AI 中文总结
针对TDOA定位的基站部署问题，提出射线追踪辅助的MARL框架，在校园数据集上训练PPO智能体，其定位精度与传统GDOP方法相当，可选择性降低定位误差。
AI 中文摘要
设备的精确定位是新兴5G和6G网络的关键能力，依赖于有效的基站（BS）部署。传统基于几何的方法，如几何精度衰减因子（GDOP），忽略了建筑物引起的非视距（NLOS）阴影和多径导致的到达时间（TOA）偏差等现实传播效应。本文提出一种射线追踪辅助的多智能体强化学习（MARL）框架，用于基于到达时间差（TDOA）定位系统的环境感知基站部署。近端策略优化（PPO）智能体在大学校园详细3D模型生成的信道冲激响应（CIR）上进行训练，每个智能体协同部署一个基站，同时优化结合定位精度和覆盖范围的共享奖励。该方法在5个具有不同传播特性的校园区域进行评估，结果显示，学习到的策略实现了与传统基于GDOP的部署相当的定位精度，相较于更强的（均值优化）几何基线，将平均定位平均绝对误差（MAE）降低了约3%。其表现具有区域依赖性，在个别区域有明显提升（最高约14%），而在其他区域误差相当或略高。这些发现表明，在部署过程中纳入特定站点的传播数据，可匹配并选择性改进纯几何策略，为实现持续增益的进一步工作提供了动力。
英文摘要
Accurate localization of devices is a key capability for emerging 5G and 6G networks and depends on effective base station (BS) placement. Conventional geometry-based approaches such as Geometric Dilution of Precision (GDOP) ignore realistic propagation effects such as Non-Line of Sight (NLOS) shadowing and multipath-induced Time of Arrival (TOA) bias caused by buildings. This paper proposes a ray-tracing-assisted Multi-Agent Reinforcement Learning (MARL) framework for environment-aware BS placement in Time Difference of Arrival (TDOA) localization systems. Proximal Policy Optimization (PPO) agents are trained on Channel Impulse Responses (CIRs) generated from a detailed 3D model of a university campus. Each agent cooperatively places one BS while optimizing a shared reward that combines localization accuracy and coverage. The approach is evaluated on five campus segments with varying propagation characteristics. Results show that the learned policy achieves localization accuracy comparable to conventional GDOP-based placement, lowering the average localization Mean Absolute Error (MAE) by about 3 % relative to the stronger (mean-optimized) geometric baseline. The behavior is segment-dependent, with a clear improvement on individual segments (up to about 14 %) and comparable or slightly higher error on the others. These findings indicate that incorporating site-specific propagation data into the placement process can match and selectively improve upon purely geometric strategies, motivating further work toward consistent gains.
Commentsto be published in conference proceedings of IEEE PIMRC 2026
