18054298. UNSUPERVISED LOCATION ESTIMATION AND MAPPING BASED ON MULTIPATH MEASUREMENTS simplified abstract (QUALCOMM Incorporated)
Contents
- 1 UNSUPERVISED LOCATION ESTIMATION AND MAPPING BASED ON MULTIPATH MEASUREMENTS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 UNSUPERVISED LOCATION ESTIMATION AND MAPPING BASED ON MULTIPATH MEASUREMENTS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Abstract
- 1.6 Bullet Points
- 1.7 Potential Applications
- 1.8 Problems Solved
- 1.9 Benefits
- 1.10 Original Abstract Submitted
UNSUPERVISED LOCATION ESTIMATION AND MAPPING BASED ON MULTIPATH MEASUREMENTS
Organization Name
Inventor(s)
Shreya Kadambi of San Diego CA (US)
Arash Behboodi of Amsterdam (NL)
Joseph Binamira Soriaga of San Diego CA (US)
UNSUPERVISED LOCATION ESTIMATION AND MAPPING BASED ON MULTIPATH MEASUREMENTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18054298 titled 'UNSUPERVISED LOCATION ESTIMATION AND MAPPING BASED ON MULTIPATH MEASUREMENTS
Simplified Explanation
Abstract
Certain aspects of the present disclosure provide methods, apparatus, and systems for predicting the location of a device in a spatial environment using a machine learning model. The method involves measuring signals received from a network entity at the device and generating a channel state information (CSI) measurement from these signals. The CSI measurement includes a multipath component. The positions of one or more anchors in the spatial environment are identified based on a machine learning model trained to identify these positions using the CSI measurement. Finally, the location of the device is estimated based on the identified positions of the anchors.
Bullet Points
- Method for predicting the location of a device in a spatial environment using a machine learning model
- Measures signals received from a network entity and generates a channel state information (CSI) measurement
- CSI measurement includes a multipath component
- Identifies positions of one or more anchors in the spatial environment using a machine learning model trained on the CSI measurement
- Estimates the location of the device based on the identified positions of the anchors
Potential Applications
- Indoor navigation: This technology can be used to accurately locate devices in indoor environments, enabling applications such as indoor navigation systems.
- Asset tracking: By accurately predicting the location of devices, this technology can be used for asset tracking in various industries, such as logistics and manufacturing.
- Location-based services: The ability to estimate device location can enhance location-based services, such as targeted advertising or personalized recommendations based on the user's location.
Problems Solved
- Accurate device location estimation: This technology solves the problem of accurately estimating the location of a device in a spatial environment, even in the presence of multipath signals.
- Machine learning-based approach: By using a machine learning model trained on channel state information, this technology overcomes the limitations of traditional localization methods and provides more accurate results.
Benefits
- Improved accuracy: The use of a machine learning model trained on channel state information allows for more accurate device location estimation compared to traditional methods.
- Cost-effective: This technology utilizes existing network signals and does not require additional infrastructure, making it a cost-effective solution for device localization.
- Versatility: The method can be applied to various spatial environments and can work with different types of devices, making it a versatile solution for location prediction.
Original Abstract Submitted
Certain aspects of the present disclosure provide methods, apparatus, and systems for predicting a location of a device in a spatial environment using a machine learning model. An example method generally includes measuring a plurality of signals received from a network entity at a device. A channel state information (CSI) measurement is generated from the measured plurality of signals. Generally, the CSI measurement includes a multipath component. Positions of one or more anchors in a spatial environment are identified based on a machine learning model trained to identify the positions of the one or more anchors based on the CSI measurement. A location of the device is estimated based on the identified positions of the one or more anchors.
