Indoor Motion Probability Maps for Accurate Device Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Indoor navigation and localization of mobile devices is challenging due to unreliable satellite-based navigation systems and inconsistent behavior of sensors in varying indoor environments, leading to inaccurate trajectory determination and positioning errors.
Innovation Solution
Representing indoor spaces as probability maps with probabilistic representations of motion transition, using sensorial data and machine learning to predict and correct device motion, allowing for accurate trajectory estimation and localization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If satellite-based navigation systems are used for indoor positioning, then positioning capability can be achieved in open areas, but positioning becomes unreliable in enclosed or partially enclosed spaces due to line-of-sight requirements
Solution Approach 1:
The patent introduces an intermediary system consisting of wireless access points and mobile devices that act as mediators between the user and the positioning system. Instead of relying directly on satellite signals blocked by buildings, the system uses local wireless infrastructure and sensor data as intermediaries to determine position, thereby resolving the line-of-sight blockage problem
Solution Approach 2:
The patent replaces the mechanical/optical satellite-based positioning system with an electronic sensor-based system. Instead of using radio waves from satellites that require line-of-sight, the system substitutes inertial sensors (accelerometers, gyroscopes, magnetometers) and wireless signal processors to achieve positioning in enclosed spaces
2Reliability
If sensor-based indoor positioning is used, then positioning can work in enclosed spaces, but accuracy deteriorates due to sensor data quality and environmental variations
Solution Approach 1:
The patent merges multiple data sources including accelerometer data, gyroscope data, magnetometer data, and wireless signal strength data into a unified positioning system. By combining these different types of sensor and signal data, the system compensates for individual sensor limitations and environmental variations, thereby improving overall positioning accuracy while maintaining availability in enclosed spaces
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously processes sensor data and wireless signal data to refine position estimates. The probabilistic positioning algorithm uses feedback from multiple measurement sources to correct errors and improve accuracy over time, addressing the measurement precision problem while maintaining indoor positioning availability
Data Source
Figure 1
Figure 2
Figure 3A~3E
AI summary
A method and a device for determining motion of a device are described. In an example, a plurality of points-of-interest (POIs) are identified in a pedestrian area of an indoor space and, with each POI, a probabilistic representation of motion transition of a device from the POI is associated. The probabilistic representation of motion transition is indicative of a probability distribution of likely directions of motion that the device can exhibit from the POI. Further, a map of the indoor space is generated based on the association and the map is usable for ascertaining motion of the device in the indoor space.