基于RBF神经网络的人形机器人在线面部表情模仿

nicholas

基于RBF神经网络的人形机器人在线面部表情模仿

基于RBF神经网络的人形机器人在线面部表情模仿.pdf (646.81 KB, 下载次数: 1)

2016-12-7 14:34 上传

点击文件名下载附件
下载积分: 金钱 -1

基于RBF神经网络的人形机器人在线面部表情模仿

黄忠1,2, 任福继1,3, 胡敏1

1. 合肥工业大学计算机与信息学院, 安徽 合肥 230009; 2. 安庆师范学院物理与电气工程学院, 安徽 安庆 246011; 3. 德岛大学工学部, 日本 徳岛 770800

Online Facial Expression Imitation for Humanoid Robot Based on RBF Neural Network

HUANG Zhong1,2, REN Fuji1,3, HU Min1

1. School of Computer and Information, Hefei University of Technology, Hefei 230009, China; 2. School of Physics and Electronic Engineering, Anqing Normal College, Anqing 246011, China; 3. Faculty of Engineering, University of Tokushima, Tokushima 770800, Japan

摘要 针对有限数目电机以及手工设置面部表情控制参数的局限，结合基于 Kinect 的主动外观模型，提出一种基于径向基函数神经网络的人形机器人在线面部表情模仿算法．在离线面部表情学习阶段，基于径向基函数网络建立前向机械模型以反映电机控制值与表情形变特征的映射关系，并进一步构建逆向预测模型以规整电机连续运动的平滑度；在在线面部表情模仿阶段，基于前向机械模型和逆向预测模型寻找最优电机值以实现机器人与表演者形变偏差的最小化，并引入权重因子调节表情模仿的瞬时相似度和电机连续运动的平滑度．最后，从均值统计和预测偏差角度验证两模型的合理性和泛化能力，并进一步讨论了权重因子对时空相似性和平滑度的影响．实验结果表明：前向机械模型形变预测偏差不超过 1%，逆向预测模型电机控制偏差不超过 1.5%．与 Jaeckel、Trovato、Magtanong 三种方法相比，本文算法在单帧表情模仿相似度以及多帧表情动作平滑度方面均具较好优势． 关键词 ： 人形机器人,  径向基函数神经网络,  在线面部表情模仿,  面部表情相似度,  动作平滑度    Abstract：To overcome the limitations in manually setting the control parameters of facial expressions with motors of limited number, an online facial expression imitation algorithm is proposed for humanoid robot based on RBF (radial basis function) neural network by combining the Kinect based AAM (active appearance model). In the offline facial expression learning phase, a forward mechanic model is modeled based on RBF networks to reflect the mapping relationship between the motor control values and the facial deformation characteristics, and an inverse prediction model is further developed for wrapping the smoothness of continuous motor movements. In the online facial expression imitating phase, optimal motor values are solved to minimize deformation deviations between the robot and the performer, based on the forward mechanic model and the inverse prediction model; moreover, a weighting factor is introduced to adjust the instantaneous similarity of expression imitation and the smoothness of motor's continuous motion. Finally, the rationality and generalization ability of the two models are validated from the perspective of mean statistics and prediction deviations, and the influence of weighting factor on space-time similarity and smoothness is further discussed. The experimental results indicate that the deformation deviations of the forward mechanic model are less than 1%, and the motor control deviations of the inverse prediction model are less than 1.5%. Compared with the three methods of Jaeckel, Trovato and Magtanong, the proposed algorithm has advantages in the similarity of single-frame expression imitation and the smoothness of multi-frame expression motion. Key words： humanoid robot           RBF (radial basis function) neural network           online facial expression imitation           facial expression similarity           motion smoothness 收稿日期: 2015-07-29      1: TP249 基金资助:国家自然科学基金（61432004）；国家自然科学基金青年科学基金（61300119）；情感计算与先进智能机器安徽省重点实验室开放课题（ACMIM150106）；安徽省教育厅自然科学研究项目（AQKJ2015B013） 通讯作者: 黄忠，huangzhong3315@163.com    E-mail: huangzhong3315@163.com 作者简介: 黄忠（1981-），男，博士生，讲师.研究领域：人机情感交互，机器人控制. 任福继（1959-），男，博士，教授.研究领域：自然语言处理，人形机器人，人机情感交互. 胡敏（1967-），女，博士，教授.研究领域：计算机视觉，情感计算，人脸表情识别. 引用本文:    黄忠, 任福继, 胡敏. 基于RBF神经网络的人形机器人在线面部表情模仿[J]. 机器人, 2016, 38(2): 225-232.         HUANG Zhong, REN Fuji, HU Min. Online Facial Expression Imitation for Humanoid Robot Based on RBF Neural Network. ROBOT, 2016, 38(2): 225-232.