用可审计的符号模型实现车辆自适应，代价是计算变慢72到102倍。
White-Box Neural Ensemble for Vehicular Plasticity: Quantifying the Efficiency Cost of Symbolic Auditability in Adaptive NMPC
- 通过模块化主权机制调度多个固定神经专家应对不同工况
- 实测适应速度仅需7.3毫秒，复合扰动下跟踪精度接近理想
- 适合需要高透明度的自动驾驶控制场景
我们提出一种白盒自适应非线性模型预测控制（NMPC）架构，通过模块化主权机制协调一组冻结的、针对特定工况的神经专家，解决车辆在无重训练情况下的可塑性问题。系统动态以完全可遍历的符号图形式在CasADi中维护，实现最大化的运行时可审计性。同步仿真验证了快速适应能力（约7.3毫秒）和在摩擦、质量、阻力等复合工况切换下的近理想跟踪性能，非自适应基线在此类情况下失效。实证基准测试量化了透明性成本：符号图维护使求解器延迟相比编译后的参数化物理模型增加72至102倍，确立了严格白盒实现的效率代价。
原文摘要 · Abstract (English)
We present a white-box adaptive NMPC architecture that resolves vehicular plasticity (adaptation to varying operating regimes without retraining) by arbitrating among frozen, regime-specific neural specialists using a Modular Sovereignty paradigm. The ensemble dynamics are maintained as a fully traversable symbolic graph in CasADi, enabling maximal runtime auditability. Synchronous simulation validates rapid adaptation (~7.3 ms) and near-ideal tracking fidelity under compound regime shifts (friction, mass, drag) where non-adaptive baselines fail. Empirical benchmarking quantifies the transparency cost: symbolic graph maintenance increases solver latency by 72-102X versus compiled parametric physics models, establishing the efficiency price of strict white-box implementation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。