Browsing by Author "Ko, Chun-Hsu"

Now showing 1 - 18 of 18

A novel teaching and training system for industrial applications based on augmented reality
(1970-01-01)
Young, Kuu-Young
;
Cheng, Shu-Ling
;
Ko, Chun-Hsu
;
Su, Yu-Hsuan
;
Liu, Qiao-Fei
Along with the high demand on automation, more industrial robot manipulators are being introduced to factories. In addition to their manufacturing, it is also very crucial on the deployment and training of the robots. It thus solicits the development of new types of manipulative devices and methods for tackling these tasks of high complexity. To achieve effective task execution, this paper proposes a novel AR-based teaching and training system, along with several assistive strategies. The technique of augmented reality (AR), which combines virtual objects with real scenes, is used for providing visual immersion. The assistive strategies, including that of collision-free path planning, occlusion effect removal, and visual guidance, are designed to ease the user from the load during the complicated teaching process. We conduct a series of experiments for performance evaluation. Questionnaires based on the system usability scale are also administered to obtain feedback from users.
Active and Passive Control of Walk-Assist Robot for Outdoor Guidance
(2013-06-01)
Ko, Chun-Hsu
;
Young, Kuu-Young
;
Huang, Yi-Che
;
Agrawal, Sunil Kumar
;
電機工程學系
In the currently aging society, walk-assist robots can play an important role in improving the activities of daily living of the elderly. In this paper, we propose a robot walking helper with both passive and active control modes for guidance. From the perspective of human safety, the passive mode adopts a braking control law on the wheels to differentially steer the vehicle. However, if the user walks uphill in the outdoor environment, external forces need to be supplied to the human-walker system. In this paper, we add an active mode to guide the user in situations where the passive control mode alone with user-applied forces is not adequate for guidance. The theory of differential flatness is used to plan the trajectory of control gains within the proposed scheme of the controller. Since the user input force and slope angle of the path are not known a priori, the theory of model predictive control is used to periodically compute the trajectory of these control gains. The simulation and experiment results show that the walk-assist robot, along with the structure of this proposed control scheme, can guide the user to a goal on a slope effectively.
Collision-Free Guidance for Passive Robot Walking Helper
(2012-01-01)
Huang, Yi-Che
;
Wu, Cheng-Je
;
Ko, Chun-Hsu
;
Young, Kuu-Young
;
電子工程學系及電子研究所
With the increase of aging population, robot walking helpers have been developed to assist the elderly in their daily life. Based on our previous work, a passive robot walking helper (named i-Go) equipped with a guidance strategy, in this paper, we further propose a navigation scheme for obstacle avoidance. The proposed scheme first locates the waypoints in the collision-free areas, and then guides the i-Go to reach the desired target with the specified orientation. Simulations and experiments are performed to verify the effectiveness of the proposed scheme. The results demonstrate that the scheme can guide the user to avoid the obstacles and successfully approach the target with the specified orientation.
Development of a 3D AR-Based Interface for Industrial Robot Manipulators
(2018-01-01)
Su, Yu-Hsuan
;
Chen, Chun-Yung
;
Cheng, Shu-Ling
;
Ko, Chun-Hsu
;
Young, Kuu-Young
Along with the progress in automation and Industry 4.0, the use of industrial robots becomes much more popular. Meanwhile, the conventional manipulative devices, such as teaching pendant and joystick, are not intuitive enough and very time-consuming for task teaching. In facing more complicated tasks these days, it then induces high cost and demands experts with proper training. This paper thus aims to develop an intuitive manipulatory interface for assistance in simplifying the teaching process. We propose a wireless 3D manipulation system based on augmented reality (AR) with the tablet PC as the platform. The system allows the user to govern the movement of a real robot in a 3D space via a virtual one generated through AR We also develop several intelligent tools to assist the manipulation, so that accurate and collision-free path can be generated for the robot to follow for task execution. In addition, the system can also be used for offline training, which yields salient training effect for the operator. Experiments are executed to demonstrate the effectiveness of the proposed system, and questionnaires conducted to investigate user's response.
