The growing demand for robots to operate effectively in diverse environments necessitates the need for robust real-time anomaly detection techniques during robotic operations. However, deep learning-based models in robotics face significant challenges due to limited training data and highly noisy signal features. In this paper, we present Sparse Masked Autoregressive Flow-based Adversarial AutoEncoder model to address these problems. This approach integrates Masked Autoregressive Flow model into Adversarial AutoEncoders to construct a flexible latent space and utilizes Sparse autoencoder to efficiently focus on important features, even in scenarios with limited feature space. Our experiments demonstrate that the proposed model achieves a 4.96% to 9.75% higher area under the receiver operating characteristic curve for pick-and-place robotic operations with randomly placed cans, compared to existing state-of-the-art methods. Notably, it showed up to 19.67% better performance in scenarios involving collisions with lightweight objects. Additionally, unlike the existing state-of-the-art model, our model performs inferences within 1 millisecond, ensuring real-time anomaly detection. These capabilities make our model highly applicable to machine learning-based robotic safety systems in dynamic environments. The code is available at https://github.com/twkang43/sparse-maf-aae .

EtherCAT has been widely adopted in industrial automation and motion control owing to its real-time performance and flexible topology. However, an EtherCAT network with devices from different vendors requires extensive software modification which eventually increases development costs and effort. To address this issue, this paper presents a real-time control architecture focusing on a software-defined approach to easily reconfigure EtherCAT devices with minimal user intervention. This is achieved by simplifying the integration of EtherCAT slaves while exposing required parameters in a configuration interface through an API based on open-source EtherCAT master. We also provide a real-time variation of the POSIX library for a hard real-time multi-tasking environment considering task synchronization. Moreover, the real-time publish-subscribe protocol is also utilized to ensure seamless communication with devices outside of the EtherCAT network. To validate feasibility, practical example involving control of multi-axis robots and real-time performance analysis has been conducted.

The COVID-19 pandemic has caused a global public health crisis, leading to increased costs for operating essential quarantine facilities and risks of infection for medical staff. To address these issues, we have developed a non-contact delivery robot, UTD-pro, that can deliver food and supplies to patients in an isolated residential treatment center. In case of emergency situations such as communication failure with the control system or malfunction of specific modules, the noncontact delivery robot should be able to perform commands robustly or return home. Otherwise, as before, medical staffs may have to enter the high-risk environment again. In this paper, we propose a flexible and robust remote control system and a robot task management system that enables the robot to execute commands correctly. Our robot task manager allows for autonomous task execution with a single command from the remote control system. Each robot task operates independently, allowing users to change task plans flexibly during robot operation. The sensor data communication and task execution communication processes are also independent, preventing any issue in one process from affecting the other. By applying our system to the robot, we conducted a long-term delivery experiment for a total of 7.723km for 79 days, and achieved 125 successes out of 149 trials. This experiment proves that our system can lead to stable delivery processes and contribute to the high reliability of the control system and the robot task manager.

In a human-robot interaction (HRI) device that performs physical collaboration operations in constant contact with the user, admittance control and impedance control are generally used. Since the two controllers exhibit opposite performances depending on the stiffness condition, controllers capable of dealing with various magnitudes of stiffness are required. As such, this study proposes hybrid control that adjusts the control distribution ratios of admittance control and impedance control based on the operating frequency analysis to react to the user intention and various stiffness conditions in real time. The proposed controller algorithm exhibited lower overshoot than impedance control in the step input response simulation, faster response speed compared to admittance control in the response simulation for 0-5 Hz input frequencies, and the smallest vibration magnitude and number of vibrations in the case of a virtual wall collision, resulting in improved performance compared to existing control methods.

As robotic telepresence is becoming more common and receives academic and industrial attention, the issue of how to increase the expressiveness of the telecommunication is becoming also important. In this paper, we explored the usage of 2D visual patterns displayed on the robot's body as a subsidiary visual channel to enhance communication between two remote users with a robot. Through a series of workshops with seventeen designers, we designed ten user-scenarios and corresponding 2D visual patterns to be used in four different environments: home, office, hospital, and department store. We then presented these patterns on the body of the M4K telepresence robot, and investigate with an online survey the expressiveness of the patterns in each of the proposed environments. Our results show the possibility of complex 2D visual expressions on the body of telepresence robots as a supplementary communication method and introduce a possible strategy for design those. Moreover, our results also show the overall perception and acceptability of these patterns split into three categories (progress indication, attention requests, and emotions) and across different environments.

Real-time rectification of stereo cameras is critical for stereoscopy in 3D vision and display. FPGA-based rectification has been suffering from the usage of large internal memory inside of the FPGA. The paper proposes a real-time stereo rectification approach using variable breakpoint indexing for enhanced compressed look-up table algorithm (E-CLUTR) in order to reduce the size of memory inside FPGA and to get a wider field-of-view (FoV) using high-distortion lenses. The proposed approach was successfully simulated using Altera ModelSim 10.4b. It is shown that the memory usage is reduced by 58∼65% compared with previous approaches and it supports real-time rectification of stereo 1920×1080 high-definition video data in 50 fps for a high-distortion lens with 110 degrees FoV.

