Portable Device Indoor Mapping Through Passive Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing portable electronic devices lack the ability to efficiently map and navigate indoor environments without requiring active user input, limiting their functionality and adaptability.
Innovation Solution
Portable electronic devices equipped with sensors and processors generate paths and maps of environments using machine learning techniques, correlating movement and location data to estimate probable configurations of indoor spaces, allowing passive mapping and navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If portable electronic devices use traditional active user input methods for mapping environments, then mapping accuracy can be maintained, but user convenience and ease of operation deteriorate due to requiring manual input
Solution Approach 1:
The system enables automatic environment mapping by having the portable electronic device autonomously collect location data from sensors, process this data through machine learning algorithms, and generate topological maps without requiring manual user input. The device serves itself by automatically performing tasks that would traditionally require active user participation.
Solution Approach 2:
The patent replaces manual mechanical input methods with sensor-based automated detection systems. Sensors detect location and movement data, which is then processed by machine learning algorithms to automatically generate environmental maps, substituting the mechanical user input system with an automated sensing and processing system.
2Ease of operation
If portable electronic devices implement automatic passive mapping using sensors and machine learning, then ease of operation improves, but device complexity increases due to additional sensors and processing requirements
Solution Approach 1:
The patent makes existing sensors in portable electronic devices serve multiple functions. Sensors originally designed for basic functions like motion detection or location tracking are repurposed to contribute to environment mapping by collecting data that feeds into machine learning algorithms for map generation, allowing one component to perform multiple roles.
Solution Approach 2:
The system combines sensor data collection, machine learning processing, and map generation into an integrated automated mapping system. Multiple functions including location detection, movement tracking, data processing, and map rendering are merged into a unified system that operates passively without requiring separate manual operations.
3Measurement precision
If portable electronic devices collect and process location data continuously for map generation, then mapping accuracy improves, but energy consumption increases
Solution Approach 1:
The system uses partial action by selectively processing location data only when sufficient data points are accumulated to meaningfully contribute to map generation. Rather than continuously processing every sensor reading, the machine learning algorithms process data in batches or when threshold criteria are met, reducing unnecessary computational energy consumption while maintaining mapping accuracy.
Data Source
AI summary
One or more electronic devices can map an environment based on movement or location data of the one or more electronic devices within the environment. The data can be analyzed, processed, or otherwise relied on to generate a path along which one or more of the electronic devices were carried (e.g., by a user) or located at given time over the duration of time. The path and attributes related to the environment can be analyzed (e.g., using machine learning techniques) to generate a topological or other type of map of the environment.