Development of a Comfort-Based Motion Guidance System for a Robot Walking Helper
(1970-01-01)
Young, Kuu-young
;
Cheng, Shu-Ling
;
Ko, Chun-Hsu
;
Tsou, Hao-Wei
;
電子工程學系及電子研究所
In research on providing motion assistance for elderly care, the robot walking helper is considered to be able to maintain their vitality. For its practicality, one issue of interest is its feasible path planning for guidance. Inspired by the concept of including human factors for path planning previously proposed, in this paper, we develop such a motion guidance system for the robot walking helper. We first selected the human factors most vital for the elderly and also public via an Internet survey, and then developed a corresponding path planning algorithm and control strategy for its realization. Experiments are conducted to demonstrate the effectiveness of the proposed system. Key contributions of the paper lie on (a) one of the few studies that include human factors into path planning of the robot walking helper and (b) a more thorough consideration on comfort with both physical and psychological factors corresponding to elderly and public preference included.
Development of Intention Detection and Control System for Robot Walking Helper
(2016-01-01)
Huang, Zih-Lun
;
Jhuang, Cing-Hao
;
Ko, Chun-Hsu
;
Young, Kuu-Young
;
電機工程學系
In current aging society, robot walking helpers play an important role in improving the activities of daily living of the elders. In this paper, we develop an intention detection and passive control system for a robot walking helper. For safe manipulation, the robot can obtain user's walking intention by identifying the foot image and adopt a braking control law on the wheels to differentially steer the robot. Experiments are conducted to demonstrate the effectiveness of the proposed system.
Development of Upper-Limb Exoskeleton Simulator for Passive Rehabilitation
(2014)
Huang, Jian-Bin
;
Hong, Jing-Chen
;
Young, Kuu-Young
;
Ko, Chun-Hsu
;
電子工程學系及電子研究所
Due to the progress in robotics, exoskeleton has been applied in rehabilitation for those enduring damage in central nervous system, spinal cord, and others. In this kind if application, the main concern is the safety of the user, as he/she is closely connected to the exoskeleton. That means the developed exoskeleton needs be carefully evaluated in each aspect of the design. For this purpose, we develop a simulator for general types of upper-limb exoskeletons. To make it realistic, this simulator considers kinematics, dynamics, path planning, control, and also human factor. For demonstration, we apply it to our developed upper-limb exoskeleton, HAMEXO-I, which is designed for passive rehabilitation.
Effective Control for an Upper-Body Exoskeleton Robot Using ANFIS
(2016)
Huang, Jian-Bin
;
Young, Kuu-Young
;
Ko, Chun-Hsu
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
In responding to the coming of an aging society, the exoskeleton robot is of focus, which provides assistance for people with locomotive problems. As the exoskeleton robot is worn by the user, the interaction in between induces several severe challenges, including adequate controller design. To deal with the nonlinearity involved during motion governing, in this paper, we take advantage of the capability of the adaptive network-based fuzzy inference system (ANFIS), and propose an ANFIS-PID controller for the exoskeleton type of robot. Especially, we apply it to a 2-DOF upper-body exoskeleton robot, HAMEXO-I, developed in our laboratory. With the proposed controller, we intend to let HAMEXO-I adaptable for a wide range of users, and able to serve for simple daily activities. Experiments are performed to demonstrate its effectiveness.
Effective Maneuver for Passive Robot Walking Helper Based on User Intention
(2015-10-01)
Hsieh, Yi-Hung
;
Young, Kuu-Young
;
Ko, Chun-Hsu
;
電機工程學系
;
Department of Electrical and Computer Engineering
In response to an aging society, a robot walking helper has come up as a research focus. To be practical for use in daily lives for the elderly, it should be able to follow user intention during maneuver and provide motion assistance when demanded. As quite a number of guidance schemes have been proposed, the studies on maneuver are comparatively few. This paper thus proposes a maneuvering system for the passive type of robot walking helper based on user intention. The proposed system first recognizes motion intention from user-applied force and hip rotation, and then utilizes an assistive control strategy to generate proper braking torque for effective maneuver. Experiments in a real environment are conducted for demonstration.
