Abstract
Navigating low-light or unfamiliar environments presents significant hazards, as traditional global positioning systems (GPS) lack granular proximity awareness and frequently fail indoors. A system and method are disclosed for a wearable device, such as extended reality glasses, that uses multi-spectral sensor fusion to generate real-time three-dimensional proximity and navigation maps. The system can be configured to fuse data from near-infrared active illumination, direct time-of-flight sensors, ultra-low-light red, green, blue (RGB) cameras, integrated sensing and communication (ISAC) signals, and/or barometric sensors. A tiered sensor activation strategy also manages power consumption based on environmental needs. The processed sensor data can be combined with floor plans and artificial intelligence mapping to provide localized navigational guidance, outputting synthesized visual overlays or spatial audio alerts to safely route users around obstacles.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Bhattacharya, Arunoday; Adiraju, Vidyadhar Ramakrishna; and Wu, Qiuxuan, "Low-Light Vicinity Navigation Using Multi-Spectral Sensor Fusion", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12040