Visual Servoing and Compliant Motion Control of a Continuum Robot

Kai-Tai Song,Han-Chih Tsai 제어로봇시스템학회 2018 제어로봇시스템학회 국제학술대회 논문집 Vol.2018 No.10

This paper presents a visual servoing and compliant motion control design of a continuum robot. Two endoscopic cameras were installed at the tip of the continuum robot to build a stereo camera system. The depth information is obtained by using semi-global block-matching (SGBM) algorithm. The visual servoing system proposed in this work includes the feature point extraction by using speeded-up robust features (SURF), followed by feature-point matching using nearest neighbor distance ratio (NNDR), and tracking of feature points by using mean shift algorithm. Through the pressure sensor installed around the circumference of the continuum robot, a compliant motion control design is proposed to make the robot to move in a constrained environment while executing the visual servoing task. Practical experiments show that the proposed method can effectively track a target and generate the adaptive motion when the robot encounters an obstacle during visual servoing.

Robust Facial Emotion Recognition Using a Temporal-Reinforced Approach

Kai-Tai Song,Chao-Yu Lin 제어로봇시스템학회 2014 제어로봇시스템학회 국제학술대회 논문집 Vol.2014 No.10

In this paper, a temporal-reinforced approach to enhancing emotion recognition from facial images is presented. Shape and texture models of facial images are computed by using active appearance model (AAM), from which facial feature points and geometrical feature values are extracted. The extracted features are used by relevance vector machine (RVM) to recognize emotional states. We propose a temporal analysis approach to recognizing likelihood of emotional categories, such that more subtle emotion, such as degree and ratio of basic emotional states can be obtained. Furthermore, a method is developed to map the recognition result to the arousal-valence plane (A-V Plane). Experimental results verify that the performance of emotion recognition is enhanced by the proposed method.

Sensorless Assistive Torque Design for a Lower Extremity Exoskeleton

Kai-Tai Song,Yun-Chih Liao,You-Lin Jian 제어로봇시스템학회 2014 제어로봇시스템학회 국제학술대회 논문집 Vol.2014 No.10

For improving mobility of the elderly, it is desirable to use a lower limb exoskeleton to enhance strength and endurance for their daily life activities. This paper presents a novel design of assist torque generation and compliant motion of a knee joint for an exoskeleton robot. Based on a sensorless approach, a method is suggested to estimate the external torque and generate the assistance torque of the attached DC motor. The developed lower limb exoskeleton joint provides assistive torque in order to comply with motion of the user. In comparison with existing lower limb exoskeletons, the proposed exoskeleton robot can execute various training programs by adjusting the assisting torque with less sensors and reduced hardware complexity. Experimental results on a knee exoskeleton validate the proposed method. Desirable assistive torque can be generated to be compliant with a swing motion.

Object Grasping of a Mobile Robot Using Image Features and Virtual Points

Kai-Tai Song,Hong-Tze Chen 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8

This paper presents a novel method of autonomous grasping design for a mobile manipulator, such that the robot can find and grasp a target object in a complex environment. Scale invariant feature transform (SIFT) algorithm is adopted to search and recognize features of the object to be grasped. Histogram-enhanced feature matching (HEFM) is developed to obtain depth estimate and reject unreliable feature points in order to improve the feature matching accuracy. The concept of virtual points is proposed to facilitate image-based visual servo controller design. Experimental results of autonomous object grasping validate the proposed method.

Design for Walking Rehabilitation of a Lower Limb Exoskeleton Based on Interaction Torque

Agus Lesmana,Kai-Tai Song 제어로봇시스템학회 2017 제어로봇시스템학회 국제학술대회 논문집 Vol.2017 No.10

In this research, an adaptive lower limb exoskeleton (AEXO) has been designed and constructed as a rehabilitation device. It is important during the rehabilitation that a user obtains assistance from the exoskeleton in an adaptive manner, as the user may improve his/her walking during rehabilitation. The assistance from the machine will be less or more according to the current situation of the user during the use of the exoskeleton. The question then arises as to how the exoskeleton can provide adaptive adjustment. It was decided that a tangible design was to measure the user status such as the user interaction force during walking. In this design, force sensors are installed on each link of exoskeleton to record the user walking effort during walking. By measuring this force, the control computer of the exoskeleton will understand for each cycle what the status of the user is and predict an adaptive torque according to measured force. In order to generate a suitable torque, the compliant motion control, which is a combination of impedance and admittance control is used. Walking experiments of a healthy person to wear the AEXO have been carried out in the lab. The first experiment verified the propose algorithm by using a predefined reference trajectory for the user and giving an adjustment to the reference trajectory based on the interaction torque. The second experiment verified that even without the predefined gait trajectory to the user, the exoskeleton can move in compliance to the user under various walking speeds. For the future development, the method will be expanded and tested for people who suffer from stroke or other walking impairment.

