Ji-Yong Lee

MAHRU-M: A mobile humanoid robot platform based on a dual-network control system and coordinated task execution

This paper introduces a mobile humanoid robot platform able to execute various services for humans in their everyday environments. For service in more intelligent and varied environments, the control system of a robot must operate efficiently to ensure a coordinated robot system. We enhanced the efficiency of the control system by developing a dual-network control system. The network system consists of two communication protocols: high-speed IEEE 1394, and a highly stable Controller Area Network (CAN). A service framework is also introduced for the coordinated task execution by a humanoid robot. To execute given tasks, various sub-systems of the robot were coordinated effectively by this system. Performance assessments of the presented framework and the proposed control system are experimentally conducted. MAHRU-M, as a platform for a mobile humanoid robot, recognizes the designated object. The objects pose is calculated by performing model-based object tracking using a particle filter with back projection-based sampling. A unique approach is used to solve the human-like arm inverse kinematics, allowing the control system to generate smooth trajectories for each joint of the humanoid robot. A mean-shift algorithm using bilateral filtering is also used for real-time and robust object tracking. The results of the experiment show that a robot can execute its services efficiently in human workspaces such as an office or a home.

Robot Head-Eye calibration using the Minimum Variance method

This paper presents a calibration method for a robot Head-Eye system which can be used in a humanoid robot vision system. This method estimates the transformation between the robot coordinate and the camera coordinate. The calibration procedure uses visual measurements and kinematic information as the inputs of nonlinear optimization. For this calibration method, an objective function for the optimization, that uses the Minimum Variance method is defined. The procedure of this method is very simple and intuitive. Besides, the result of this method is considerably precise and robust against the noisy environment. The performance is compared with earlier approaches and the results of simulation and actual experiment are followed.

Autonomous task execution of a humanoid robot using a cognitive model

Cognitive architectures provide infrastructure for modeling human cognition. Recent studies reveal that these architectures are useful control mechanisms for a variety of robots. Previously, we showed one such architecture, ICARUS, can successfully control a humanoid robot for Blocks World tasks in a simulated environment. In the current work, we extend the application to the real world and use the architecture to perform similar tasks with Mahru-Z platform. As commonly expected, we encountered many challenges in system integration, vision-based information updates, and manipulation tasks. This paper reports the result of our initial work to address some of these issues. The successful completion of a color sorting task indicates the system is capable to adapt to such challenges and we expect similar results in more complicated tasks in this domain.

Providing services using network-based humanoids in a home environment

This paper describes the development of network based humanoids to provide services in the home environment. For successful service in more intelligent and varied environments, various robot sub-systems need to be coordinated effectively. Thus, this paper also introduces a coordinated framework which makes robot-human interaction while executing various tasks by means of various robots. Using a task script, an operator can easily describe tasks and regulate actions of the sub-systems while a robot is performing the task. Furthermore, the control system of a robot must operate efficiently to ensure a coordinated robot system, so the realization of an IEEE-1394 real-time distributed control system and a motor controller for a humanoid robot are introduced. Many algorithms have been developed, and the following technologies are described herein: autonomous biped walking; real-time modification of collision-free paths; and interaction ability with humans and environments, such as face, voice, or object recognition. The results of the demonstration show that humanoids can execute tasks efficiently and are suitable to provide services in human environments, such as restaurants or homes.1.

Controlling a humanoid robot in home environment with a cognitive architecture

Latest humanoid robots mimic the human body in realistic ways, but their control mechanisms fall short of the human mind. More often than not, the robots simply have a fixed set of routine codes that govern their behavior, and even the ones with some learning capabilities are not human-like. Since cognitive architectures aim for general intelligence and provide infrastructure for modeling human cognition, we can benefit from this line of research by adapting such architectures as control mechanisms in our robots. Recent studies revealed that this strategy is, in fact, very useful. Previously, we used one such architecture, Icarus, to control a humanoid robot for Blocks World tasks. In this paper, we extend the system to perform more complex tasks autonomously on a similar platform. Despite the challenges we encountered in system integration, sensory updates, and navigation, the overall success of this application indicates that the system is capable of more complex tasks to provide services in home environments.

Coexistent Space : Collaborative Interaction in Shared 3D Space

It has long been a desire of human beings to coexist in the same space together with people in remote locations, and interact with them in a natural way. There have been proposed various concepts to connect the real world with the remote world in 3D space [1, 2]. In this paper, the concept of Coexistent Space for collaborative interaction in shared 3D virtual space is proposed. Coexistent Space provides not only the feeling of coexistence as the sense of being with others, but also a shared virtual workspace for collaboration. The main feature is that the users can share a virtual whiteboard for writing interaction and manipulate shared virtual objects with the bare hand touch interaction.

Real-time optimization for the high-fidelity of human motion imitation

This paper proposes a real-time optimization method for the high-fidelity of human motion imitation using a marker-based motion capture system. Although many ways to generate realistic synthetic motions from the capturing data have been developed, there are common problems related to marker occlusion. Our approach is useful for getting over marker occlusion in real-time system environments, and this is fit for altering human motion to other skeleton structures such as human avatars and humanoid robots. In this paper, we applied the proposed optimization method to construct the whole body joint configuration. The result has been demonstrated by simulation test using a 20-DOF skeleton model.

Network-based humanoid operation in home environment

This paper describes the development process of the network-based humanoid to provide services in home environment. To provide successful service, various sub-systems of the robot need to be coordinated effectively. So the paper introduces a coordinated framework which makes it possible to interact with humans while executing various tasks by various robots. Using a task script, operator can easily describe tasks and it regulates actions of the sub-systems while the robot is performing the task. Many strategies and algorithms are developed and some of technologies are described: autonomous biped walking and real-time modification of collision-free path, interaction ability with humans and environments such as a face, a voice or object recognition, and manipulation in contact environments. We also talk about emergency situations and safety issues. The results of our demonstration show plural humanoids can execute the task efficiently and be suitable for providing services in human environments, such as a restaurant or a home.

A service framework of humanoid in daily life

This paper presents a service framework of a humanoid robot for the coordinated task execution. To execute given tasks, various sub-systems of the robot need to be coordinated effectively. The goal of our paper is to develop the service framework which makes it possible to execute various tasks in daily life environments. A script is used as a tool for describing tasks to easily regulate actions of the sub-systems while the robot is performing the task. The performance of the presented framework is experimentally demonstrated as follows: A humanoid robot, as the platform of the task execution, recognizes the designated object. The object pose is calculated by performing model-based object tracking using a particle filter with back projection-based sampling. An approach proposed by Kim et al. [1] is used to solve a human-like arm inverse kinematics and then the control system generates smooth trajectories for each joint of the humanoid robot. The results of our implementation show the robot can execute the task efficiently in human workspaces, such as an office or home.