Pneumatic artificial muscle (PAM) systems are a kind of tube-like actuators, which can act roughly like human muscles by performing contractile or extensional motions actuated by pressurized air. At present, it is still an open and challenging issue to tackle positioning and tracking control problems of PAM systems, due to inherent characteristics, e.g., unidirectional inputs, high nonlinearities, hysteresis, time-varying characteristics, etc. In this paper, a new adaptive control method is proposed for PAM systems, which achieves satisfactory tracking performance. To this end, an update law is designed to estimate unknown system parameters online. Also, some control input transforming operations are applied to address unidirectional constraints (i.e., control inputs of PAM systems should always be positive). As far as we know, compared with most of the existing control methods, this paper gives the first continuous control solution for PAM systems that can simultaneously compensate parametric uncertainties, reject external disturbances, and meet unidirectional constraints. Without linearizing the nonlinear dynamics, the closed-loop system is theoretically proven to be asymptotically stable at the equilibrium point with the stability analysis. In addition, a series of hardware experiments are implemented on a self-built hardware platform, indicating that the proposed method achieves satisfactory tracking control and exhibits robustness against parametric uncertainties and disturbances.

Adaptive Control for Pneumatic Artificial Muscle Systems With Parametric Uncertainties and Unidirectional Input Constraints

A bipedal walking robot is a kind of humanoid robot. It is suppose to mimics human behavior and designed to perform human specific tasks. Currently, humanoid robots are not capable to walk like human being. To perform the walking task, in the current work, human gait data of six different walking styles named brisk walk, normal walk, very slow walk, medium walk, jogging and fast walk is collected through our configured IMU sensor and mobile-based accelerometers device. To capture the pattern for six different walking styles, data is extracted for hip, knee, ankle, shank, thigh and foot. A total six classes of walking activities are explored for clinical examination. The accelerometer is placed at center of the human body of 15 male and 10 female subjects. In the experimental setup, we have done exploratory analysis over the different gait capturing techniques, different gait features and different gait classification techniques. For the classification purpose, three state of art techniques are used as artificial neural network, extreme learning machine and deep neural network learning based CNN mode. The model classification accuracy is obtained as 87.4%, 88% and 92%, respectively. Here, WISDM activity data set is also used for verification purpose.

Pattern identification of different human joints for different human walking styles using inertial measurement unit (IMU) sensor

This paper describes some important classes of two degrees of freedom of underactuated mechanical system and also surveys review of the recent state-of-the-art concerning the mathematical modeling of these systems, their classification, and all the control strategies (linear, nonlinear, and intelligent) that have been made so far (i.e., from the year 2000 to date) to control these systems. Future research and challenges concerning the improvement, the effectiveness, and robustness of the proposed controllers for underactuated mechanical systems are presented.

/pdf/a-review-on-the-control-of-second-order-underactuated-5ctxvxw2kk.pdf

A Review on the Control of Second Order Underactuated Mechanical Systems

Design of fuzzy system-fuzzy neural network-backstepping control for complex robot system

Parameters identification of Bouc–Wen hysteresis model for piezoelectric actuators using hybrid adaptive differential evolution and Jaya algorithm

A novel adaptive feed-forward-PID controller of a SCARA parallel robot using pneumatic artificial muscle actuator based on neural network and modified differential evolution algorithm

This paper proposes the novel adaptive neural network (ADNN) compliant force/position control algorithm applied to a highly nonlinear serial pneumatic artificial muscle (PAM) robot as to improve its compliant force/position output performance Based on the new adaptive neural ADNN model which is dynamically identified to adapt well all nonlinear features of the 2-axes serial PAM robot, a new hybrid adaptive neural ADNN-PID controller was initiatively implemented for compliant force/position controlling the serial PAM robot system used as an elbow and wrist rehabilitation robot which is subjected to not only the internal coupled-effects interactions but also the external end-effecter contact force variations (from 10[N] up to critical value 30[N]) The experiment results have proved the feasibility of the new control approach compared with the optimal PID control approach The novel proposed hybrid adaptive neural ADNN-PID compliant force/position controller successfully guides the upper limb of subject to follow the linear and circular trajectories under different variable end-effecter contact force levels

Cao Van Kien

Papers

Parameters identification of Bouc–Wen hysteresis model for piezoelectric actuators using hybrid adaptive differential evolution and Jaya algorithm

A novel adaptive feed-forward-PID controller of a SCARA parallel robot using pneumatic artificial muscle actuator based on neural network and modified differential evolution algorithm

Adaptive Neural Compliant Force-Position Control of Serial PAM Robot

Parameter identification using adaptive differential evolution algorithm applied to robust control of uncertain nonlinear systems

Adaptive gait generation for humanoid robot using evolutionary neural model optimized with modified differential evolution technique