用共享参数的神经网络生成控制序列，提升非线性模型预测控制的安全性与效率
Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling
- 通过时序共享参数设计神经控制策略，降低在线计算负担
- 仅需少量专家数据即可实现高可行性控制序列，闭环安全性显著提升
- 适合高维系统且训练更稳定，适用于嵌入式实时控制场景
非线性模型预测控制（NMPC）的实际部署常受限于在线计算：在高控制频率下求解非线性规划对嵌入式硬件压力大，尤其当模型复杂或预测时域长时。基于学习的NMPC将计算移至离线阶段，但通常需要大量专家数据和昂贵训练。本文提出Sequential-AMPC，一种通过在预测时域内共享参数生成候选控制序列的时序神经策略。部署时，通过安全增强的在线评估与回退机制封装该策略，形成安全型的Safe Sequential-AMPC。在多个基准测试中，相较于基线前馈策略，Sequential-AMPC所需专家MPC回滚次数显著减少，候选序列可行性更高，闭环安全性更优。在高维系统上，其学习动态更佳，收敛更快，且验证性能稳定提升，而基线策略易陷入停滞。
原文摘要 · Abstract (English)
The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on embedded hardware, especially when models are complex or horizons are long. Learning-based NMPC approximations shift this computation offline but typically demand large expert datasets and costly training. We propose Sequential-AMPC, a sequential neural policy that generates MPC candidate control sequences by sharing parameters across the prediction horizon. For deployment, we wrap the policy in a safety-augmented online evaluation and fallback mechanism, yielding Safe Sequential-AMPC. Compared to a naive feedforward policy baseline across several benchmarks, Sequential-AMPC requires substantially fewer expert MPC rollouts and yields candidate sequences with higher feasibility rates and improved closed-loop safety. On high-dimensional systems, it also exhibits better learning dynamics and performance in fewer epochs while maintaining stable validation improvement where the feedforward baseline can stagnate.
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。