arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01655cs.LGeess.SP
收藏

变换不变生成射线路径采样用于高效无线电传播建模

Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling

OPTIT S.r.l.(OPTIT公司)

Jérome Eertmans, Enrico M. Vitucci, Vittorio Degli-Esposti, Nicola Di Cicco, Laurent Jacques, Claude Oestges

AI总结:

提出基于生成流网络的机器学习框架,通过智能采样替代穷举搜索,实现高效无线电传播建模,在理想街道峡谷场景中GPU加速达10倍、CPU加速达100倍。

摘要:

射线追踪已成为精确无线电传播建模的标准方法,但其计算复杂度呈指数增长,因为候选路径数量随物体数量的交互阶数而增加。这一瓶颈限制了其在大型或实时应用中的使用,迫使传统工具依赖启发式方法减少路径候选,但可能牺牲精度。为克服这一限制,我们提出了一种机器学习辅助框架,通过生成流网络进行智能采样,取代穷举路径搜索。将这些生成模型应用于该领域面临挑战,特别是由于有效路径的稀缺性导致的稀疏奖励,这可能导致在复杂环境中评估高阶交互时收敛失败和琐碎解。为确保鲁棒学习和高效探索,我们的框架包含三个关键组件。首先,经验回放缓冲区捕获并保留稀有的有效路径。其次,统一探索策略提高了泛化能力,防止过拟合简单几何形状。第三,基于物理的动作掩蔽策略在模型考虑之前过滤掉物理上不可能的路径。在理想街道峡谷场景上的验证表明,我们的模型相比穷举搜索实现了显著加速——GPU上最高10倍,CPU上最高100倍——同时保持高覆盖精度并成功发现复杂传播路径。然而,在真实曼哈顿街道几何形状上的分布外评估显示,泛化到显著不同的城市形态需要模型容量或训练策略的进一步改进。源代码、测试和教程见https://github.com/jeertmans/sampling-paths。

英文摘要:

Ray tracing has become a standard for accurate radio propagation modeling, but suffers from exponential computational complexity, as the number of candidate paths scales with the number of objects raised to the interaction order. This bottleneck limits its use in large-scale or real-time applications, forcing traditional tools to rely on heuristics that reduce path candidates at the cost of potentially reduced accuracy. To overcome this limitation, we propose a machine-learning-assisted framework that replaces exhaustive path searching with intelligent sampling via Generative Flow Networks. Applying these generative models to this domain presents challenges, particularly sparse rewards due to the rarity of valid paths, which can lead to convergence failures and trivial solutions when evaluating high-order interactions in complex environments. To ensure robust learning and efficient exploration, our framework incorporates three key components. First, an \emph{experience replay buffer} captures and retains rare valid paths. Second, a uniform exploratory policy improves generalization and prevents overfitting to simple geometries. Third, a physics-based action masking strategy filters out physically impossible paths before the model considers them. Validated on idealized street-canyon scenarios, our model achieves substantial speedups over exhaustive search -- up to $10\times$ faster on GPU and $100\times$ faster on CPU -- while maintaining high coverage accuracy and successfully uncovering complex propagation paths. However, out-of-distribution evaluations on real-world Manhattan street geometries reveal that generalizing to substantially different urban morphologies requires further advancement in model capacity or alternative training strategies. Source code, tests, and a tutorial are available at https://github.com/jeertmans/sampling-paths.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