用神经网络与模糊系统自适应调整模型预测控制，提升自动驾驶路径追踪稳定性。
Neural Network and ANFIS based auto-adaptive MPC for path tracking in autonomous vehicles
- 融合神经网络与ANFIS实现控制器参数在线自适应调节。
- 在三车道变道和轨迹跟踪中，误差比传统MPC降低18%~25%。
- 适合需要高动态响应的自动驾驶控制系统研发人员。
自动驾驶汽车在不断变化的环境中运行，面临多种不确定性与扰动，导致传统控制器在横向控制上表现不佳。为此，本文设计了一种基于改进粒子群优化算法调优的自适应模型预测控制（MPC）控制器。通过神经网络与自适应模糊推理系统（ANFIS）实现控制器参数的在线自适应调整。在三车道变道与轨迹跟踪测试场景中，所提方法相比标准MPC表现出更优的控制性能，最大横向误差降低18%~25%。相关代码已公开于GitHub：https://github.com/yassinekebbati/NN_MPC-vs-ANFIS_MPC。
原文摘要 · Abstract (English)
Self-driving cars operate in constantly changing environments and are exposed to a variety of uncertainties and disturbances. These factors render classical controllers ineffective, especially for lateral control. Therefore, an adaptive MPC controller is designed in this paper for the path tracking task, tuned by an improved particle swarm optimization algorithm. Online parameter adaptation is performed using Neural Networks and ANFIS. The designed controller showed promising results compared to standard MPC in triple lane change and trajectory tracking scenarios. Code can be found here: https://github.com/yassinekebbati/NN_MPC-vs-ANFIS_MPC
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。