Dynamic Geofencing via Vehicle Sensor Data Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional map data lacks information on newer businesses and secondary characteristics, making it difficult for fleet managers to create geofences around entities without traditional identifiers, such as specific business names or addresses, limiting their ability to restrict vehicle usage or travel based on dynamic observations.
Innovation Solution
A system that uses vehicle data snapshots, processed by a processor, to compare characteristics with a database of known features, allowing for the dynamic identification and geofencing of instances not typically included in map data, such as businesses or areas, by analyzing data from sensors like cameras, LIDAR, and wireless communication systems, and updating geofences in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional map data is used for geofencing, then geofences can be created around known businesses with traditional identifiers, but geofences cannot be created around newer businesses or entities without traditional identifiers
Solution Approach 1:
The system performs preliminary actions by deploying vehicles equipped with sensors to capture data snapshots of locations before traditional map data is updated. These snapshots include images, LIDAR data, and other sensor readings that document the presence of businesses and entities. This preliminary data collection enables geofencing to be established around newer businesses and entities without traditional identifiers, resolving the contradiction between adaptability and information loss.
Solution Approach 2:
The system introduces an intermediary mechanism - a database of characteristic data derived from vehicle sensor snapshots - that bridges the gap between physical entities and traditional map data. This intermediary database stores characteristic features (visual appearance, layout, sensor signatures) that can be matched against snapshot data to identify entities for geofencing, even when traditional identifiers are absent, thus enabling geofences around entities previously excluded by traditional map data limitations.
2Adaptability or versatility
If vehicle data snapshots are analyzed to identify instances, then geofences can be established around entities without traditional identifiers, but the system complexity increases
Solution Approach 1:
The system extracts only the essential characteristic features from complex vehicle data snapshots - such as visual appearance, structural layout, and key sensor signatures - and stores these extracted characteristics in a database. This extraction process separates the critical identification features from the overwhelming amount of raw sensor data, enabling efficient comparison and matching without requiring the full complexity of original snapshots to be processed each time, thus managing system complexity while maintaining adaptability.
Solution Approach 2:
The system creates simplified copies of entity characteristics from vehicle snapshots - storing representative feature sets that capture the essential identity of each entity without replicating the full complexity of original sensor data. These characteristic copies enable rapid comparison and identification operations, reducing computational complexity while preserving the ability to identify entities for geofencing purposes.
3Measurement precision
If characteristic data is continuously updated and refined, then identification accuracy improves, but data processing time and computational resources increase
Solution Approach 1:
The system applies partial action by selectively updating and refining characteristic data only when necessary - such as when new entity types are encountered or when confidence in identification falls below thresholds. Rather than continuously processing all data, the system intervenes partially to improve accuracy only where needed, balancing identification precision with acceptable processing time and resource consumption.
Data Source
AI summary
A system receives a vehicle data snapshot. The system compares characteristics of the vehicle data snapshot to a database of known characteristics, the known characteristics identifying one or more instances corresponding to an instance type identified in a geo-fence request, the instance types in the geo-fence request having been submitted for geo-fencing around occurrences of instances of the instance type. Responsive to identifying an existence of an instance at a location where the vehicle data snapshot was taken, based on the comparison, the system establishes a geo-fence around the identified instance and transmits the established geo-fence to one or more vehicles associated with the geo-fence request.