• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Robot Intelligence Technology and Applications >Artificial Intelligence Approach to the Trajectory Generation and Dynamics of a Soft Robotic Swallowing Simulator
【24h】

Artificial Intelligence Approach to the Trajectory Generation and Dynamics of a Soft Robotic Swallowing Simulator

机译：软机械吞咽模拟器轨迹生成和动态的人工智能方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Soft robotics is an area where the robots are designed by using soft and compliant modules which provide them with infinite degrees of freedom. The intrinsic movements and deformation of such robots are complex, continuous and highly compliant because of which the current modelling techniques are unable to predict and capture their dynamics. This paper describes a machine learning based actuation and system identification technique to discover the governing dynamics of a soft bodied swallowing robot. A neural based generator designed by using Matsuoka's oscillator has been implemented to actuate the robot so that it can deliver its maximum potential. The parameters of the oscillator were found by defining and optimising a quadratic objective function. By using optical motion tracking, time-series data was captured and stored. Further, the data were processed and utilised to model the dynamics of the robot by assuming that few significant non-linearities are governing it. It has also been shown that the method can generalise the surface deformation of the time-varying actuation of the robot.
机译：软机器人是机器人通过使用柔软和柔和的模块设计的区域，这些模块为它们提供无限的自由度。这种机器人的内在运动和变形是复杂的，连续且高度兼容的，因为其中当前的建模技术无法预测和捕获其动态。本文介绍了一种基于机器学习的致动和系统识别技术，以发现软体吞咽机器人的控制动态。通过使用Matsuoka的振荡器设计的神经基发生器已经实施以致动机机器人，以便它可以提供其最大潜力。通过定义和优化二次目标函数来找到振荡器的参数。通过使用光学运动跟踪，捕获和存储时间序列数据。此外，通过假设少数重要的非线性正在管理它来处理并利用数据来模拟机器人的动态。还表明该方法可以概括机器人的时变致动的表面变形。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号