Max Robotics — Global Service Robot Directory + US Certification

About

Yasutomo Kawanishi is a leading researcher in human-robot interaction, multimodal emotion recognition, and autonomous robotic systems. His most impactful work, "Audio and Video-based Emotion Recognition using Multimodal Transformers" (25 citations), achieves state-of-the-art performance in extracting human emotions from audio-visual data using deep learning sensor fusion—a critical capability for natural human-robot collaboration. Kawanishi also pioneered the Butsukusa conversational mobile robot (8 citations), which autonomously describes its observations and internal states during patrolling tasks, advancing transparency in autonomous systems. His research extends to analyzing driver eye-gaze behavior for robotic wheelchair operation (7 citations), improving safety for inexperienced users, and predicting future human poses from 3D skeleton sequences (7 citations) to enable proactive robot responses. Additional contributions include open-set scene graph generation for robot vision and next-viewpoint recommendation for accurate object pose estimation. With a growing citation record spanning emotion recognition, assistive robotics, and scene understanding, Kawanishi’s work directly addresses the challenge of creating robots that perceive, interpret, and respond to complex human environments—making him a key figure in developing socially aware, autonomous systems for real-world applications.