All the people have their own individual force ranges to feel the sense of touch and its minimum value is called light touch threshold (in short LTT). For instance, if a touching force is very weak, people do not know whether the object is contacted to their skin, even though it is pushing the skin already. This paper presents a novel apparatus to measure the LTT felt by each subject, which is referred to as Active von Frey (AvF) in this paper. As far as the authors know, the LTT measurement device is for the first time proposed in this paper. It is possible for the AvF to provide the touching force ranges from 1[mgf] to 400[mgf]. In order to provide an accurate touching force for the subject, D'Arsonval movement is chosen as an actuator to rotate a touching AvF pin. Both an electric current applied to the D'Arsonval movement and a rotational angle of AvF pin are utilized to calculate the touching force by the electro-mechanical statics. In addition, the image processing technique is used to measure the rotational angle of AvF pin. Finally we show that the LTTs are very different from individual to individual through the experimental results of 10 participants. We hope that the personalized parameters is used to design or control haptic or tele-operation devices for various applications.

The present study used both self-report and electroencephalogram (EEG) measures and explored if users' sense of co-presence with communication counterparts' avatars would be salient when their own faces are morphed with the avatars' faces. Thirty-four undergraduate female students participated in an EEG/ERPbased experiment. In the experiment, each of the subjects who were assigned to either the morphed face condition or the non-morphed condition was exposed to the image presentation of avatar. The self-report data analyses indicated that the subjects felt significantly higher senses of being together with the counterparts whose faces were morphed with their own faces than those whose faces were not morphed. Further, the EEG/ERP data analyses demonstrated that the subjects paid much more attention to the counterparts whose faces were morphed than those who were not morphed.

We introduce a novel finger worn ring interface that enables complex spatial interactions through 3D hand movement in virtual reality environment. Users receive physical feedback in the form of vibrations from the wearable ring interface as their finger reaches a certain 3D position. The positions of the fingertip are extracted, linked, and then reconstructed as a trajectory. This system allows the wearer to write characters in midair as if they were using an imaginary whiteboard. User can freely write in the air using Korean characters, English letters, both upper and lower case, and digits in real time with over 92% accuracy rate. Thus, it is now conceivable that anything people can do on contemporary touch based devices, they could do in midair with a pseudocontact interface.

In manipulation tasks, skills are usually modeled using the continuous motion trajectories acquired in the task space. The motion trajectories obtained from a human's multiple demonstrations can be broadly divided into four portions, according to the spatial variations between the demonstrations and the time spent in the demonstrations: the portions in which a long/short time is spent, and those in which the spatial variations are large/small. In these four portions, the portions in which a long time is spent and the spatial variation is small (e.g., passing a thread through the eye of a needle) are usually modeled using a small number of parameters, even if such portions represent the movement that is essential for achieving the task. The reason for this is that these portions are slightly changed in the task space as compared with the other portions. In fact, such portions should be densely modeled using more parameters (i.e., overfitting) to improve the performance of the skill because the movements of those portions must be accurately executed to achieve the task. In this paper, we propose a method for adaptively fitting these skills based on the temporal and the spatial entropies calculated by a Gaussian mixture model. We found that it is possible to retrieve accurate motion trajectories as compared with those of well-fitted models, whereas the estimation performance is generally higher than that of an overfitted model. To validate our proposed method, we present the experimental results and evaluations when using a robot arm that performed two tasks.

This paper proposes a path planner for a humanoid robot to enhance its performance in terms of the human-robot interaction perspective. From the human point of view, the proposed method uses the time index that can generate a path that humans feel to be natural. In terms of the robot, the proposed method yields a waypoint-based path, the simplicity of which enables accurate tracking even for humanoid robots with complex dynamics. From an environmental perspective through which interactions occur, the proposed method can be easily expanded to a wide area. Overall, the proposed method can be described as a scalable path planner via waypoints with a time index for humanoid robots. Experiments have been conducted in test beds where the robot encounters unexpected exceptional situations. Throughout these trials, the robot successfully reached the goal location while iteratively replanning the path.

For a robot to learn complex movement skills, programming by demonstration and/or learning by trial and error is necessary. Measuring the complexity of such movement skills is important to decide the appropriate learning model, and the required size of dataset and additional prior knowledge. To deal with measuring the complexity of movement skills for robots, we propose an information-theoretic complexity measure. By modeling proprioceptive as well as exteroceptive sensory data as a multivariate Gaussian distribution, movement skills can be modeled as a probabilistic model. Next, complexity of the movement skills is measured by using neural complexity. In addition to the original neural complexity measure, endogeneous changes in time of the movement skills are modeled by sampling in time and modeling as individual random variables. To evaluate our proposed complexity measure, several experiments are performed on real robotic movement skills.

In recent, control approaches for the human-like behavior in the field of service robotics have been attracting considerable attention, since most humans or animals perform various tasks uncomplicatedly. Hence simple control methods based on gaining a physical insight into human reaching movement in redundancy of DOFs have been proposed. In comparison with the conventional approaches, the proposed method tries to control directly robotic systems in task-space with the control signal composed of linear superposition of three terms 1) joint-damping, 2) virtual spring, and 3) virtual damper in task-space. In particular, our work contains a muscle tension effect of a human under the gravity. This give birth to energy efficient natural motions avoiding problems on repeatability of the motion and ill-posedness problems emerged in most of redundant DOF systems. Thus, this paper exhibits expendability of the position control into the orientation control and compliant behavior. It is verified with a real robotic arm that satisfies human-like movements and motion repeatability under kinematic redundancy of joints.

