KangGeon Kim

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.

Human-like catching motion of humanoid using Evolutionary Algorithm(EA)-based imitation learning

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 robots arm motions in real-time, which look like humans 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.

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.

Problem solving and learning for a humanoid robot

Based on our previous work that integrated a cognitive architecture, Icarus, and a humanoid robot, Mahru, we extend our use of the architecture to higher-level capabilities of problem solving and learning. During this process, we found the need to address a known limitation of ICARUSs problem solver. An extension is made to allow handling of underspecified goals in the system, and we demonstrate this new ability in a blocks world task that involves alphabet writing with several identical blocks.

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.