This paper presents a new concept of supplementary arms for the collaborative task with a worker during a thin panel installation on the wall. Foldable robot arms for holding and installation (FRAHI) using scissor structure have been proposed as a new concept of the human-robot collaboration. The foldable and wearable FRAHI arm has been designed to influence cooperativeness and worker safety. FRAHI arms are developed and integrated with a worker's safety suit, and a soft and flexible waist belt is introduced for the arms and worker interface, comfortable to the user while working. The design principle of FRAHI is based on folding capability, gravity compensation for the cooperative thin-panel installation with workers. The experimental demonstration of a thin panel installation on the wall has been performed for the feasibility of the supplementary arm for worker assistance and cooperativeness in construction works.

Stabilization of the inverse model of the target system is a critical problem in a current disturbance observer (DOB) based control scheme. When the system is identified as a second order system by the recursive least square (RLS) algorithm, the minimum phase (MP) of the model is not guaranteed. This paper addresses a guaranteed minimum phase method of the identified second order model. Jury's test is conducted to check the stability. All-Pass-Filtering (APF) process are conducted for updating prior parameters of RLS to satisfy the minimum phase criteria. To verify the proposal, a single-wheel robot is identified as a second order model by the RLS method with guaranteed stability. Disturbance observer is designed based on the model. Balancing control experiments of a single-wheel robot are conducted.

Balancing control of a single-wheel mobile robot is achieved by the gyroscopic force induced by a gimbal system. There are two configurations of the gimbal system, horizontal and vertical configuration, depending upon how to generate the gyroscopic force. The horizontal configuration is a conventional one used in one-wheel robot systems. This paper presents the novel vertical configuration of the gimbal system that consists of a flywheel, a flywheel motor, and a tilt motor. The vertical configuration of the gimbal system has advantages of less power consumption but disadvantages of easy instability over the horizontal configuration. The typical characteristics of the vertical configuration are verified through experimental studies of balancing control tasks.

Gyroscopically manipulated lateral motion of a single-wheel based robot system has a parametric oscillation problem. In this paper, we analyze the stability regions for balancing the single-wheel robot system and then propose how to determine the offset range of its suppression controller. Since the roll motion is coupled with the pitch motion, the parametric oscillation problem should be analyzed. The dynamics model is parameterized as a Mathieu's equation from an inverted stick model. The stability region of a pitch oscillation parameter using the phase trajectory is analyzed from simulation. Simultaneously, its suppression control performance by determining the offset range is examined. Experimental studies are conducted to verify the analysis for the stable balancing control and to confirm the stability region based on the determined offset value.

In this paper, contact force control of a quadrotor system is presented. Due to an expensive cost of sensors for localization, a camera system is used to locate the quadrotor system. Using a maker on the top of a quadrotor system, heading direction can be justified. Based on the localization, the position control of a quadrotor system is performed in indoor environment. In addition, contact force from a human operator is applied to the quadrotor system so that the feasibility of applying force control to the flying system is tested. Experimental studies of interaction control between a quadrotor system and a human operator are presented to confirm the proposed force control performance.

This paper presents the implementation of a novel control method of using air for balancing the roll angle of a unicycle robot. The unicycle robot is designed and built. The roll angle of the unicycle robot is controlled by blowing air while the pitch angle is also controlled by DC motors. Successful balancing performances are demonstrated.

This article presents the hardware implementation of the radial basis function (RBF) neural network whose internal weights are updated in the real-time fashion by the back propagation algorithm. The floating-point processor is designed on a field programmable gate array (FPGA) chip to execute nonlinear functions required in the parallel processing calculation of the back-propagation algorithm. The performance of the on-line learning process of the RBF chip is compared numerically with the results of the RBF neural network learning program written in the MATLAB software under the same condition to check the feasibility of the implemented neural chip. The performance of the designed RBF neural chip is tested for the real-time pattern classification of the nonlinear XOR logic.

This article presents the implementation of position control of a mobile inverted pendulum(MIP) system by using the radial basis function network(RBF). The MIP has two wheels to move on the plane and to balance the pendulum. The MIP is known as a nonlinear system whose dynamics is non-holonomic. The goal is to control the MIP to maintain the balance of the pendulum while tracking a desired position of the cart. The reference compensation technique (RCT) scheme is used as a neural network control method to control the MIP. The back propagation learning algorithm for the RBF network is derived for on-line learning and control. The control algorithm has been embedded on a DSP 2812 board to achieve real-time control. Experimental results are conducted and show successful control performances of both balancing and tracking the position of the MIP.

In this paper, experimental studies of a decentralized neural network control scheme of the reference compensation technique applied to control a 2-degrees-of-freedom (2-DOF) inverted pendulum on an x - y plane are presented. Each axis is controlled by two separate neural network controllers to have a decoupled control structure. Neural network controllers are applied not only to balance the angle of pendulum, but also to control the position tracking of the cart. The decoupled control structure can compensate for uncertainties and cancel coupling effects. Especially, a circular trajectory tracking task is tested for position tracking control of the cart while maintaining the angle of the pendulum. Experimental result shows that position control of the inverted pendulum and cart is successful.

