METHOD FOR ESTIMATING A METRIC OF INTEREST IN CONNECTION WITH THE MOVEMENT OF A BODY
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- FOCAL POINT POSITIONING LTD
- Filing Date
- 2019-10-11
- Publication Date
- 2026-05-06
AI Technical Summary
Inertial navigation systems using low-cost IMUs suffer from significant error drift due to sensor noise, biases, and alignment errors, leading to inaccurate positioning and navigation, especially in situations where GNSS data is unavailable or unreliable, such as indoors or in urban canyons, and conventional techniques like dead-reckoning provide reliable estimates for only a few seconds.
A method utilizing a trained machine learning algorithm to estimate a motion model using data from secondary sensors on platforms independently movable with respect to the body, constrained by a first metric obtained during a previous time period when primary positioning units are operational, allowing accurate tracking and navigation even when primary units are not operational.
Enables accurate estimation of body motion trajectories for extended periods, overcoming error drift and context changes, providing reliable navigation solutions in scenarios where conventional methods fail.