There are many difficulties in operating a humanoid which has high degree-of-freedom and instability in balancing its body. In addition, due to the shape of a humanoid, it is expected to have motions like a human. In order to overcome its operational difficulties and to provide a humanlike motion, a teleoperation with the motion imitation is studied in this paper. Specifically, a framework for online generation of a footprint from a human walking motion is proposed. The human walking motions acquired from a motion capture device are parameterized and normalized to give a human independent foot motion. The normalized parameters are restored by a humanoid considering its hardware limit. The restored footprints generate a walking trajectory of a humanoid, which imitates the human walking motion in terms of the footprint. Experiments are conducted with MAHRU-R, a humanoid robot developed in KIST.

Recently, biologically inspired control approaches for robotic systems that involve the use of central pattern generators (CPGs) have been attracting considerable attention owing to the fact that most humans or animals move and walk easily without explicitly controlling their movements. Furthermore, they exhibit natural adaptive motions against unexpected disturbances or environmental changes without considering their kinematic configurations. Inspired by such novel phenomena, this paper endeavors to achieve self-adapting robotic arm motion. For this, biologically inspired CPG based control is proposed. In particular, this approach deals with crucial problems such as motion generation and repeatability of the joints emerged remarkably in most of redundant DOF systems. These problems can be overcome by employing a control based on artificial neural oscillators, virtual force and virtual muscle damping instead of trajectories planning and inverse kinematics. Biologically inspired motions can be attained if the joints of a robotic arm are coupled to neural oscillators and virtual muscles. We experimentally demonstrate self-adaptation motions that that enables a 7-DOF robotic arm to make adaptive changes from the given motion to a compliant motion. In addition, it is verified with real a real robotic arm that human-like movements and motion repeatability are satisfied under kinematic redundancy of joints.

This paper presents a characterization of the Hokuyo UBG-04LX-F01 laser rangefinder (LRF). The Hokuyo LRFs are suitable for a small mobile robot due to their small size and light weight. In particular, the scan frequency of Hokuyo UBG-04LX-F01 is higher than those of the previous LRFs in its price range. However, there is no research on characterizing this LRF for the convenience of practical use. Therefore, this paper characterizes the Hokuyo UBG-04LX-F01 and analyzes the effect of the target properties, such as incidence angle, color, brightness, and material, by measuring the distance to a target. The experimental results show that the measurement error is strongly influenced by the incidence angle and the brightness of the target surface. From the experimental results, a calibration model is also proposed to measure the accurate distance to a target.

Today, there are increased interest and various efforts in using cognitive architectures to control robotic platforms. Recent advances to essential capabilities in robots contributed to this trend, which tries to meet the increased demand for high-level control mechanisms. The tradition of cognitive architectures aims for general intelligence, and they have some great potential for use in robots that are now increasingly more capable of complex tasks. In this paper, we introduce one such architecture, ICARUS, used in a robotic environment to provide knowledge-based control for a humanoid robot, MAHRU. We show some experimental observations in the Blocks World domain.

This paper proposes a new walking pattern generation method for humanoid robots. The proposed method consists of feedforward control and feedback control for walking pattern generation. The pole placement method as a feedback controller changes the poles of system in order to generate more stable and smoother walking pattern. The advanced pole-zero cancellation by series approximation (PZCSA) as a feedforward controller plays a role of reducing the inherent property of linear inverted pendulum model (LIPM), that is, non-minimum phase property due to an unstable zero of LIPM and tracking efficiently the desired zero moment point (ZMP). The efficiency of the proposed method is verified by three simulations such as arbitrary walking step length, arbitrary walking phase time and sudden change of walking path.

This work presents a methodology to generate dynamically stable whole-body motions for a humanoid robot, which are converted from human motion capture data. The methodology consists of the kinematic and dynamical mappings for human-likeness and stability, respectively. The kinematic mapping includes the scaling of human foot and Zero Moment Point (ZMP) trajectories considering the geometric differences between a humanoid robot and a human. It also provides the conversion of human upper body motions using the method in. The dynamic mapping modifies the humanoid pelvis motion to ensure the movement stability of humanoid whole-body motions, which are converted from the kinematic mapping. In addition, we propose a simplified human model to obtain a human ZMP trajectory, which is used as a reference ZMP trajectory for the humanoid robot to imitate during the kinematic mapping. A human whole-body dancing motion is converted by the methodology and performed by a humanoid robot with online balancing controllers.

This paper proposes a neural oscillator based control to attain rhythmically dynamic movements of a robot arm. In human or animal, it is known that neural oscillators could produce rhythmic commands efficiently and robustly under the changing task environment. In particular, entrainments of the neural oscillator play a key role to adapt the nervous system to the natural frequency of the interacted environments. Hence, we discuss how a robot arm controls for exhibiting natural adaptive motions as a controller employing the entrainment property. To demonstrate the excellence of entrainment, we implement the proposed control scheme to a real robot arm. Then this work shows the performance of the robot arm coupled to neural oscillators in various tasks that the arm traces a trajectory. Exploiting the neural oscillator and its entrainment property, we experimentally verify an impressive capability of self-adaptation of the neural oscillator that enables the robot arm to make adaptive changes corresponding to an exterior environment.

