Max Robotics — Global Service Robot Directory + US Certification

About

Reina Ishikawa is a pioneering roboticist whose research sits at the intersection of robotic manipulation, multimodal perception, and food science. Her most impactful work, "Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation" (13 citations), introduces a novel paradigm where robots learn to predict and adapt to the brittle fracture of foods during handling—a critical skill for autonomous cooking and food processing. This work, along with its follow-up on reusable fragile objects, addresses the fundamental challenge of inter- and intra-category diversity in food properties, moving beyond preset physical models to real-time, learning-based anticipation. Ishikawa also excels in multimodal sensing, as evidenced by her contributions to audio-visual hybrid approaches for filling mass estimation (10 citations) and the CORSMAL benchmark (9 citations), which tackles the difficult problem of estimating container weight and content during human-to-robot handovers. Her self-supervised audio-visual feature learning for terrain clustering (8 citations) demonstrates a versatile ability to extract robust features from noisy, multimodal data. With over 44 total citations across these key works, Ishikawa is shaping the future of robots that can safely and intelligently interact with the fragile, variable, and opaque objects of our everyday world.