R1-2409480
discussion
Discussion on AI/ML-based positioning enhancement
From ZTE
ZTE's prior position on
9.1.2
at
RAN1#118bis
· AI-synthesized, paraphrased
verify sources →
Strongly supports maximizing reuse of existing 3GPP procedures and advocates for CIR with phase information over PDP for better positioning accuracy despite higher overhead, while also favoring sample-based measurements over path-based approaches.
Summary
ZTE presents a comprehensive contribution on AI/ML-based positioning enhancements for Rel-19, containing 30 proposals and 11 observations across model input, output, training, and monitoring. The document strongly favors sample-based measurements over path-based ones due to reduced implementation ambiguity and argues for the inclusion of phase information (CIR) in model inputs despite higher signaling overhead.
Position
ZTE proposes supporting sample-based measurements for Rel-19 AI/ML positioning, arguing that implementation ambiguities in path-based measurements cannot be removed, whereas sample-based ambiguities can be resolved via LMF configuration. They require the starting point of Nt samples to be configurable by the LMF (Option C/D) to ensure consistent positioning performance across different TRP implementations. ZTE supports using Channel Impulse Response (CIR) including phase information for model input, presenting technical evidence that CIR provides significantly better positioning accuracy than Power Delay Profile (PDP) with acceptable overhead increases. They oppose introducing a specific indicator to identify AI/ML-derived measurements, arguing that LMF awareness of the procedure and timestamp suffices. For model monitoring, ZTE proposes that label-free monitoring is implementation-specific and requires no specification discussion, while supporting LMF-centric metric calculation for Case 1. They also argue against introducing an associated ID for AI/ML positioning, stating that UE-side generalization can be handled via mixed dataset training.
Key proposals
- Proposal 1 (Model Input): Supports Option C/D for determining the starting time of Nt consecutive samples, where the starting point is determined by a pre-configured/configured timing difference relative to a reference time.
- Proposal 6 (Model Input): Proposes supporting sample-based measurements for time domain channel measurements in Rel-19 AI/ML positioning, citing clearer implementation details and unified UE/TRP behavior compared to path-based measurements.
- Proposal 10 (Model Input): Proposes using phase information (CIR) for determining model input, arguing that the positioning performance gain outweighs the slightly higher signaling overhead compared to PDP.
- Proposal 13 (Model Output): Proposes that for Case 3a, the LOS/NLOS indicator should be mandatorily supported in measurement reports from gNB to LMF, with the quality of the indicator optionally supported.
- Proposal 16 (Model Output): Proposes that an indicator identifying whether a measurement is based on an AI/ML model is not needed for reporting model output.
- Proposal 18 (Model Training): Proposes reusing existing IEs for label quality indicators: horizontalUncertainty for location information and NR-TimingQuality for timing information.
- Proposal 20 (Model Training): Proposes enhancing UE-initiated DL PRS configuration (Option A) to include the suggested number of activated TRPs in the on-demand PRS request.
- Proposal 22 (Model Training): Proposes that the association between Part A (measurements) and Part B (labels) can be determined by the model training entity using timestamps and UE IDs.
- Proposal 24 (Model Training): Proposes that there is no need to introduce an associated ID for AI/ML positioning, as UE implementation can judge alignment with training data limitations.
- Proposal 26 (Model Monitoring): Proposes supporting Option B-1 and B-2 for label-based model monitoring metric calculation in Case 1, where the LMF performs the calculation using inference results sent by the UE.
- Proposal 29 (Model Monitoring): Proposes that model monitoring metric calculation and model monitoring functions can be located in the same or different entities for UE-side and NG-RAN-side models.
- Proposal 30 (Model Monitoring): Proposes that UE capability for AI/ML positioning should be reported per use case (Case 1, 2a, 2b).