It is known that biologically inspired neural systems could exhibit natural dynamics efficiently and robustly for motion control, especially for rhythmic motion tasks. In addition, humans or animals exhibit natural adaptive motions without considering their kinematic configurations against unexpected disturbances or environment changes. In this paper, we focus on rhythmic arm motions that can be achieved by using a controller based on neural oscillators and virtual force. In comparison with conventional researches, this work treats neither trajectories planning nor inverse kinematics. Instead of those, a few desired points in task-space and a control method with Jacobian transpose and joint velocity damping are merely adopted. In addition, if the joints of robotic arms are coupled to neural oscillators, they may be capable of achieving biologically inspired motions corresponding to environmental changes. To verify the proposed control scheme, we perform some simulations to trace a desired motion and show the potential features related with self-adaptation that enables a three-link planar arm to make adaptive changes from the given motion to a compliant motion. Specifically, we investigate that human-like movements and motion repeatability are satisfied under kinematic redundancy of joints.

This paper proposes a new walking pattern generation method for humanoid robots. This paper uses the linear inverted pendulum model (LIPM) which is composed of zero moment point (ZMP) and center of mass (CoM). Based on LIPM, the proposed method consists of feedforward control and feedback control for walking pattern generation of humanoid robots. The linear quadratic regulator(LQR) as a feedback controller tracks the desired ZMP according to footprints of humanoid robots and makes poles of LIPM stable. The feedback controller, pole-zero cancelation by series approximation (PZCSA) plays a role of reducing the inherent property of LIPM and approximating the transfer function of the overall system including LIPM and controllers to be unity. The usefulness of the proposed method is verified by simulations such as arbitrary time intervals of support phases, arbitrary desired ZMP position and sudden changed desired ZMP position. And the validity of the proposed method is confirmed by the experiment of a humanoid robot using a joystick.

A framework to generate a human-like arm motion of a humanoid robot using an Evolutionary Algorithm (EA)-based imitation learning is proposed. The framework consists of two processes, imitation learning of human arm motions and real-time generating of a human-like arm motion using the motion database evolved in the learning process. The imitation learning builds the database for the humanoid robot that is initially converted from human motion capture data and then evolved using a genetic operator based on a Principal Component Analysis (PCA) in an evolutionary algorithm. This evolution process also considers the minimizing of joint torques in the robot. The database is then used to generate humanoid robot's arm motions in real-time, which look like human's and require minimal torques. The framework is examined for humanoid robot to reach its arms for catching a ball. Additionally, the inverse kinematics problem to determine the final posture of 6-DOF robot arm with a waist for the task of catching a ball, is proposed.

This paper proposes an adaptive CPG based controller for a lower limb prosthesis consisting of online trajectory generation and interlimb coordination. The adaptive CPG can produce multidimensional rhythmic patterns and modulate their frequency by tuning relevant parameters in an autonomously way adapting to a changing periodicity of external signals. Also, to increase the stability of the prosthesis, a spring-damper component is attached between the hip and ankle joints, allowing the absorption of impulsive ground reaction forces at landing. We verify the validity of the proposed controller with a simulated humanoid robot through the investigation of the self-coordination between the healthy and robotic legs.

This paper proposes a new genetic operator in order to evolve the humanoid movements, which is composed of principal component analysis (PCA) and descent-based local optimization with respect to robot dynamics. The aim of the evolution is to let humanoid robots generate human-like and energy-efficient motions in real-time. We first capture human motions and build a set of movement primitives. The set is then evolved to the optimal movement primitives for the specific robot, which contain its dynamic characteristics, by using an evolutionary algorithm with the proposed genetic operator. Finally, the humanoid robot can generate arbitrary motions in real-time through the mathematical interpolation of the movement primitives in the evolved set. The evolved set of movement primitives endows the humanoid robot with natural motions which require minimal torque. This technique gives a systematic methodology for a humanoid robot to learn natural motions from human considering dynamics of the robot. The feasibility of our genetic operator is investigated by simulation experiments in regard to catching a ball that a man throws of the humanoid robot.

Humans or animals exhibit natural adaptive motions against unexpected disturbances or environment changes. In this paper, we focus on periodic, rhythmic arm motions that can be achieved by using a controller based on neural oscillators. The challenge of this work is to determine appropriate parameters of neural oscillators coupled to a robot arm, accomplishing a given task as well as self-sustaining natural rhythms. For this, an enhanced simulated annealing (SA) algorithm is developed. This work also demonstrates how to technically implement the proposed control scheme to a real robot. Exploiting the entrainment property of neural oscillators coupled to the joints of the arm, we verify that the arm traces a trajectory in such a way that the total energy consumption is minimized, responding to external disturbances.

Research on human-robot interaction has recently been getting increasing attention. In the research field of human-robot interaction, speech signal processing in particular is the source of much interest. In this paper, we report on a speaker localization system with six microphones for a humanoid robot called MAHRU of KIST and propose a time delay of arrival (TDOA)-based feature matrix with its algorithm based on the minimum sum of absolute errors (MSAE) for sound source localization. The TDOA-based feature matrix is defined as a simple database matrix calculated from pairs of microphones installed on a humanoid robot. To verify the solid performance of our speaker localization system for a humanoid robot, we present the various experimental results for the speech sources at all directions within 5 m distance and the height divided into three parts.

This paper presents a multiple humanoid cooperative control system(MHCCS) developed for the demonstration of heterogeneous humanoid collaborating to complete a mission consists of multiple humanoid tasks. MHCCS consists of CORBA based framework, humanoid control software, multiple humanoid cooperative control software, sensing software. Multiple humanoid cooperative control software consists of 3 layers: mission layer, task layer, action layer. User can design a task for humanoid by drawing a state diagram using developed graphical user interface, or edit XML-based command script directly. We defined action primitives suitable to abstract humanoid tasks by using state diagram, which is stored in a knowledge database for the future use. The developed MHCCS is successfully tested through the demonstration of a heterogeneous humanoid team cleaning the tables without confliction.