This paper presents the guidance and control of a mobile robot using a neural network. Location of a mobile robot is determined by the global laser sensor remotely located from the robot. A cascaded controller is used as a primary controller for position control of the robot, and a deviated position error is corrected by a neural network using the reference compensation algorithm. A car-like robot has been built for the test. Several control algorithms are investigated and tested. Among them, the cascaded controller with compensation by a neural network performs best

In this paper, a novel collision avoidance algorithm of a mobile robot is proposed. Virtual force field between a robot and an obstacle is formed and regulated to maintain a desired distance. To avoid obstacles on the path of a mobile robot, intelligent hybrid force control is used to regulate force field of an accurate distance between a robot and an obstacle. Since uncertainties from robot dynamics and obstacles degrade the performance of a collision avoidance task, neural network is used to compensate for uncertainties. Simulation studies of avoiding obstacles by maintaining a desired distance on the path of a wheeled mobile robot are conducted to confirm the proposed algorithm.

In this paper, a force control technique is applied to an autonomous aerial helicopter system. Applying a force control technique to a helicopter system is quite new since the helicopter system is mostly used for carrying humans or objects and navigating. For those operations, speed control is used most. For a specific task, however, position control for attitude control application is required as well. Here, the speed of a helicopter is controlled by the LQR method, and position is controlled by closing the other outer loop. After the position control is done, the force control is also applied. The adaptive impedance force control algorithm is applied and tested to control the desired force under unknown location and stiffness of the environment. The simple adaptive law minimizes the force tracking error. Simulation studies show that the proposed control algorithm works well.

In this paper, a collision avoidance algorithm using an impedance force control method for a mobile robot is proposed. A distance between a mobile robot and an obstacle is considered as a virtual force to be regulated by a well known impedance force control algorithm. The proposed collision avoidance algorithm is expected to react dynamically well when the obstacle is moving around. Simulation studies are conducted based on the dynamic model of a mobile robot. Simulation results confirm that the performance of the proposed force algorithm is better in maintaining the virtual distance to avoid moving obstacles compared with results of using a position control method.

In this paper, lateral force control of a mobile robot in contact with an object or environment is presented. Considering slip condition of wheels, the front wheel steered bicycle model of the mobile robot is derived. The explicit force control algorithm is applied to regulate contact force generated from the object which minimizes a force error between a desired force and an actual force. Performances of force tracking control for different stiffness of environment have been tested. Simulation results show that the proposed control algorithm works quite well to maintain desired contact force on the environment.

This paper presents the implementation of the crack tracking robot. The purpose of a crack tracking robot is to detect, track the crack on the pavement, and clean up the dirt for preparing for a sealing job. To detect an exact crack position, laser sensor and camera sensor are used. The explicit force control method is used to regulate a specified desired force by maintaining a constant contact force with the ground. Experimental studies of force tracking control are conducted under unknown environment stiffness and location. Force tracking results are excellent and the robot finds and tracks the crack quite well.

In this paper, we implement the intelligent controller hardware such as a neural network controller with an FPGA based general purpose controller and a DSP board to solve nonlinear control problems. The designed control hardware can perform a real time control of the backpropagation learning algorithm of a neural network. The basic PID control algorithms are implemented in an FPGA chip and a neural network controller is implemented in a DSP board. By using high capacity of an FPGA, the additional hardware such as an encoder counter and a PWM generator can be implemented in a single FPGA device. As a result, the controller is very cost effective. In order to show the performance of the controller, it was tested for controlling nonlinear systems such as an inverted pendulum.

In this paper, decentralized neural network control of the reference compensation technique is applied to control a 2-DOF inverted pendulum on an x-y plane. The cart with an inverted pendulum moves on the x-y plane by the x-y plane by the x-y table robot. Decentralized neural network control is applied not only to balance the angle of pendulum, but also to control the position tracking of the cart. In order to estimate velocity of the pendulum correctly, discrete filters are used. Especially, a circular trajectory tracking is tested for position tracking control of the cart while maintaining the angle of the pendulum. Experimental result shows that position control of the inverted pendulum and cart is successful.

In this paper, the neural network force control is presented. Under the framework of impedance control, neural network is used to compensate for all the uncertainties from robot dynamics and unknown environment. A modified simple impedance function is realized after the convergence of the neural network. Learning algorithms for the neural network to minimize the force error directly are designed. As a test-bed, the large X-Y table robot was implemented. Experimental results obtained show better force tracking when the neural network is used.

