• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.5
• /
• pp.480-488
• /
• 2006

Industrial and economical importance of CP(Cellular Phone) is growing rapidly. Combined with IT technology, CP is one of the most attractive technologies of today. However, unless we find a new breakthrough in the technology, its growth may slow down soon. RT(Robot Technology) is considered one of the most promising next generation technologies. Unlike the industrial robot of the past, today's robots require advanced features, such as soft computing, human-friendly interface, interaction technique, speech recognition object recognition, among many others. In this paper, we present a new technological concept named RCP (Robotic Cellular Phone) which integrates RT and CP in the vision of opening a combined advancement of CP, IT, and RT, RCP consists of 3 sub-modules. They are $RCP^{Mobility}$(RCP Mobility System), $RCP^{Interaction}$, and $RCP^{Integration}$. The main focus of this paper is on $RCP^{Mobility}$ which combines an autonomous navigation system of the RT mobility with CP. Through $RCP^{Mobility}$, we are able to provide CP with robotic functions such as auto-charging and real-world robotic entertainment. Ultimately, CP may become a robotic pet to the human beings. $RCP^{Mobility}$ consists of various controllers. Two of the main controllers are trajectory controller and self-localization controller. While the former is responsible for the wheel-based navigation of RCP, the latter provides localization information of the moving RCP With the coordinates acquired from RFID-based self-localization controller, trajectory controller refines RCP's movement to achieve better navigation. In this paper, a prototype of $RCP^{Mobility}$ is presented. We describe overall structure of the system and provide experimental results on the RCP navigation.

• Archives of design research
• /
• v.20 no.3 s.71
• /
• pp.97-106
• /
• 2007

This study examines whether the reinforcement theory could be effectively applied to teaching assistant robots between a robot and a student in the same way as it is applied to teaching methods between a teacher and a student. Participants interacted with a teaching assistant robot in a 3 (types of robots: positive reinforcement vs. negative reinforcement vs. both reinforcements) by 2 (types of participants: honor students vs. backward students), within-subject experiment. Three different types of robots, such as 'Ching-chan-ee' which gives 'positive reinforcement', 'Um-bul-ee' which gives 'negative reinforcement', and 'Sang-bul-ee' which gives both 'positive and negative reinforcement' were designed based on the reinforcement theory and the token reinforcement system. Subjective impressions and preferences were measured according to the types of robots and the types of participants. Participants preferred the positive reinforcement robot most, and the negative reinforcement robot least. Regarding the number of stimulus, in case of the negative reinforcement robot for honor students, the less the stimulus is, the more positive the impressions toward the robot are. The findings demonstrate that the reinforcement interaction is important and effective factor which determines children's preferences and impressions for teaching assistant robots. The results of this study can be implicated as an effective guideline to interaction design of teaching assistant robots.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.6C
• /
• pp.593-603
• /
• 2009

In this paper, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with an active stereo camera. The proposed system consists of three modules: detection, tracking and silhouette extraction. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap is estimated in advance and then this was effectively incorporated into the graph cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data and it was shown to detect and track multiple people very well and also produce high quality silhouettes. The proposed system can assist in gesture and gait recognition in field of Human-Robot Interaction (HRI).

• The Journal of Korea Robotics Society
• /
• v.3 no.2
• /
• pp.154-163
• /
• 2008

This paper presents the concept for the development of a pet-type robot with an emotion engine. The pet-type robot named KOBIE (KOala roBot with Intelligent Emotion) is able to interact with a person through touch. KOBIE is equipped with tactile sensors on the body for interaction with a person through recognition of his/her touching behaviors such as "Stroke","Tickle","Hit". We have covered KOBIE with synthetic fur fabric in order to can make him/her feel affection as well. KOBIE is able to also express an emotional status that varies according to the circumstances under which it is presented. The emotion engine of KOBIE's emotion expression system generates an emotional status in an emotion vector space which is associated with a predefined needs and mood models. In order to examine the feasibility of our emotion expression system, we verified a changing emotional status in our emotion vector space by a touching behavior. We specially examined the reaction of children who have interacted with three kind of pet-type robots: KOBIE, PARO, AIBO for roughly 10 minutes to investigate the children's preference for pet-type robots.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5496-5521
• /
• 2018

