Max Robotics — Global Service Robot Directory + US Certification

About

Jan Richarz’s research lies at the intersection of human-robot interaction, computer vision, and multi-modal perception, with a central focus on enabling intuitive, non-verbal communication between people and mobile robotic assistants. A key contribution is the development of a monocular pointing pose estimator, which allows a robot to interpret a user’s pointing gesture to determine a specific target location in the environment. This work, detailed in a 2007 paper (25 citations), forms the backbone of a natural gestural instruction interface. Richarz also advanced multi-modal saliency and attention systems for smart environments (17 citations), moving beyond purely visual cues to create more robust, context-aware robotic perception. Within the long-term PERSES framework, Richarz integrated these capabilities into a probabilistic, multi-modal people tracker, enabling robots to both detect and follow human partners while understanding their gestural commands. Though the citation counts for these foundational works are modest, they represent early, influential steps toward companion robots that can understand human intent through natural, non-verbal cues—a critical capability for assistive robotics.