This paper presents the feasibility study of an adaptive impedance force control application to deburring/milling process. The proposed control regulates desired force on nonhomogeneous workpiece in regardless of unknown location and stiffness of the workpiece. The adaptive technique of minimizing the force error between the desired and the actual force is used to compensate for uncertainties in unknown workpiece. Effect of selecting the impedance damping gain with different workpiece stiffness on force tracking is analytically determined. Analyzing the stability of the proposed adaptive force control yields the bound of the adaptive gain for stability. Simulation studies of deburring/milling process show the excellent force tracking and confirm stability bound for stable force tracking.

A simple adaptive robust force tracking impedance control scheme that has the capability to track a specified desired force is proposed. The new impedance function is realized by the relationship between force error and velocity/acceleration error. The proposed control scheme uses the adaptive technique to compensate for uncertainties in environment location and stiffness. The robot dynamic model uncertainty is compensated by a robust position control algorithm based on time-delayed information. Simulation studies are shown to demonstrate the analysis of the stability and the convergence of the proposed scheme under uncertainties.

A force tracking nonlinear impedance control scheme using a neural network is introduced. Due to the nonlinear characteristics of the proposed control law, stability has been analyzed. The numerical bound of environment position uncertainty for ensuring robot contact with the environment and to perform desired force tracking has been found. Intensive simulation studies with a three link rotary robot manipulator tracking the surface with a desired force are carried out to confirm the boundary solutions of the proposed scheme under no knowledge of environment surface position and environment stiffness.

For the Cartesian position controlled robot it is required to have an accurate mapping from the Cartesian space to the joint space in order to command the desired joint trajectories to achieve desired movements in the Cartesian space. That requires the correct kinematic Jacobian information. Since the actual mapping from the Cartesian space to the joint space is obtained at the joint coordinate not at the actuator coordinate, uncertainty in the Jacobian can be present. In the paper two feasible neural network schemes are proposed to compensate for the kinematic Jacobian uncertainty. Uncertainty in the Jacobian can be compensated by identifying either the actuator Jacobian matrix off-line or the inverse of that in online fashion. The case study of a stencilling robot is examined.

In this paper, accurate position control of a stencilling robot manipulator is designed. The stencilling robot mounted on a truck is required to draw lines and characters in the Cartesian space. One of the goals of the stencilling robot design is to make the controller as simple as possible such that a simple PID controller can be used. Since the robot is huge and heavy, the inertia of the robot is expected to play a major role in the tracking performance. The conventional PID controller works within certain accuracy, but does not guarantee the accurate trading performance as desired. Here we propose a neural network control scheme for a computed-torque like controller for the stencilling robot. The stability of the closed loop system is analyzed based on the Lyapunov theory. Simulation studies with the stencilling robot are carried out to test the performances.

An impedance function is proposed to achieve accurate force tracking under the presence of uncertainties in robot dynamics and environment models. The new impedance function is formulated on the basis of PID control of the force tracking error which compensates for the unknown environment stiffness and position. The robot dynamics uncertainties are compensated by a simple time-delayed robust control algorithm. Stability and convergence of the control scheme are analyzed. Simulation studies with a three link rotary robot manipulator are shown. Furthermore, experimental results on a PUMA 560 arm are carried out to confirm the proposed impedance controller's performance.

In this paper, a robust robot force tracking impedance control scheme that uses a neural network as a compensator is proposed. The proposed neural compensator has the capability of making the robot track a specified desired force as well as of compensating for uncertainties in environment location and stiffness, and the uncertainties in robot dynamics. The neural compensator is trained separately for free space motion and contact space motion control using two different training signals. The proposed training signal for force control can be used regardless of the environment profile in order to achieve desired force tracking. Simulation studies with three link rotary robot manipulator are carried out to demonstrate the robustness of the proposed scheme under uncertainties in robot dynamics, environment position and environment stiffness. The results show that excellent force tracking is achieved by the neural network.

It is well known that computed torque robot control is subjected to performance degradation due to uncertainties in robot model, and application of neural network (NN) compensation techniques are promising. In this paper we examine the effectiveness of NN as a compensator for the complex problem of Cartesian space control. In particular we examine the differences in system performance when the same NN compensator is applied at different locations in the controller. It is found that using NN to modify the reference trajectory to compensate for model uncertainties is much more effective than the traditional approach of modifying joint torque/force. To facilitate the analysis, a new NN training signal is introduced. The study is extended to non-model based Cartesian control problem. Simulation results are also presented.

Performance of impedance controller for robot force tracking is affected by the uncertainties in the robot model and environment stiffness. The purpose of the paper is to improve the controller robustness by applying the neural network technique to compensate for the uncertainties in the robot model. A novel error signal is proposed for the neural network training. In addition, an algorithm is developed to determine the reference trajectory when the environment stiffness is unknown. Simulations show that highly robust position/force tracking by a three degrees-of-freedom robot can be achieved under large uncertainties.