method can shorten the maximum overshoot and the adjustment time compared with traditional the PID method.

Force Control of a Hydraulic Actuator With a Neural Network Inverse Model

2021 ◽  
Vol 6 (2) ◽  
pp. 2814-2821
Author(s):  
Sung-Woo Kim ◽  
Buyoun Cho ◽  
Seunghoon Shin ◽  
Jun-Ho Oh ◽  
Jemin Hwangbo ◽  
...  
Keyword(s):  
Neural Network ◽  
Force Control ◽  
Inverse Model ◽  
Hydraulic Actuator

Research on sports aided teaching and training decision system oriented to deep convolutional neural network

2021 ◽  
pp. 1-15
Author(s):  
Qinyu Mei ◽  
Ming Li
Keyword(s):  
Neural Network ◽  
Decision Making ◽  
Control System ◽  
Convolutional Neural Network ◽  
Force Control ◽  
Control Experiment ◽  
Deep Convolutional Neural Network ◽  
Flexible Cable ◽  
Cable Force ◽  
And Training

Aiming at the construction of the decision-making system for sports-assisted teaching and training, this article first gives a deep convolutional neural network model for sports-assisted teaching and training decision-making. Subsequently, In order to meet the needs of athletes to assist in physical exercise, a squat training robot is built using a self-developed modular flexible cable drive unit, and its control system is designed to assist athletes in squatting training in sports. First, the human squat training mechanism is analyzed, and the overall structure of the robot is determined; second, the robot force servo control strategy is designed, including the flexible cable traction force planning link, the lateral force compensation link and the establishment of a single flexible cable passive force controller; In order to verify the effect of robot training, a single flexible cable force control experiment and a man-machine squat training experiment were carried out. In the single flexible cable force control experiment, the suppression effect of excess force reached more than 50%. In the squat experiment under 200 N, the standard deviation of the system loading force is 7.52 N, and the dynamic accuracy is above 90.2%. Experimental results show that the robot has a reasonable configuration, small footprint, stable control system, high loading accuracy, and can assist in squat training in physical education.

Sign in / Sign up

Export Citation Format

Share Document