Precision Immobilization Technique (PIT) is a potentially effective intervention maneuver for emergency out-of-control vehicle, but its automation is challenged by highly nonlinear collision dynamics, strict safety constraints, and real-time computation requirements. This work presents a PIT-oriented neural optimal-control framework built around PicoPINN (Planning-Informed Compact Physics-Informed Neural Network), a compact physics-informed surrogate obtained through knowledge distillation, hierarchical parameter clustering, and relation-matrix-based parameter reconstruction. A hierarchical neural-OCP (Optimal Control Problem) architecture is then developed, in which an upper virtual decision layer generates PIT decision packages under scenario constraints and a lower coupled-MPC (Model Predictive Control) layer executes interaction-aware control. To evaluate the framework, we construct a PIT Scenario Dataset and conduct surrogate-model comparison, planning-structure ablation, and multi-fidelity assessment from simulation to scaled by-wire vehicle tests. In simulation, adding the upper planning layer improves PIT success rate from 63.8% to 76.7%, and PicoPINN reduces the original PINN parameter count from 8965 to 812 and achieves the smallest average heading error among the learned surrogates (0.112 rad). Scaled vehicle experiments are further used as evidence of control feasibility, with 3 of 4 low-speed controllable-contact PIT trials achieving successful yaw reversal.

翻译：精密截停技术（Precision Immobilization Technique, PIT）是针对失控紧急车辆的一种潜在有效干预手段，但其自动化面临高度非线性碰撞动力学、严格安全约束及实时计算需求的挑战。本研究提出了一种面向PIT的神经最优控制框架，其核心是PicoPINN（规划驱动的紧凑型物理信息神经网络）——一种通过知识蒸馏、层次化参数聚类及基于关系矩阵的参数重构获得的紧凑型物理信息替代模型。进一步，我们开发了一种分层神经最优控制问题架构：上层虚拟决策层在场景约束下生成PIT决策方案，下层耦合模型预测控制层执行交互感知控制。为评估该框架，我们构建了PIT场景数据集，开展了替代模型对比、规划结构消融实验以及从仿真至线控缩比车辆的多保真度评估。仿真结果表明，引入上层规划层使PIT成功率从63.8%提升至76.7%，PicoPINN将原始PINN参数量从8965缩减至812，并在学习型替代模型中取得了最小的平均航向误差（0.112弧度）。缩比车辆实验进一步验证了控制可行性：在4次低速可控接触式PIT试验中，有3次成功实现了横摆反转。