Measurement of wrist force/torque using data fusion technique

This paper proposes a kind of measurement method of wrist force/torque for robots. The method adopts the data fusion technique according to the output variations of the finger force sensors installed in the gripper. The finger force sensors are used to measure the clamping force of the gripper in the design. When the accuracy of measurement is not required exactly and there is the limitation of weight and volume in space robots, we utilize the existing devices to estimate the wrist force/torque without the wrist force/torque sensor, which not only meets the practical requirement but also decreases the weight and cost of robots. An experimental bench is developed and the calibration experiments are conducted to detect the relationship between the wrist force/torque and finger forces. The experimental data are used to train a radial basis function (RBF) artificial neural network, and the construction and parameters of the network are obtained. The results of data fusion of the wrist force/torque are consistent with the practical calibration values, and the effectiveness of the wrist force/torque estimating technique is proved.

Introduction

The wrist force and torque must be measured during the operating of robots. One aim is to ensure that robots can complete tasks with accuracy, such as mechanical assembling, precise grinding, outline trace and so on, in this situation the high measuring accuracy is required. For this purpose wrist force/torque sensors are developed [1]∼[3]. Another is to ensure the safety of operation of robots, e.g. a kind of space robot - the extravehicular mobile robot (EMR) has two arms equipped with two grippers at the arm ends. The gripper has not only the hand function to grasp the work-piece, but also the foot function to connect to the I-shaped beam fixed on the experimental platform [4]∼[8]. Therefore, the gripper must grasp objects firmly during the EMR moving and operating processes, otherwise the robot probably separates itself from the experimental platform and becomes the space rubbish. In order to ensure the safety of operation of robots, it is necessary to monitor the wrist force/torque of robots to avoid it exceeding the limitation. The EMR, however, cannot install a wrist force/torque sensor because of the limitation of its weight and dimension. At the same time, the high measuring accuracy is not required. Can other sensors in the gripper be utilized to detect the wrist force/torque? This paper presents a novel kind of technique to estimate the wrist force/torque using the data fusion method according to the output variations of finger force sensors.