RTLS Sensor-to-Sensor Training Data Collection for Asset Location
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional real-time location systems (RTLS) for asset tracking require manual data collection, which is costly, logistically challenging, and intrusive, often necessitating security clearance and interfering with customer operations.
Innovation Solution
An automated data collection method for RTLS using sensor-to-sensor communication to generate training data for the machine learning model, simulating beacon signals from different positions within zones using an RSSI-to-distance relation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If manual data collection is used to train RTLS ML model, then training data can be obtained, but it increases cost, time consumption, and operational disruption
Solution Approach 1:
The system performs self-service by automatically collecting training data through sensor-to-sensor communication without requiring manual intervention. Sensors autonomously transmit beacons and receive signals from other sensors, automatically generating the training dataset needed for ML model development.
Solution Approach 2:
The system performs preliminary actions by pre-configuring sensors with unique identifiers and pre-establishing communication protocols before data collection begins. The automated data collection process is initiated without manual setup, using pre-programmed sensor behavior to generate training data.
2Loss of information
If manual data collection is performed, then training data is gathered, but it requires security clearance and interferes with customer operations
Solution Approach 1:
The system eliminates the need for manual data collection by implementing self-service automation. Sensors automatically communicate with each other, collect signal strength data, and generate training datasets without human presence, thereby avoiding security clearance requirements and operational disruptions.
Solution Approach 2:
The patent replaces the mechanical/manual data collection process with an automated electronic system. Sensors electronically transmit and receive beacon signals, automatically processing data to generate training sets, substituting human operators with automated sensor networks.
3Extent of automation
If automated sensor-to-sensor data collection is used, then manual intervention is reduced, but system complexity increases
Solution Approach 1:
The system segments the sensor network into individual sensor units, each with standardized functionality. Each sensor independently transmits beacons and receives signals from others, allowing modular configuration and simplified management despite the automated nature of the system.
Solution Approach 2:
Sensors are designed with universal functionality to perform multiple tasks: transmitting beacons, receiving signals from other sensors, measuring signal strength, and identifying their own locations. This multi-functionality reduces the need for specialized equipment and simplifies the overall system architecture.
Data Source
AI summary
A real-time location system comprises sensors and an upstream device communicating with the sensors. Sensor pairs of the sensors include a transmitting sensor and a receiving sensor. Each sensor is assigned as the transmitting sensor in turn, while all other sensors are designated as the receiving sensors and collect signal strength data. The upstream device determines a labelled dataset based on the signal strength data for the sensor pairs and zone labels associated with the signal strength data. The RTLS ML model is trained based on the labelled dataset.