Gait Analysis for a Human with a Robot Walking Helper
(2013)
Ko, Chun-Hsu
;
Young, Kuu-Young
;
Agrawal, Sunil K.
;
電機工程學系
;
Department of Electrical and Computer Engineering
With the growth of elderly population in our society, intelligent walking aids will play an important role in providing functional mobility to humans. In this paper, we propose a model to compute gait of humans walking with a robot helper. This model is aimed at designing a control system for the robot walking helper. The human model includes both the single support phase and impacts. Since a human will be walking along with the robot with its help, geometrical constraints and interaction forces are included. To achieve stable walking, zero moment point (ZMP) is utilized in the analysis and friction constraint is included within the reaction force from the ground. Simulations are performed to obtain optimal gait trajectories, the human applied joint torques, and the supporting forces from the robot walking helper.
Motion and Visual Control for an Upper-Limb Exoskeleton Robot via Learning
(2017-01-01)
Huang, Jian-Bin
;
Lin, I-Yu
;
Young, Kuu-Young
;
Ko, Chun-Hsu
;
電子工程學系及電子研究所
The arrival of an aging society brings up many challenges, including the demanding need in medical resources. In responding, the exoskeleton robot becomes one of the focuses, which provides assistance for people with locomotive problems. Motivated by it, our laboratory has developed a wearable upper-limb exoskeleton robot, named as HAMEXO. It is of 2 DOF and intended to provide motion assistance for users in their daily activities. To serve the purpose, HAMEXO is equipped with a visual system to detect objects in the environment, and also a motion controller for its governing. To deal with the coupling involved during the movements of the two joints and the need to adapt to various users, we adopted the learning approach for controller design. Experiments are performed to demonstrate its effectiveness.
Motion Guidance for a Passive Robot Walking Helper via User\'s Applied Hand Forces
(2016-12)
Hsieh, Yi-Hung
;
Huang, Yi-Che
;
Young, Kuu-Young
;
Ko, Chun-Hsu
;
Agrawal, Sunil K.
As the elderly population is rapidly growing in our society, robot walking helpers are receiving more attention these days. To be practical and safe for use in daily life, an important issue is whether these robot walking helpers can be effectively maneuvered and provide guidance to the users. These concerns become even more important for a passive robot walking helper, as it relies mainly on the user\'s applied forces to move. In this paper, we propose a motion guidance system for a passive robot walking helper. More specifically, we develop a system to identify user\'s intentions from applied grip forces. This system consists of a pair of force-sensing grips attached to the handles of the robot walking helper and a learning scheme for themapping between the measured grip forces and the driving force/torque imposed on the helper. The learning scheme, combined with an assistive strategy extended from our previous work, provides motion guidance to the elders during walking. The feasibility of the proposed system is demonstrated via a series of experiments involving motion assistance with i-Go, a passive robot walking helper developed in our laboratory.
Obstacle Avoidance for Passive Robot Walking Helper Based on Receding Horizon Control
(2016-01-01)
Hsieh, Yi-Hung
;
Ko, Chun-Hsu
;
Young, Kuu-Young
;
電機工程學系
;
Department of Electrical and Computer Engineering
With the arrival of aging society, the passive robot walking helper is introduced to provide safe mobility for the elders, which features continuous energy dissipation from the system and is thus intrinsically safe. As both static and moving obstacles may be present in daily activities, obstacle avoidance during guidance is very imperative for its practical use, which motivates us to propose such a scheme based on receding horizon control. With a desired goal to reach, the proposed scheme first plans a smooth path for the walking helper to follow. A novel strategy, combined with receding horizon control, is then proposed to avoid the incoming obstacles detected by the equipped sensing system. Experiments based on our developed passive robot walking helper, i-Go, are conducted in real environments to demonstrate the effectiveness of the proposed scheme.
