Multimodal Command Grounding for Telepresence Robot Navigation using Vision–Language Perception and Classical Planning
Abstract
This framework enables telepresence robots to execute multimodal commands (speech/text and pointing) by grounding them into Semantic Waypoints. It integrates di-rectly with ROS 2 Nav2 to ensure safer, more predictable indoor navigation in dynamic environments such as healthcare facilities, offices, and smart homes.
Fields of Study & Subjects
Robot Manipulation and Learning
Robotics and Sensor-Based Localization
Speech and dialogue systems
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 15 February 2026
- Language
- EN
- Document type
- Dataset