This paper introduces an omni-directional walking pattern generation method according to various footprints for a humanoid robot. We propose three step modules for generating stable walking pattern based on zero moment point(ZMP) and linear inverted pendulum model. The proposed step module uses both the characteristics of periodicity and the least square method in order to reduce the fluctuation range of the ZMP trajectory according to various footprints. In order to implement it, the trajectory of the desired ZMP is designed with the quartic polynomials. This method is more insensitive to variation of the walking pattern owing to the initial value of the ZMP and CoM and various walking step length. And it makes more efficient trajectory of CoM on account of the slope of ZMP in the single support phase. The effectiveness of the propose method is verified by simulation.

Stable and robust dynamic locomotion has been gaining increasing attention in humanoid research. This paper presents a neural oscillator network for the generation of periodic locomotion patterns adapting to changes in the slope of the terrain. Specifically, locomotion trajectories of individual limbs are predetermined in the trajectory generator as a periodic function of the gait. The phase of the periodic function is coordinated with the output of the neural oscillator network incorporating sensory signals detecting the state of the foot in contact with the unknown changing terrain. For stability to be maintained, the neural oscillator plays an important role by controlling the trajectory of the COM in phase with the trajectory of the ZMP. In order to verify the validity of the proposed scheme, we carry out simulations and experiments. A preliminary investigation has yielded promising results, indicating that it may be applied to humanoid locomotion through uneven and uncertain terrain.

In this paper, an estimate method of control system measurement error variance for Kalman estimator at run-time is proposed. In general, control system's measurement error variance is measured by some measuring instruments or tuned after implementation of Kalman estimator, but the precise measuring the control system measurement error variance is too hard. Moreover, even though we could tune the measurement error variance value, it could not deal with changes of system measurement error variance because of the phenomena of aging of system sensors or unpredictable external disturbances. So we introduce a method to estimate measurement error variance of the system for Kalman estimator at run-time to improve the performance of the estimator. Also a simple simulation and experimental result will be presented to show the effect of the proposed method.

This paper proposes a knowledge-based approach for adopting user's preferences and policies to plan and execute various services by a human-centered robot. To create an image of an obedient assistant in user's mind, we have suggested developing a robot that can customize its services according to user's guidelines. For materializing our idea, we have presented our knowledge-based human-centered (KBH) architecture. Using the deductive database technology, we have also presented some results demonstrating how our robot can take the high-level know ledge of user's guidelines into account and plan and execute an object delivery service accordingly.

A parameter tuning scheme for the neural oscillator is addressed to achieve biologically inspired robot control architectures based on a neural oscillator. It would be desirable to determine appropriately unknown parameters of the neural oscillator to accomplish a task of rhythmic movement under various changes of environment. Human or animal exhibits natural dynamics with efficient and performs robust motions against unexpected disturbances or environment changes. The neural oscillator needs to be tuned using its optimal parameters to generate such natural movement. As simple examples, this paper connects the neural oscillator to a pendulum system and a rotating crank system. To determine the optimal parameters of the neural oscillator for the examples, the optimization scheme based on the Simulated Annealing (SA) method is used. We verify the performance of the given tasks with the obtained optimal parameters of the neural oscillator, showing the adaptation motions of the example systems with entrainment property in numerical simulations.

This paper proposes the walking pattern generation method, the kinematic resolution method of center of mass (CoM) Jacobian with embedded motions, and the design method of posture/walking controller for humanoid robots. First, the walking pattern is generated using the simplified model for bipedal robot. Second, the kinematic resolution of CoM Jacobian with embedded motions makes a humanoid robot balanced automatically during movement of all other limbs. Actually, it offers an ability of whole body coordination to humanoid robot. Third, the posture/walking controller is completed by adding the CoM controller minus the zero moment point controller to the suggested kinematic resolution method. We prove that the proposed posture/walking controller brings the disturbance input-to-state stability for the simplified bipedal walking robot model. Finally, the effectiveness of the suggested posture/walking control method is shown through experiments with regard to the arm dancing and walking of humanoid robot.

This paper proposes the walking pattern generation method, the kinematic resolution method of CoM (center of mass) Jacobian with an embedded motion, and the walking controller design method for humanoid robots. First, the walking pattern is generated using the simplified model for bipedal robot. Second, the kinematic resolution of CoM Jacobian with embedded motion makes a humanoid robot balanced automatically during the movement of the all other limbs. Actually, it offers the ability of whole body coordination to the humanoid robot. Third, the walking controller is composed of the CoM controller minus the ZMP (zero momentum position) controller. Also, we show that the proposed walking controller brings the disturbance input-to-state stability (ISS) for the simplified bipedal walking robot model. Finally, the effectiveness of the proposed kinematic resolution method and walking controller is shown through experiments in regard to humanoid robot dancing and walking

Humanoids have a large set of basis behaviors and could perform various tasks. Controlling a humanoid with many degrees of freedom and behaviors consumes a lot of resources. By exploring the external service servers on the network, the ability of a humanoid is extendable beyond its resource constrains. This system is named network-based humanoid. In this paper, the network-based humanoid architecture (NBHA) is proposed to provide a core framework to develop this network-based humanoid system. It creates a system where humans, robots, and external service servers can interact without complicated configuration. Using this architecture, behaviors can be created, added and removed dynamically. A number of experiments have been conducted successfully by using JadeLeap middleware, FIPA standard and JESS rule engine on our humanoid. Experimental results show that the proposed architecture provides the extendable behavior control system in the network environment, decreases the development time for adding new services and it decreases the time for network connection of robots and user devices

