权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Research on the emergent mechanism of skillful motion

熟练动作发生机制研究

基本信息

批准号：
15360225
负责人：
MIYAZAKI Fumio
金额：
$ 5.7万
依托单位：
Osaka University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (B)
财政年份：
2003
资助国家：
日本
起止时间：
2003 至 2004
项目状态：
已结题

项目摘要

To perform tasks during intermittent interactions between robot and environment, the robot must be able to adjust the strength and timing of interactions during execution of the tasks. These are called hybrid (mixed continuous and discrete) control problems by Burridge et al., who gave hopping, catching, hitting, and juggling as typical examples. These tasks have attracted the attention of researchers also in the area of experimental psychology in the sense that they require both receptor anticipation of the environmental situation and effector anticipation of internal movement processes. However, it is difficult to find general approaches that are sufficiently tractable for the robot to perform these tasks.In this research, we focused on the table tennis task that involves the intermittent nature of the robot-ball interaction in order to explore the hybrid control problems. We verified the usefulness of the following two methods based on the memory based learning approach to achieve a … More robotic table tennis task. (1)a method of generating stroke movement based on virtual targets that means the point at which the ball should be struck and the paddle velocity just before hitting the ball. (2)a method of controlling the paddle using three input-output maps : (a)a map for predicting the impact time of the ball hit by the paddle and the ball position and velocity at that moment according to input vectors describing the state of the incoming ball, (b)a map representing a change in ball velocities before and after the impact, and (c)a map giving the inverse relation between the ball velocity just after the impact and the bouncing point and time of the returned ball.Contributions of this research to the robotic field are summarized as follows :(1)to verify the effectiveness of the memory based learning approach to the hybrid control problems involved in robotic tasks with intermittent interactions between a robot and its environment,(2)to demonstrate that a good combination of forward and inverse maps makes it possible for a robot system to interact with a dynamical environment, and(3)to propose a Direct ILC method of perfectly realizing the robot's action planned using the maps given in (2). Less

为了在机器人与环境之间间歇性交互期间执行任务，机器人必须能够在任务执行期间调整交互的强度和时间。 Burridge 等人将这些问题称为混合（混合连续和离散）控制问题，他们以跳跃、接球、击打和杂耍作为典型例子。这些任务也引起了实验心理学领域研究人员的注意，因为它们需要受体对环境情况的预期和效应器对内部运动过程的预期。然而，很难找到足够容易处理的通用方法来让机器人执行这些任务。在这项研究中，我们重点关注涉及机器人与球交互的间歇性的乒乓球任务，以探索混合控制问题。我们验证了以下两种基于基于记忆的学习方法来实现机器人乒乓球任务的有用性。 (1)基于虚拟目标产生击球运动的方法，虚拟目标是指应击球的点和击球前的球拍速度。 (2)使用三个输入输出映射来控制球拍的方法：(a)根据描述来球状态的输入向量来预测球拍击球的撞击时间以及此时球的位置和速度的映射，(b)表示撞击前后球速度变化的映射，以及(c)给出撞击后球速度与弹跳之间球速度之间的反比关系的映射这项研究对机器人领域的贡献总结如下：（1）验证基于记忆的学习方法对涉及机器人与其环境之间间歇性交互的机器人任务中的混合控制问题的有效性，（2）证明正向映射和逆向映射的良好组合使机器人系统能够与动态环境交互，以及（3）提出直接ILC方法使用（2）中给出的地图完美地实现机器人计划的动作。较少的