Controlling humanoid robots with human motion data: Experimental validation

Controlling humanoid robots with human motion data: Experimental validation
复制标题

用人体运动数据控制人形机器人:实验验证

DOI:
10.1109/ichr.2010.5686312
复制
发表时间:
2010
期刊:
2010 10th IEEE-RAS International Conference on Humanoid Robots
影响因子:
--
通讯作者:
J. Hodgins
J. Hodgins
中科院分区:
--
文献类型:
--
作者:
K. Yamane;S. O. Anderson;J. Hodgins

文献摘要

参考文献

被引文献

相似文献

动作捕捉是编程类人机器人的一个很好的数据来源,因为它包含了人类行为的自然风格和协同作用。然而,由于类人机器人的运动学和动力学与人类有很大的不同,因此很难直接使用捕获的运动数据。在我们之前的工作中,我们开发了一种控制器,可以让机器人在跟踪给定的参考运动时保持平衡,而不包括接触状态变化。该控制器由基于简化机器人模型的平衡控制器和跟踪控制器组成,跟踪控制器通过关节局部反馈和优化过程获取关节力矩,同时实现平衡和跟踪。在本文中,我们改进了控制器,以解决与根位置/方向估计、模型不确定性以及期望与实际接触力之间的差异有关的问题。我们在一个全身力控人形机器人上实现了该控制器。实验结果表明,该控制器能够成功地使机器人跟踪捕捉到的人体运动序列。
Motion capture is a good source of data for programming humanoid robots because it contains the natural styles and synergies of human behaviors. However, it is difficult to directly use captured motion data because the kinematics and dynamics of humanoid robots differ significantly from those of humans. In our previous work, we developed a controller that allows a robot to maintain balance while tracking a given reference motion that does not include contact state changes. The controller consists of a balance controller based on a simplified robot model and a tracking controller that performs local joint feedback and an optimization process to obtain the joint torques to simultaneously realize balancing and tracking. In this paper, we improve the controller to address the issues related to root position/orientation estimation, model uncertainties, and the difference between expected and actual contact forces. We implement the controller on a full-body, force-controlled humanoid robot. Experimental results demonstrate that the controller can successfully make the robot track captured human motion sequences.
DOI: 10.1109/tvcg.2003.1207443
发表时间: 2003-07
期刊: IEEE Trans. Vis. Comput. Graph.
影响因子: --
作者:
K. Yamane;Yoshihiko Nakamura
通讯作者: K. Yamane;Yoshihiko Nakamura