Prediction of fingers posture using artificial neural networks
Prediction of fingers posture using artificial neural networks
复制标题
DOI：
10.1016/j.jbiomech.2008.06.005
复制
发表时间：
2008-08-28
影响因子：
2.4
通讯作者：
Gorce, Philippe
中科院分区：
文献类型：
--
作者：
Rezzoug, Nasser;Gorce, Philippe
预测手和手指在抓握过程中的姿势是生物力学框架中的一个重要问题。本文提出了一种基于神经网络的指尖三维位置与相应关节角度的逆运动学映射学习方法。手指的运动通过仪表手套获得，并映射到手的多链模型。从指尖期望的位置，神经网络允许预测相应的手指关节角度保持特定的主体协调模式。本研究考虑了两组动作。第一个是由自由手指运动组成的训练集，用于构建指尖位置和关节角度之间的映射。第二个是为测试目的而构建的，由一系列日常生活对象的抓取任务组成。训练集的指尖测量位置与模拟关节角度和正运动学得到的指尖位置的最大平均误差为0.99 +/- 0.76 mm，测试集的最大平均误差为1.49 +/- 1.62 mm。训练集和测试集的关节角预测最大均方根误差分别为2.85度和5.10度，而训练集和测试集的关节角预测最大均方根误差分别为-0.11 +/- 434度和-2.52 +/- 6.71度。对该体系结构的学习和泛化能力的相关结果也进行了介绍和讨论。(c) 2008 Elsevier Ltd.版权所有。
Predicting the hand and fingers posture during grasping tasks is an important issue in the frame of biomechanics. In this paper, a technique based on neural networks is proposed to learn the inverse kinematics mapping between the fingertip 3D position and the corresponding joint angles. Finger movements are obtained by an instrumented glove and are mapped to a multichain model of the hand. From the fingertip desired position, the neural networks allow predicting the corresponding finger joint angles keeping the specific subject coordination patterns. Two sets of movements are considered in this study. The first one, the training set, consisting of free fingers movements is used to construct the mapping between fingertip position and joint angles. The second one, constructed for testing purposes, is composed of a sequence of grasping tasks of everyday-life objects. The maximal mean error between fingertip measured position and fingertip position obtained from simulated joint angles and forward kinematics is 0.99 +/- 0.76 mm for the training set and 1.49 +/- 1.62 mm for the test set. Also, the maximal RMS error of joint angles prediction is 2.85 degrees and 5.10 degrees for the training and test sets respectively, while the maximal mean joint angles prediction error is -0.11 +/- 434 degrees and -2.52 +/- 6.71 degrees for the training and test sets, respectively. Results relative to the learning and generalization capabilities of this architecture are also presented and discussed. (c) 2008 Elsevier Ltd. All rights reserved.