Multimodal data fusion for natural human-robot interaction

Wen QI; Stavros Ntalampiras; Zhengjun Yue; Zhengjun Yue; Salih Ertug Ovur; Yue Chen

The use of robots in various applications has increased significantly in recent years, leading to the need for more natural and effective human-robot interaction. One way to achieve this is through the integration of multiple modalities of data, such as vision, audio, and haptic information. Multimodal social cues, including verbal and nonverbal behaviors such as speech, body language, facial expression, and gaze, are frequently utilized in the development of natural human-robot interaction for a variety of intelligent fields, including rehabilitation, remote server management, medical assistance, and surgery. Despite their widespread use, several challenges remain in the application of these cues, including the integration of multiple sensors, the autonomy of robots, advanced control methods, and the use of artificial intelligence algorithms for image processing and speech analysis. The aim of this special session is to bring together researchers from academia and industry to address these challenges and present new theories and engineering approaches in the realm of human-robot interaction.

In this special session, we invite submissions that focus on the fusion of multimodal data for improved human-robot interaction. Topics of interest include, but are not limited to:

• Multimodal data fusion algorithms for human-robot interaction
• Human-robot interaction in dynamic environments
• Multimodal natural language processing for human-robot interaction
• Multimodal gesture recognition for human-robot interaction
• Multimodal emotion recognition for human-robot interaction
• Multimodal sensor fusion for human-robot interaction in unstructured environments
• Multiple sensors fusion for human data collection
• Data-driven kinematics and dynamics modeling
• Advanced image processing for robotics
• Multimodal signal processing for robotics

Chairs Information