Object detection and tracking is the basic capability of mobile robots to achieve natural human-robot interaction. In this paper, an object tracking system of mobile robot is designed and validated using improved multiple instance learning algorithm. The improved multiple instance learning algorithm which prevents model drift significantly. Secondly, in order to improve the capability of classifiers, an active sample selection strategy is proposed by optimizing a bag Fisher information function instead of the bag likelihood function, which dynamically chooses most discriminative samples for classifier training. Furthermore, we integrate the co-training criterion into algorithm to update the appearance model accurately and avoid error accumulation. Finally, we evaluate our system on challenging sequences and an indoor environment in a laboratory. And the experiment results demonstrate that the proposed methods can stably and robustly track moving object.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.2
• /
• pp.223-231
• /
• 2014

Humanoid robot is the most suitable robot platform for effective human interaction and various intelligent services. The present work addresses development of real time wireless control application of humanoid robot's forward and backward walks, and turning in walking. For convenience of human users, the application is developed on Android OS (Operating System) working on his or her smartphone. To this end, theoretic background on various-directional biped walking is proposed based on joint trajectories for forward walking, which have been shaped with a global optimization method. In this paper, backward walking is scheduled by interchange of angles and angular velocities and additional change of signs in angular velocities at all the via-points connecting cubic polynomial trajectories. Turning direction in walking is also implemented by activating the transversal hip joint initially located in the support leg in two stages. After validation of the proposed walking schemes with Matlab simulator, a smartphone application for the omnidirectional walking has been developed to control a humanoid robot platform named DARwIn-OP interconnected via Wi-Fi. Experiment result of the present wireless control of a humanoid robot with smartphone is successful, and the application will be released in application market near future.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.8
• /
• pp.870-877
• /
• 2013

There has been much recent research interest in developing numerous kinds of human-machine interface. This field currently requires more accurate and reliable sensing systems to detect the intended human motion. Most conventional human-machine interface use electromyography (EMG) sensors to detect the intended motion. However, EMG sensors have a number of disadvantages and, as a consequence, the human-machine interface is difficult to use. This study describes a muscle volume sensor (MVS) that has been developed to measure variation in the outline of a muscle, for use as a human-machine interface. We developed an algorithm to calibrate the system, and the feasibility of using MVS for detecting muscular activity was demonstrated experimentally. We evaluated the performance of the MVS via isotonic contraction using the KIN-COM$^{(R)}$ equipment at torques of 5, 10, and 15 Nm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.565-570
• /
• 2013

The mirror neuron regions which are distributed in cortical area handled a functionality of intention recognition on the basis of imitative learning of an observed action which is acquired from visual-information of a goal-directed action. In this paper an automated intention recognition system is proposed by applying computational model of mirror neuron system to the human-robot interaction system. The computational model of mirror neuron system is designed by using dynamic neural networks which have model input which includes sequential feature vector set from the behaviors from the target object and actor and produce results as a form of motor data which can be used to perform the corresponding intentional action through the imitative learning and estimation procedures of the proposed computational model. The intention recognition framework is designed by a system which has a model input from KINECT sensor and has a model output by calculating the corresponding motor data within a virtual robot simulation environment on the basis of intention-related scenario with the limited experimental space and specified target object.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.79-85
• /
• 2021

Soft fluidic actuators (SFAs) are widely utilized in various areas such as wearable systems due to the inherent compliance which allows safe and flexible interaction. However, SFA-driven systems generally require a large pump, multiple valves and tubes, which hinders to develop a miniaturized system with small range of motion. Thus, a highly integrated soft actuator needs to be developed for implementing a compact SFA-driven system. In this study, we propose an electro-hydraulic soft zipping actuator that can be used as a miniature pump. This actuator exerts tactile force as a dielectric liquid contained inside the actuator pressurized its deformable part. In addition, the proposed actuator can estimate the internal dielectric liquid thickness by using its self-sensing function. Besides, the electrical characteristics and driving performance of the proposed system were verified through experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.300-300
• /
• 2000

Reduced life-cycle and scale of electronic products make the conventional automated manufacturing system difficult to keep on competitiveness in these days. Reduced life-cycle requires an agile adaptation of manufacturing to new products and reduced scale requires enhanced precision as well as high speed. In this research, We propose a new concept called as "One-Cell Minifactory" in which various processes are combined to produce final modules or products and human interaction can be combined easily. We hope the proposed concept can guide new developments of automated manufacturing in electronics, optics and bio-engineering.