:: ICCAS 2015 ::

FB04		Human-Robot Interaction and Visual Servoing
Time : 13:30~15:00 Room : 104		Chair : Kai-Tai Song (National Chiao Tung University, )



13:30~13:45	FB04-1

Sensitivity Analysis of Detection and Discrimination Transparency for Haptic Teleoperation
Sangsoo Park, Riaz Uddin, Jeha Ryu(Gwangju Institute of Science and Technology, Korea, Republic of )

This paper presents a sensitivity analysis for detection and discrimination transparency of perceived impedance for haptic teleoperation system considering a surgical tool flexibility. Based on the analysis, dominant parameters that affect transparency are figured out.



13:45~14:00	FB04-2

A Psychological Framework to Objectively Evaluate Socially Capable Robots for Interactive Tutoring Systems
Barnabas Takacs, Klara Csizinszky, Lajos Simon(Semmelweis Medical University, Hungary), Daniele Mazzei(University of Pisa, Italy)

A novel evaluation methodology to evaluate socially capable robots is introduced using psychometrically validated measures. We create a digital computer generated face model designed to replicate the facial expression space of the robot and use this model to render test sequences, which are in turn analyzed with independent facial metrics. We compared 3 different facial modelings techniques to approximate our robot's face and achieved 98.86% accuracy in replicating its appearance. Our methodology is a first step towards objectively assessing the believability of commercially available robots.



14:00~14:15	FB04-3

Design and development of the sorting system based on robot
Tuong Phuoc Tho, Nguyen Truong Thinh(Ho Chi Minh City University of Technology and Educational, Viet Nam)

Sorting is one of the important tasks in production line. Using Robot to increase productivity in automatic sorting system interests a large of researchers. In this paper, we recommend a sorting system based on Robot that can identify the position and properties of objects. The sorting system uses the camera placed on the top of the mechanical conveyor belt. With the images captured by the camera, the software will perform the algorithms to identify the location and characteristics of the object (ei. tomatoes), the data of objects is used by pick and place process that synchronize with control



14:15~14:30	FB04-4

CAD-Based Pose Estimation for Random Bin-Picking of Multiple Objects Using a RGB-D Camera
Cheng-Hei Wu, Sin-Yi Jiang, Kai-Tai Song(National Chiao Tung University, Taiwan)

In this paper, we propose a CAD-based 6-DOF pose estimation design for random bin-picking of multiple different objects using a Kinect RGB-D sensor. 3D CAD models of objects are constructed via a virtual camera, which generates a point cloud database for object recognition and pose estimation. A voxel grid filter is suggested to reduce the number of 3D point cloud of objects for reducing computing time of pose estimation. A voting-scheme method was adopted for the 6-DOF pose estimation a swell as object recognition of different type objects in the bin. Furthermore, an outlier filter is designe



14:30~14:45	FB04-5

Kinect Camera Sensor-based Object Tracking and Following of Four wheel Independent Steering Automatic Guided Vehicle Using Kalman Filter
Amruta Vinod Gulalkari(Pukyong National University, Korea, Republic of ), Dongbo Sheng, Pandu Sandi Pratama, Hak Kyeong Kim, Gi Sig Byun, Sang Bong Kim(Pukyong National Univesity, Korea, Republic of )

This paper presents a Kinect camera sensor-based object tracking and following system for the four wheel independent steering automatic guided vehicle (4WIS-AGV) using Kalman filter and backstepping control method.Firstly, a blue colored object is detected by the Kinect camera sensor using a color-based object detection method. Secondly, a Kalman filter is used to estimate the global position and velocity coordinates of the detected moving object. Thirdly, a backstepping control method using Lyapunov function is adopted for the 4WIS-AGV to perform the object following task.