Hybrid Visual Servoing Design for a Continuum Robot under Visibility Constraint and Voice Commands

Chien-Yu Wu,Kai-Tai Song 제어로봇시스템학회 2016 제어로봇시스템학회 국제학술대회 논문집 Vol.2016 No.10

This paper presents a method to combine voice control and hybrid visual servoing for a continuum robot. In this design, the continuum robot autonomously tracks the element of interest and maintains its position in the safe region based on image information. A method of hybrid visual servoing is proposed to integrate 2D image-based visual servoing (IBVS) to ensure the elements of interests under visibility constraints and 3D position-based visual servoing (PBVS) to adjust the robot to a desired pose in the constraint region. The robotic camera thus provides stable image while tracking the element of interest. In this design, the user can move the continuum robot to acquire the desired view by voice commands. In voice control, the system can recognize connecting words to control the robot. All software modules are integrated using Robot Operating System (ROS) for controlling the continuum robot. Experimental results obtained from a prototype continuum robot verify the effectiveness of the proposed method.

Interactive Motion Planning for Autonomous Robotic Photo Taking

Pei-Chun Lu,Kai-Tai Song 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10

In this paper, a motion planning method is proposed for an autonomous photo-taking robot. The developed human-robot interactive motion planning and control system is based on face recognition and facial pose estimation of a target person. The target person’s location is estimated after combined with robot self-localization result. Then the goal position and orientation of the robot are determined for autonomous photo-taking of the specific person. An APP for mobile phones has been integrated to select the target person and transmit the command to the robot for photo taking. After receiving the command, the robot autonomously navigates to the goal location and shoots pictures of the target person. Experimental results show that the experimental mobile robot can recognize the specific person, regardless the person is stand alone or in a crowd. The robot completed two types of picture-taking tasks by using the proposed method.

User Identification Design by Fusion of Face Recognition and Speaker Recognition

Chao-Yu Lin,Kai-Tai Song,Yi-Wen Chen,Shuo-Cheng Chien,Sin-Horng Chen,Chen-Yu Chiang,Jyh-Her Yang,Yi-Chiao Wu,Tzu-Jui Liu 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10

Intelligent human-robot interface helps a mobile robot to extract external information and interact with a user. User identification information allows a robot to generate appropriate behaviors and make personalized human-robot interaction (PHRI) more natural and safe. Most of service robots move around in various application settings, and biometric features always change during relative movements. In this work, a fusion recognition system based on face and speaker classifiers is designed to achieve the user recognition in various environments. We propose a method to fuse face and speech recognition results based on the concept of confidence indices. Through the derived confidence indices, the system combines the two classifiers and gives improved recognition results. Experiments on a laboratory home service robot show that person recognition rates in 15 environmental situations all outperform those of using single modality.

Supervised Control for Robot-Assisted Surgery Using Augmented Reality

Tzu-Hsuan Ho,Kai-Tai Song 제어로봇시스템학회 2020 제어로봇시스템학회 국제학술대회 논문집 Vol.2020 No.10

In this paper, we propose an AR-based robotic system that can plan and execute a trajectory based on a 3D medical model and allow the surgeon to supervise the execution of surgical process. In order to achieve image-guided surgery, a hand-eye calibration procedure is developed by using AprilTag to obtain the transformation between the workspace coordinate and the robot coordinate, and perform the image navigation task of the surgical robot to complete a drilling task. A procedure of robot supervised control is proposed to assign or modify the robot trajectory based on AR visualization and 3D model. A specified AR marker is used to project virtual objects in the AR glasses. We developed a robot registration algorithm to match the AR virtual coordinate system and the workspace coordinate system, and convert the planned trajectory into robot trajectory. Experimental results on the lab-built robotic system show that a user can adjust the position and orientation of the insertion point on a bone model, and transmit the trajectory information to the robot for execution. The proposed visualization-based robot navigation method has the potential to enhance the safety of surgical operation.

Control Design for Robotic Human-Following and Obstacle Avoidance Using an RGB-D Camera

Cheng-An Yang,Kai-Tai Song 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10

The task of robotic human-following requires a mobile robot to detect and follow the selected target person and maintain an appropriate distance to the person. In practical applications, the robot must continuously estimate the target location considering unexpected obstacles to keep stable human-following control. This paper proposes to combine human-following control with obstacle avoidance, so that the robot can avoid obstacles while simultaneously follow the target person. In this design, obstacle as well as human features are obtained by using a RGB-D camera. A deep neural network(DNN) model works to detect and identify the user in the environment. An improved artificial potential field (APF) is applied to robot motion planning by integrating the target human position and obstacle information. Practical experiments on a mobile robot verified the proposed method. The robot can follow the user stably while avoiding obstacles in an indoor environment.