Optimized Trajectory Planning for Mobile Robot in the Presence of Moving Obstacles
(2015)
Ko, Chun-Hsu
;
Young, Kuu-Young
;
Hsieh, Yi-Hung
;
電機學院
;
College of Electrical and Computer Engineering
Navigation and obstacle avoidance are essential for mobile robots. In the dynamic environment, the obstacles may move with varying velocities. It is thus crucial to develop an effective scheme for moving obstacle avoidance. Motivated by this, in this paper, we propose such a scheme based on parametric trajectory planning. With the conditions for collision avoidance formulated as the constraints, a feasible collision-free trajectory is then derived by solving an unconstrained optimization problem. The corresponding control torques for robot governing is calculated using the dynamic model and derived trajectory, with the information about the obstacle not known a priori. Simulations are performed to demonstrate the efficiency of the proposed approach.
Real-time Control for an Upper-limb Exoskeleton Robot using ANFIS
(2017-01-01)
Jiang, Shao-Fu
;
Young, Kuu-Young
;
Ko, Chun-Hsu
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
In this paper, we propose a control system based on the Electromyography (EMG) to govern a two-DOF upper-limb exoskeleton robot developed in our laboratory, named as HAMEXO. Achieving real-time control is the main concern for the proposed system. In addition, the adaptive neural fuzzy inference system (ANFIS) is adopted for tackling the coupling present between joints during motion, and also providing the adaptability for various users. Experiments are conducted to verify its feasibility.
Receding Horizon Passive Control for a Walk-Assist Robot
(2012)
Ko, Chun-Hsu
;
Young, Kuu-Young
;
Agrawal, Sunil K.
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
Passive walk-assist robots play an important role in providing safe mobility to the elderly. They use the brake torques on the wheels to assist the user walking and differentially steer the vehicle, while the user pushes the walker. It is important to appropriately select the brake torques in accordance with user-applied forces for controlling the robot. In this paper, a receding horizon passive control method is presented to calculate the brake torques so that the robot can perform point-to-point guidance. The control scheme first designs a smooth path to be followed by the robot. The terminal-state penalty is added to the cost function for path following, while the end point equality constraint is used to achieve the goal when the robot approaches the end point. The passivity of the system is guaranteed by adding the brake torque constraints into the formulated optimization problem. To be efficient, we look for a suboptimal solution of the optimization problem by using an analytical method. Simulation results show that the passive walk-assist robot, along with the proposed control scheme, can guide the user to a goal effectively.
Two smooth support vector machines for epsilon-insensitive regression
(2018-05-01)
Gu, Weizhe
;
Chen, Wei-Po
;
Ko, Chun-Hsu
;
Lee, Yuh-Jye
;
Chen, Jein-Shan
In this paper, we propose two new smooth support vector machines for -insensitive regression. According to these two smooth support vector machines, we construct two systems of smooth equations based on two novel families of smoothing functions, from which we seek the solution to -support vector regression (-SVR). More specifically, using the proposed smoothing functions, we employ the smoothing Newton method to solve the systems of smooth equations. The algorithm is shown to be globally and quadratically convergent without any additional conditions. Numerical comparisons among different values of parameter are also reported.
Walk-Assist Robot: A Novel Approach to Gain Selection of a Braking Controller Using Differential Flatness
(2013-11-01)
Ko, Chun-Hsu
;
Young, Kuu-Young
;
Huang, Yi-Che
;
Agrawal, Sunil K.
;
電機工程學系
With increasing populations of the elderly in our society, robot technology will play an important role in providing functional mobility to humans. From the perspective of human safety, it is desirable that controllers for walk-assist robots be dissipative, i.e., the energy is supplied from the human to the walker, while the controller modulates this energy. The simplest form of a dissipating controller is a brake, where resistive torques are applied to the wheels proportional to their speeds. The fundamental question that we ask in this brief is how to modulate these proportional gains over time for the two wheels so that the walker can perform point-to-point motions. The unique contribution of this brief is a novel way in which the theory of differential flatness is used to plan the trajectory of these braking gains. Since the user input forces are not known a priori, the trajectory of the braking gain is computed iteratively during the motion. Simulation and experimental results show that the walk-assist robot, along with the structure of this proposed control scheme, can guide the user to reach the goal.