AI/ML Positioning via QCL Reference Signal Indication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems, particularly in 5G networks, face challenges in accurately determining the location of mobile devices due to the complexity of radio signal propagation and the need for enhanced spectral efficiency, signaling efficiency, and reduced latency.
Innovation Solution
The implementation of AI/ML models that utilize quasi co-location (QCL) relationships with reference signals to improve positioning accuracy. These models are trained to learn specific radio characteristics and site-specific features, enabling better selection and prioritization of reference signal measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If AI/ML models are used to interpret radio signal data for positioning, then positioning accuracy is improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent segments the positioning task by dividing radio signal measurements into multiple reference signal measurements (e.g., SSB and CSI-RS measurements). The AI/ML model processes these segmented measurements individually or in combinations, rather than attempting to process all possible measurements at once. This reduces the computational complexity while maintaining positioning accuracy.
Solution Approach 2:
The patent applies preliminary action by pre-training AI/ML models with simulated radio signal data before deployment. The models are pre-configured with knowledge of radio propagation characteristics, site-specific features, and measurement patterns. This preliminary preparation reduces the computational burden during actual positioning operations, as the models only need to perform inference rather than learn from scratch.
2Measurement precision
If multiple reference signal measurements are processed to improve positioning accuracy, then measurement precision is improved, but signaling overhead and processing time increase
Solution Approach 1:
The patent implements partial action by selecting and processing only the most relevant reference signal measurements for positioning, rather than processing all available measurements. The AI/ML model identifies and prioritizes measurements that contribute most to positioning accuracy, processing a subset of measurements (e.g., selecting 2-4 SSB beams out of many available). This reduces processing time while maintaining sufficient positioning accuracy.
Solution Approach 2:
The patent changes parameters by dynamically adjusting which reference signal measurements are processed based on current radio conditions, UE capabilities, and positioning requirements. The system can adaptively select measurement configurations, processing priorities, and model inference parameters to optimize the balance between accuracy and processing time for different scenarios.
3Measurement precision
If AI/ML models utilize QCL relationships with reference signals, then positioning accuracy is improved, but signaling overhead increases
Solution Approach 1:
The patent applies universality by designing the QCL indication mechanism to serve multiple functions simultaneously. The same QCL indication information is used for both beam management purposes (helping the UE identify spatially correlated beams) and positioning purposes (enabling the AI/ML model to understand relationships between reference signals). This multi-functionality reduces signaling overhead, as a single indication mechanism achieves both objectives rather than requiring separate signaling for each purpose.
Data Source
AI summary
Techniques are provided for utilizing QCL relationships with AI/ML models and reference signals. An example method for providing positioning reference signal configuration information includes receiving, from a wireless node, an indication of a quasi co-location (QCL) relationship between an AI/ML model and a reference signal, configuring one or more positioning reference signal resources based at least in part on the indication of the QCL relationship, and providing configuration information for the one or more positioning reference signal resources to the wireless node.