Color segmentation takes a great attention because color is an effective and robust visual cue for characterizing an object from the others. However, color segmentation suffers from color variations incurred by irregular illumination changes. We propose a reliable color modeling approach in HSI (hue-saturation-intensity) color space while considering intensity information by adopting the B-spline curve fitting to make a mathematical model for statistical characteristics of a color with respect to intensity. It is based on the fact that color distribution of a single-colored object is not invariant with respect to brightness variations even in the HS (hue-saturation) plane. The statistical characteristics contain the mean and standard deviation of hue and saturation with respect to intensity. They are mathematically expressed as four bar graphs. In order to fit the bar graphs to continuous curves, we use B-spline curve fitting procedure. From several experimental results, we verify that the proposed algorithm is successfully applied to color segmentation under various illumination conditions

In this paper, a network-based humanoid architecture (NBHA) is proposed. NBHA is a distributed architecture that based on multi-agent technology to provide a systematic method for developing humanoid software system, external services and coordinating them in an effective manner. Behaviors of these humanoids and their surrounding network environment can be created, added and removed dynamically via a simple scripting method. Some experiments on our network-based humanoid are presented in this paper. Experimental results show that the multi-agent architecture is a good selection for developing this system. It provides an extendable behavior control method in the network environment and it decreases the development time for adding new services. Using this distributed multi-agent architecture, roles of a humanoid, method for coordination and performing scenario can be changed easily

Modern sophisticated robots, e.g. humanoids, require significant real-time communication speed in their fieldbuses. Several existing field-bus technologies, like controller area network (CAN), Profibus etc., provide real-time performance and reliability, however the bandwidth is not enough to support the communication demand of the complex humanoids. In this research, we have addressed this critical issue by utilizing comparatively faster IEEE 1394 serial bus on commercial off-the-shelf hardware and Linux-based real-time software platforms. Since the lack of user-level communication protocols in IEEE 1394 standard is a major obstacle for designing a IEEE 1394 based control system, we have solved this issue by customizing the predefined IEEE 1394 packet formats. Moreover, various IEEE 1394 serial bus related features have been investigated for designing an efficient humanoid control system. In this work, we have followed the real-time modeling and analysis method using Unified Modeling Language (UML). A use case driven analysis of timing requirement and determination of real-time constrain have been shown to prove the usefulness of our approach. The ongoing implementation of this proposed system in our network based humanoid, MAHRU, has been demonstrated in both commercial RTOS RTLinux (Pro) and free OSS RTOS Xenomai. The performance measurement of basic IEEE 1394 read transaction has been shown in both platforms along with a comparison with similar experiment on CAN bus. This provides an estimation of performance improvement of a humanoid control system on IEEE 1394 serial bus over CAN bus. Moreover the results obtained from two different Linux-based RTOS platforms indicate their relative pros and cons. This also enables us to select the suitable real-time framework for designing an efficient IEEE 1394 based humanoid control system

We propose a novel framework for imitation learning that helps a humanoid robot achieve its goal of learning. There are apparent discrepancies in shapes and sizes among humans and humanoid robots. It would be advantageous if robots could learn their behavior from different individuals. Toward this end, this paper discusses appropriate behavior generation method through imitation learning considering that demonstrator and imitator robots have different kinematics and dynamics. As part of a wider interest in behavior generation in general, this work mainly investigates how an imitator robot adapts a reference locomotion gait captured from a demonstrator robot. Specifically, a goal-directed adaptation process that we call self-adjusting adaptor is proposed to achieve stable locomotion of the imitator. The proposed adaptor has an important role that the perceived locomotion patterns are modified to keep the direction of lower leg contacting the ground identical between the demonstrator and the imitator, sustaining the dynamic stability by controlling the position of the center of mass. The validity of the proposed scheme is evaluated through simulations employing various imitator models on OpenHRP and then verified on a real robot

In this paper, we present a visual navigation algorithm by combining visual localization with the extraction of valid planar regions from a single camera of an indoor mobile robot. Only two pairs of natural line and point are used for the visual localization to take the advantage of fast detection. To track a given landmark model, Lucas-Kanade optical flow algorithm is applied by using gradient descent. We use the odometer data combined with visual information to determine the height of the landmark features. On-ground image features are used to calculate the homography between two image frames and to detect the planar region for navigation. Experimental results show the robustness of the method with respect to image illumination and noises. The performance in indoor environments shows the feasibility of the proposed visual navigation algorithm in realtime.

This paper proposes the indirect zero momentum position (ZMP) controller for biped robot systems and proves its disturbance input-to-state stability (ISS). The ZMP control has been used as a standard method for stable walking control of biped robot systems. Since the ZMP information consists of position and acceleration of the center of gravity (COG) for a biped robot system, the ZMP can be indirectly controlled by the motion of COG. In this paper, the reference COG planner is developed by solving the reference ZMP differential equation. The indirect ZMP controller is proposed to derive the desired motion of COG from the reference ZMP trajectory and the COG error (the difference between the reference and real COG). The ISS of the proposed indirect ZMP controller is proved for the simplified biped robot model. The robustness of the proposed indirect ZMP controller is shown in simulation.

