We investigate the task and motion planning problem for Signal Temporal Logic (STL) specifications in robotics. Existing STL methods rely on pre-defined maps or mobility representations, which are ineffective in unstructured real-world environments. We propose the \emph{Structured-MoE STL Planner} (\textbf{S-MSP}), a differentiable framework that maps synchronized multi-view camera observations and an STL specification directly to a feasible trajectory. S-MSP integrates STL constraints within a unified pipeline, trained with a composite loss that combines trajectory reconstruction and STL robustness. A \emph{structure-aware} Mixture-of-Experts (MoE) model enables horizon-aware specialization by projecting sub-tasks into temporally anchored embeddings. We evaluate S-MSP using a high-fidelity simulation of factory-logistics scenarios with temporally constrained tasks. Experiments show that S-MSP outperforms single-expert baselines in STL satisfaction and trajectory feasibility. A rule-based \emph{safety filter} at inference improves physical executability without compromising logical correctness, showcasing the practicality of the approach.

翻译：本文研究了机器人学中信号时序逻辑（STL）规范下的任务与运动规划问题。现有STL方法依赖于预定义地图或移动性表示，在非结构化现实环境中效果有限。我们提出**结构化专家混合STL规划器**（**S-MSP**），这是一个可微分框架，能够将同步的多视角相机观测与STL规范直接映射为可行轨迹。S-MSP在统一流程中集成STL约束，通过结合轨迹重建与STL鲁棒性的复合损失进行训练。一种**结构感知**的专家混合（MoE）模型通过将子任务投影至时间锚定嵌入，实现了对规划时域的自适应专业化。我们在具有时序约束任务的工厂物流场景高保真仿真中对S-MSP进行评估。实验表明，S-MSP在STL满足率与轨迹可行性方面均优于单专家基线模型。推理阶段采用的基于规则的**安全过滤器**在不影响逻辑正确性的前提下提升了物理可执行性，验证了该方法的实用性。