• The Journal of Korea Robotics Society
• /
• v.8 no.1
• /
• pp.20-28
• /
• 2013

Large workspace and strong grasping force are required when a robot manipulates big and/or heavy objects. In that situation, bimanual manipulation is more useful than unimanual manipulation. However, the control of both hands to manipulate an object requires a more complex model compared to unimanual manipulation. Learning by human demonstration is a useful technique for a robot to learn a model. In this paper, we propose an imitation learning method of bimanual object manipulation by human demonstrations. For robust imitation of bimanual object manipulation, movement trajectories of two hands are encoded as a movement trajectory of the object and a force trajectory to grasp the object. The movement trajectory of the object is modeled by using the framework of dynamic movement primitives, which represent demonstrated movements with a set of goal-directed dynamic equations. The force trajectory to grasp an object is also modeled as a dynamic equation with an adjustable force term. These equations have an adjustable force term, where locally weighted regression and multiple linear regression methods are employed, to imitate complex non-linear movements of human demonstrations. In order to show the effectiveness our proposed method, a movement skill of pick-and-place in simulation environment is shown.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.8
• /
• pp.1231-1239
• /
• 2015

We developed a robot that has four limbs, each of which has the same kinematic structure and has 6 degrees of freedom. The robot is 600mm high and weighs 4.3kg. The robot can perform walking and manipulating task by using the four limbs selectively. The robot has three walking patterns. The first one is biped walking, which uses two rear limbs as legs and two front limbs as arms. The second one is biped walking with supporting arms, which is basically biped walking but uses two arms as supporting legs for increasing stability of the robot. The last one is quadruped walking, which uses all the four limbs as legs. When a task for the robot is given, the robot approaches the task point by selecting an appropriate walking pattern among three walking patterns and performs the task. The robot has many degrees of freedom and is a redundant system for a three dimensional task. We propose a redundancy resolution method, in which the robot’s translational move to the task point is modeled as a prismatic joint and optimal solutions are obtained by optimizing some performance criteria. Several simulations are performed for the validity of the proposed method.

• The Journal of Korea Robotics Society
• /
• v.16 no.4
• /
• pp.313-318
• /
• 2021

This paper proposes a new method to generate inverse reachability maps that are more efficient for mobile manipulators than the previous algorithms. The base positioning is important to perform the given tasks. Using the inverse reachability method, we can know where to place the robot's base for given tasks. For example, the robot successfully performed the task with relocation, even when the target is initially in a low manipulability area or outside the workspace. However, there are some inefficiencies in the online process of the classical inverse reachability method. We describe what inefficiencies appear in the online phase and how to change the offline process to make the online efficient. Moreover, we demonstrate that the proposed approach achieves better performance than usual inverse reachability approaches for mobile manipulation. Finally, we discuss the limitations and advantages of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2676-2681
• /
• 2003

The Haptic Exploration Laboratory at The Johns Hopkins University is currently exploring many problems related to haptics (force and tactile information) in human-machine systems. We divide our work into two main areas: virtual environments and robot-assisted manipulation systems. Our interest in virtual environments focuses on reality-based modeling, in which measurements of the static and dynamic properties of actual objects are taken in order to produce realistic virtual environments. Thus, we must develop methods for acquiring data from real objects and populating pre-defined models. We also seek to create systems that can provide active manipulation assistance to the operator through haptic, visual, and audio cues. These systems may be teleoperated systems, which allow human users to operate in environments that would normally be inaccessible due to hazards, distance, or scale. Alternatively, cooperative manipulation systems allow a user and a robot to share a tool, allowing the user to guide or override the robot directly if necessary. Haptics in human-machine systems can have many applications, such as undersea and space operations, training for pilots and surgeons, and manufacturing. We focus much of our work on medical applications.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1779-1784
• /
• 1991

The problem of fine manipulation is considered in this paper. By fine manipulation, we mean the positioning of the object relative to the palm as opposed to gross manipulation by the arm. The compliance in the fingers and the object is modeled by linear springs. It is shown that the motion of the fingers and object can be predicted by minimizing a quadratic objective function. A method for simulating position control algorithms is developed.

• Journal of Drive and Control
• /
• v.17 no.4
• /
• pp.31-37
• /
• 2020

We are concerned with the dual-arm manipulation for disaster-responding special-purpose machinery. This paper presents a control strategy for performing complex work in an irregular environment, the control algorithm, the hydraulic circuit, and the master devices. The occurrence of collapse accidents at disaster sites such as natural disasters and building collapses is increasing, which is emerging as a social problem. In particular, for the initial response, various tasks must be performed in an irregular environment. The Marionette algorithm for intuitive control of 'as if the operator's arm is moving' was presented as a control strategy for dual-arm manipulators with attachments and the prototype. Next, the hydraulic circuit, control system, and wearable-type master device presented to implement the Marionette algorithm were explained and verified through an experiment in which rebar-cutting, drum-lifting, and lifting a bottle with one arm and pouring the water into the bucket with the other arm were tested.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.06a
• /
• pp.751-752
• /
• 2008

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.9
• /
• pp.5-12
• /
• 2000

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.183-184
• /
• 2010

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.101-102
• /
• 2011