Masaya Ashida

Wakayama University, The University of Osaka

Papers

Total Citations

H-Index

About

Masaya Ashida’s research career bridges two fascinating frontiers: intuitive human-robot interaction and the cognitive modeling of object understanding. In his most-cited work on mobile robot navigation (2002, 4 citations), Ashida tackled a deeply practical problem—how to guide a robot without requiring precise coordinates. By allowing users to specify goals through natural, verbal route descriptions (e.g., “turn at the large tree”), he pioneered a more accessible, user-friendly paradigm for autonomous navigation in unknown environments. This work anticipated today’s push toward natural language interfaces in robotics. Earlier, in a 1992 paper (3 citations), Ashida introduced the concept of “Functant” within a functional model for reasoning about shape, structure, and function. This theoretical contribution challenged the prevailing shape-based object models in image understanding, arguing that true recognition requires integrating what an object *does* with what it *looks like*. Though his citation counts are modest, Ashida’s ideas—especially the Functant framework—offer a prescient foundation for modern research in functional object recognition and cognitive robotics. His work remains a thoughtful touchstone for engineers and scientists exploring how machines can perceive and interact with the world in more human-like ways.