基于深度分离卷积的情绪识别机器人即时交互研究

Research on real-time interaction for the emotion recognition robot based on depthwise separable convolution

情绪识别是人工智能领域的研究热点,人机交互系统若能感知人类的情感行为并能表达情感,将会使机器人与人类的交互更加自然。人类主要通过面部表情、语义语调、肢体语言等几个方面获取情感信息。以拥有高自由度的NAO机器人为应用平台,设计了机器人面部情绪识别和肢体情感表达的人机交互系统。首先,引入深度分离卷积算法对人脸表情(生气、恐惧、伤心、高兴、惊讶和中性)进行特征提取和分类,结果表明通过训练得到的网络模型对FER2013人脸表情测试集的预测正确率可以达到0.711;其次,设计NAO机器人的肢体动作,对6种面部情感做出了分类;最后,对机器人实时表达使用者的情绪状态进行了测试,反馈时间均在2 s内,并对连续10帧预测结果进行了统计分析。

Emotion recognition is a research hotspot in the field of artificial intelligence. If the human-robot interaction system can perceive human emotional behavior and express emotion, it will make the interaction between robot and human more natural. Humans acquire emotional information mainly through facial expression, semantic intonation and body language. Taking the NAO robot with high degree of freedom as an application platform, a human-robot interaction system is designed for facial emotion recognition and body emotion expression. Firstly, the depthwise separable convolution algorithm is introduced to extract and classify features of facial expressions(e.g., angry, fear, sad, happy, surprise and neutral). Results showed that the prediction accuracy of FER2013 facial expression test set could reach 0.711 by the trained network model. Secondly, the body movement of NAO robot are designed and classified according to six facial emotions. Finally, the real-time expression of the user′s emotional state by the robot is tested, and the feedback time is within 2 s. The statistical analysis of the prediction results of 10 consecutive frames is carried out.