In this paper, we present a simple method for visual localization of indoor mobile robots based on a natural landmark model. Only two natural lines and an intersection point are used for localization to take the advantage of fast detection. To track the landmark model, Lucas-Kanade optical flow algorithm is applied by using gradient descent. Then, by adopting reasonable assumption for indoor environments, a quick localization method for mobile robots from correspondent landmark is proposed in a linear technique. Experimental results that demonstrate the robustness of the method with respect to image illumination and noises are also presented. The performance in indoor environments shows the feasibility of the proposed localization algorithm in real-time.

This paper proposes an autonomous motion controller for mobile robots. It combines a biologically inspired motion planner and a nonlinear feedback controller in order to make a simple and practical motion controller in natural unknown environments. The motion planner part is designed in the frame of behavior-based scheme and adopts the biological concept "homeostasis". It plays the role of determining desired temporal target posture and modifying controller's gain parameters. The other nonlinear controller part drives the robot to the given target posture from the planner. As a result, the stable nonlinear feedback controller in ideal obstacle free space becomes practical one in natural environments constrained by obstacles. The proposed controller is simple mainly due to its behavior-based characteristics and stable due to the feedback controller considering robot's physical constraints. Simulated results and some experimental feature for autonomous navigation of the differential drive mobile robot, named "MARI", are shown for the present.

In this paper, an algorithm for hyper symmetric environment simultaneous localization and mapping (SLAM) is developed based on the generalized Voronoi graph. The hyper symmetric environment is a challenging environment for the SLAM and the most difficult problem on this is a data association. To redeem this problem, we propose three techniques. The first one is a breadth first node navigation algorithm which highly reduces the complexity of the data association. The second scheme is an odometry calibration method which converts untrustable odometry into reliable one. The third method is a multi layered data association scheme. We integrate above three techniques into one framework and propose a SLAM algorithm for the hyper symmetric environment. The simulation result shows that the proposed algorithm can successfully cover a large hyper symmetric environment under 20% odometry uncertainty.

In this paper, we present a simple linear method for localization an indoor mobile robot based on a natural landmark model and a robust tracking algorithm. The landmark model is sets of three or more natural lines such as baselines, door edges and linear edges in tables or chairs, to take the advantages of fast landmark detection. Lucas-Kanade optical flow algorithm is applied to track the landmark model by using gradient descent. Then, a quick localization method for mobile robots from correspondent lines is proposed by adopting a linear technique. We present experimental results that demonstrate the robustness of the method with respect to image illumination and noises. The performance in indoor environments shows the feasibility of the proposed localization algorithm in real-time.

Human friendly service robots such as home service robots, cleaning robots, entertainment robots take great attention in order to create new markets for robots since the markets for conventional industrial robots are saturating. It is a step to change the working environments of robots from industries to homes and offices, and to extend markets for robots from industrial markets to commercial home appliance markets. This paper introduces a home service robot 'ISSAC' applicable for vacuum cleaning, home security to find intruders and to transfer captured images of the intruder to the police or security companies, voice-based information service, real-time image transfer through wireless TCP/IP Ethernet and/or CDMA-2000 wireless communication, and a telepresence controllable by mobile computers such as pocket PC's and/or cellular phones. The overall controller is developed as a network-based layered modular controller using CAN (controller area network). The robot is tested in an apartment for a week successfully.

When a construction company builds a high structure, many piles should be driven into the ground by a hammer whose weight is 7,000 kg in order to make the ground under the structure safe and strong. So, it is essential to determine whether a pile is penetrated into the ground enough to support the weight of the structure since ground characteristics at different locations are different to each other. The paper proposes a visual measurement system for pile rebound and penetration movement including vibration using a high-speed line-scan camera and a specially designed mark to recognize two-dimensional motion parameters of the mark using only a line-scan camera. A mark stacking white and black right-angled triangles is used for the measurement, and movement information for vertical distance, horizontal distance and rotational angle is determined simultaneously. By adopting a line-scan CCD camera whose line rate is 20 kHz, the measurement performance of dynamic characteristics of the pile at impact instant is improved dramatically.

Despite that omni-directional mobile robots have been employed popularly in several application areas, effort on optimal design of such mobile robots has been few in literature. Thus, this paper investigates the optimal design of omni-directional mobile robots. Particularly, optimal design parameters such as one or double offset distance of wheel mechanism and the wheel radius are identifed with respect to isotropic characteristic of mobile robots. In addition, the force transmission characteristics and actuator-sizing problem of mobile robots are investigated Analysis has been performed for three actuation sets. It is shown that the redundantly acruated mobile robot with three active caster wheels represents the best performance among them.

Presents a situation-driven reconfigurable architecture for a schema-based robot controller which is operating in partially known indoor environments. Instead of the purely repulsive forces from the obstacles, we employ the linear combination of the repulsive and the detouring forces around the obstacle, so that the obstacles generate virtual forces pushing the robot toward the goal rather than just blocking it. By reconfiguring the detouring direction and the activation level of each schema based on the geometric and/or topological information provided by the variable resolution maps, the robot can navigate through the environments in very natural way. Simulation results show that our approach can remarkably improve the intrinsic defects of traditional potential field-bused schemas.

