华南理工大学学报(自然科学版) ›› 2024, Vol. 52 ›› Issue (3): 84-92.doi: 10.12141/j.issn.1000-565X.230086

• 机械工程 • 上一篇    下一篇

基于外力矩观测器的机器人碰撞检测

张铁 陈亿杰 邹焱飚   

  1. 华南理工大学 机械与汽车工程学院,广东 广州 510460
  • 收稿日期:2023-03-06 出版日期:2024-03-25 发布日期:2023-04-04
  • 作者简介:张铁(1968-),男,博士,教授,主要从事机器人技术及工程应用研究。E-mail: merobot@scut.edu.cn
  • 基金资助:
    广东省科技计划项目(2021B0101420003)

Robot Collision Detection Based on External Torque Observer

ZHANG Tie CHEN Yijie ZOU Yanbiao   

  1. School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China
  • Received:2023-03-06 Online:2024-03-25 Published:2023-04-04
  • About author:张铁(1968-),男,博士,教授,主要从事机器人技术及工程应用研究。E-mail: merobot@scut.edu.cn
  • Supported by:
    the Science and Technology Planning Project of Guangdong Province(2021B0101420003)

摘要:

碰撞检测技术可以降低设备损坏和人身伤害的几率,在现代化的人机协作生产中起着重要的作用。实现免外力矩传感器的碰撞检测需要准确地估计工业机器人受到碰撞时的关节外力矩。然而,动力学模型的参数辨识误差以及电机电流的测量误差等因素会影响外力矩估计的准确性。为了解决这些问题,本文设计了一种扰动卡尔曼滤波外力矩观测器。该观测器基于扰动原理将外部碰撞等效的外力矩作为扰动项,并定义关节扰动模型。同时,引入机器人的广义动量构建状态空间方程。考虑到动力学模型的参数辨识以及电机电流的测量存在误差,基于卡尔曼滤波算法进行迭代估计,从而得到最优的外力矩观测值。为了提高碰撞检测的灵敏度,本文提出了一种随关节速度变化的时变对称阈值函数,用于实现碰撞检测。该方法可以根据关节速度的变化调整阈值,以适应不同工作速度下的外力矩观测值。实验结果表明,与广义动量观测器相比,所提出的观测器在外力矩估计的整体精度上提高了52.03%。为了验证所提方法的有效性,本文利用6自由度串联关节型工业机器人进行了碰撞检测实验。实验结果显示,相比于静态阈值,采用时变阈值的方法缩短了58.06%的检测延时,从而可以提高碰撞检测的灵敏度,更有利于工业机器人的安全操作和碰撞防护。

关键词: 工业机器人, 碰撞检测, 外力矩观测器, 时变阈值

Abstract:

Collision detection technology can reduce the probability of equipment damage and personal injury and plays an important role in modern human-robot collaborative production. To realize the collision detection without external torque sensor, it is necessary to accurately estimate the external torque of industrial robots. However, the accuracy of external torque estimation can be affected by parameters identification error of dynamic model and measurement error of motor current. To solve these problems, this paper designed a disturbance Kalman filter external torque observer based on the disturbance principle. The observer takes the equivalent external torque of external collision as the disturbance term, defines the joint disturbance model, and introduces the generalized momentum of the robot to construct the state-space equation. Considering the parameters identification error of the dynamic model and the measurement error of the motor current, it carried out an iterative estimation based on Kalman filter algorithm to obtain the optimal external torque. In order to improve the sensitivity of collision detection, a time-varying symmetric threshold function which varies with joint velocity was proposed for collision detection. The proposed method can adjust the threshold according to the change of joint velocity to adapt to the observed values of external torques at different working speeds. Experimental results show that compared with the generalized momentum observer, the accuracy of external torque estimation of the proposed observer is improved by 52.03%. In order to verify the effectiveness of the proposed method, this paper used a 6-DOF series joint industrial robot to conduct collision detection experiments. The experimental results show that compared with the static threshold, the time-varying threshold method reduces the detection delay by 58.06%, which can improve the sensitivity of collision detection and is more conducive to the safe operation and collision protection of industrial robots.

Key words: industrial robot, collision detection, external torque observer, time-varying threshold

中图分类号: