机器人的CP-nets优化类人轨迹规划（英文）

Optimal human-like trajectory planning of CP-nets for robot

中文关键词  机器人控制  人机系统  条件偏好网  轨迹

英文关键词  Robot control  Human-machine system  CP-nets  Trajectory

中文摘要

      机器人移动轨迹按照人的手臂来模拟是提高机器人安全性和人机交互能力的有效方法，特别是针对机器人抓取路径不唯一的场合，类人行为对于人机系统表现更加自然。此前，通常利用Kinect等设备，基于人工神经网络和K近邻算法等智能算法对类人轨迹进行规划，但无法获得未采样过的最优轨迹。本文基于CP-nets采用偏好模型研究类人运动轨迹，然后将该模型应用于机器人控制，在没有采样的情况下，也可得到最优的类人轨迹。实验结果表明，基于CP-nets 的类人规划轨迹具有较高的效率和舒适性，符合人的运动特征。

英文摘要

      Robot moving trajectory simulated with human arm and wrist is an effective method to improve the safety of the robot and the ability of human-robot interaction. Especially, the reaching path for robot hand grasping is not unique. Human-like system is known as more understandable and natural for human-robot interaction. The planning of human-like trajectory were presented based on intelligent algorithm like as artificial neural network and the K-nearest neighbors algorithm by using the Kinect or other equipment, but they cannot learn the optimal trajectory which not been sampled. In this paper, a preference model is adopted to study the trajectory of human-like movement based on CP-nets. Then the model is applied on the robot control to obtain the optimal human-like trajectory even it not been sampled. The results showed that the planned trajectory has high efficiency and comfort with human like movement characteristics.