A kinematic modeling method is proposed which uses augmenting variables to match the dimensions of the input vector and output vector of each serial subchain of the mobile robots. Firstly, kinematic models of various type of wheels are derived including skidding and sliding velocities. Then the method of augmented generalized coordinates is applied to obtain inverse and forward kinematic models. The kinematic models derived by the direct inverse of the augmented matrices provide an accurate solution, which was not achievable by the modeling method based on the pseudo-inverse method which provides an approximate solution. Lastly, two kinematic models for typical, differential-driven mobile robots are presented to show the effectiveness of the proposed modeling method.

Color-based object tracking is an important issue since color is an efficient and robust visual cue for characterizing one object from the other objects. Color segmentation is, however, suffered from color variations induced from irregular illumination variations and the viewing geometry of a camera. This paper proposes a reliable color modeling approach including intensity information in HSI color space using B-spline curves based on the fact that the color distribution of a single-colored object, even in a hue-saturation plane, is not invariant with respect to brightness variations in practical cameras. By using the approach, our color-based visual tracker is able to adapt to irregular illumination variations and abrupt changes of brightness. The approach is applied to real-time face tracking under various illumination conditions in a PC-based vision system.

This paper proposes a visual serving method based on QR decomposition and disturbance observer. The QR decomposition factorizes the image feature Jacobian into a unitary matrix and an upper triangular matrix. It is shown that several performance indices such as measurement sensitivity of visual features, sensitivity of the control to noise and controllability can be improved for any general image feature Jacobian by OR decomposition and disturbance observer. To show the validities of the proposed approach, visual servoing with stereo cameras is experimented on Samsung FARAMAN 6-axis industrial manipulator.

This paper deals with target tracking control of unicycle type mobile robots. Target tracking function is essential for autonomous robots such as guide robots, security guard robots, etc. In the field of mobile robot control, many control schemes for posture stabilization and trajectory tracking problem have been proposed. Target tracking control, however, cannot be achieved using these kinds of control laws. Therefore, a new global asymptotic stable controller for this problem is designed using the backstepping method. The stability of the system is proved using the Lyapunov function. Various simulation results validate the performance and theoretical analysis.

To improve the visual servoing performance, several strategies have been proposed by using redundant feature points, by using a point with different height, and by a weighted selection of image features. The performance of these visual servoing methods depends on the configuration between the camera and objects. And redundant feature points require much computational efforts. The paper proposes a visual servoing method based on a disturbance observer which compensates the effect of the off-diagonal component of the image feature Jacobian to be null. The performance indices such as measurement sensitivity of visual features, sensitivity of the control to noise, and controllability are improved when an image feature Jacobian is given as a block diagonal matrix. The proposed approach is applied to the PUMA560 and Samsung FARAMAN 6-axis industrial robot manipulators successfully.

This paper describes a method of 3D object tracking by projective invariance. Usually, projective invariance has been used for object recognition and its property discards the need for cumbersome camera calibration to obtain metric information. We focus on the fact the projective invariance is not only regarded as recognition cues but also able to verify, the status of a 3D object for visual tracking. With projective invariance relevant to points, we develop a fast and reliable visual tracking strategy by combining a recognition module using projective invariance, window-based corner trackers for object's center tracking and a visibility checking module. The proposed method is experimented in single IBM-PC platform successfully.

There has been much interests on three-dimensional pose estimation of an object since there are a lot of robotic applications such as intelligent robotic assembly and/or vision-guided control of a humanoid or human-friendly robot. In this paper, there are proposed a simple and fast stereo matching algorithm for real-time robotic applications and an improved scheme for feature matching using three-dimensional information by adopting backprojection as a feedback element measuring the degree of feature matching. The degree of feature matching is determined by checking existence ratio of each feature point in real images after back-projecting an object model into image plane. The proposed pose determination algorithm is applied for a humanoid robot in KIST, whose name is CENTAUR, successfully and determine the pose of several polyhedral objects using 3D information of vertexes on the outline of an object in image plane.

A visual servoing method has been proposed based on a disturbance observer to eliminate the effect of the off-diagonal component of the image feature Jacobian, since performance indices such as measurement sensitivity of visual features, sensitivity of the control to noise, and controllability could be improved when an image feature Jacobian was given as a block diagonal matrix. In this paper, experimental results of disturbance observer-based visual servoing are discussed, where a Samsung FARAMAN-ASI 6-axis industrial robot manipulator is employed. Also, the feature saturator is proposed to stabilize the disturbance observer loop by saturating the differential changes of the image features.

We propose a new method for recognizing three-dimensional objects using a three-dimensional invariant relationship for a special structure and geometric hashing by single-view. We use a special structure consisting of four co-planar points and any two non-coplanar points with respect to the plane. We derive an invariant relationship for the structure, which is represented by a plane equation. For recognition of 3-D objects using geometric hashing, a set of points on the plane is mapped into a set of points intersecting the plane and the unit sphere, thereby satisfying the invariant relationship. Experiments using 3-D polyhedral objects are carried out to demonstrate the feasibility of our method for 3-D object recognition.

A compliance control strategy is proposed by using a new type of self-controlled stiffness function, where no explicit wrist force/torque sensor is employed. Specifically, the stiffness gain is given as the exponential function of the error between virtually given desired trajectory and actual trajectory, where virtual desired trajectory is designed to be inside the surface of the object to be compliance-controlled. And, a motion speed scheduling technique is also proposed to avoid serious damages due to lack of environmental knowledge and to minimally maintain the task performances. It is experimentally shown that the proposed control method is useful for various manipulator motion types such as path following, initial contact with soft impact and force regulation during contact.