Hiromu Onda

Task skill transfer method using a bilateral teleoperation

In this paper, we propose a task skill transfer method using a bilateral teleoperation. We assume that a task skill for a complicated motion is described by the suitable trajectory of the impedance center. Thus, a important point is how to get the suitable trajectory of the impedance center. In our method, the suitable trajectory is got from results of bilateral teleoperation. In the bilateral teleoperation, an operator constructs a motion procedure able to execute the task. The suitable trajectory of the impedance center is calculated from the position and the force data in the teleoperation experiment. A basic element of the task skill is composed of an initial condition, a task skill motion and a final condition. The initial and final conditions are described by values of both sensor and tip position. The task skill motion is described by a hybrid impedance/force control. To demonstrate how to use of our method, we choose the nut attachment task as an example

Visualization and simulation of sensory events as a representation of states for state-based teaching by demonstration in VR

Teaching by demonstration is a method to generate a robot program that makes a robot do the same task as the task that a human operator demonstrates. We have developed a teaching by demonstration in VR system (TbDinVR) which automatically generates a robot program to work in the real world after a task is demonstrated by an operator in the virtual world. In this paper, we have explained necessary and sufficient condition for states in a task description, advantages of using state-based TbDinVR system, and a simulator for determining parameters of skill primitives by using sensor simulation in VR and a random search technique in detail. We have shown an experimental result and visualization of that result.

Task skill transfer of nut attachment task

This paper describes how to construct a task skill of nut attachment. An operator constructs a teleoperation procedure able to execute this task using a bilateral teleoperation system. A motion process of the nut attachment task skill is defined from the teleoperation procedure. Each motion of the task skill is composed of an initial condition, a task skill motion and a final condition. The initial and final conditions are described by values of both sensor and tip position. The task skill motion is described by a hybrid control composed of impedance and force controls. The necessary parameters of the task skill can be obtained from the result of teleoperation experiment. Our experiment which is executed by several sizes of the nut shows the effectiveness and robustness of the nut attachment task skill

Task skill transfer of circle handle valve manipulation

This paper describes how to write a task skill program of circle handle valve manipulation. It is difficult to program a complicated motion with a knack. Thus, in a previous paper, we proposed a task skill transfer method using a bilateral teleoperation to be able to program the knack easily. The task skill is composed of an initial condition, a task skill motion and a final condition. The initial and final conditions are described by the force and the position of the end-effector. The task skill motion is implemented by the hybrid impedance/force control. This hybrid impedance/force control is effective to a positional error. In this paper, we show that it is able to program the complicated motion with the knack (the hole search motion) easily.

Task skill transfer of 3-prong plug manipulation

This paper describes how to write a task skill program for a 3-prong plug manipulation. One of important features in this paper is that it is easy to program a hole search motion and so on. In a previous paper, we proposed a task skill transfer method using a bilateral teleoperation. The task skill is composed of an initial condition, a task skill motion and a final condition. The initial and final conditions are described by the force and the position of the end-effector. The task skill motion is implemented by the hybrid impedance/force control. This hybrid impedance/force control is effective to a positional error. A motion process of the task skill is defined from the teleoperation procedure. The necessary parameters of the task skill are obtained from the results of teleoperation experiment. Thus, the task skill is generated from the teaching data and the teaching intention (motion strategy). In this paper, our task skill transfer method is applied to the 3-prong plug manipulation. Some experiments shows an efficiency of the 3-prong plug manipulation task skill

Improving task skill transfer method by acquiring impedance parameters from human demonstration

This paper addresses how to acquire reusable robot skills for practical tasks based on a programming by demonstration approach. Specifically, this paper aims at improving the task skill transfer method, which has been proposed by the authors, by acquiring impedance parameters and equilibrium trajectories simultaneously from demonstration data. First, the overview of the task skill acquisition method is described. Then, how to acquire the impedance parameters is discussed. Finally, the effectiveness of the proposed method is verified by experiments.

Visualization and analysis for reorganization of task-and-environmental information structure for robot program

Reusability of a robot program in different environments for a different robot is one of key issues for robotics. Since information structures of a task and environments at programming phase and the information structures at execution phase of a robot program is usually different, it is sometimes difficult to use the program, which is executable in an environment at programming phase, in different environments at execution phase. In this paper, we describe how to visualize, understand and reorganize information structure of a task and an environment at programming phase in order to adjust them to different environments and reuse them at execution phase.

Task skill transfer of bolt attachment task

This paper describes how to write a task skill program for a bolt attachment. One of important features in this paper is that it is easy to find a knack for an axis adjustment and to program the axis adjustment. In a previous paper, we proposed a task skill transfer method using a bilateral teleoperation. The task skill is composed of an initial condition, a task skill motion and a final condition. The initial and final conditions are described by the force and the position of the end-effector. The task skill motion is implemented by the hybrid impedance/force control. This hybrid impedance/force control is effective to a positional error. A motion process of the task skill is defined from the teleoperation procedure. The necessary parameters of the task skill are obtained from the results of teleoperation experiment. Thus, the task skill is generated from the teaching data and the teaching intention (motion strategy). In this paper, our task skill transfer method is applied to the bolt attachment. Some experiments show an efficiency of the bolt attachment task skill.

Manipulation primitive analysis support system of state-based teaching by demonstration in VR - visualization and simulation of sensory events

Teaching by demonstration is a method to generate a robot program that makes a robot do the same task as the task that a human operator demonstrates. The authors has developed a teaching by demonstration in VR system (TbDinVR) which automatically generates a robot program to work in the real world after a task is demonstrated by an operator in the virtual world. In this paper, we have explained necessary and sufficient condition for states in a task description, advantages of using state-based TbDinVR system, and a simulator for determining parameters of skill primitives by using sensor simulation in VR and a random search technique. We have shown an experimental result and visualization of that result