Scholarlink

<p>This paper proposes an adaptive-neural-network based robust hierarchical path-tracking controller for autonomous four-wheel-independent-drive electric vehicles (4WID-EVs) with parametric uncertainties and external disturbances. Firstly, considering the uncertain tire cornering stiffness and longitudinal speed, a control-oriented mismatched norm bounded uncertain system model of 4WID-EVs is established by using Takagi–Sugeno (T–S) fuzzy modeling approach. Secondly, an adaptive integral sliding mode controller combined with radial basis function neural network (RBFNN) is proposed, in which an improved RBFNN is used to approximate uncertain dynamics to improve tracking performance and reduce chattering. A sufficient condition for the asymptotic stability of sliding mode dynamics is given based on linear matrix inequality. According to Lyapunov theory, it has been proved that the estimation errors are bounded and finally converge near the origin. Further, a novel torque vectoring algorithm is introduced to allocate longitudinal driving force and additional yaw moment, aiming to reduce tire load rate and slip energy consumption, in which the weights assigned to the two objective functions are determined by taking into account the customized vehicle stability index and slip rate. Finally, the simulation results conducted on the CarSim-Simulink platform confirm the outstanding tracking and energy-efficient performance of the proposed controller.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive-Neural-Network-Based Robust Hierarchical Path-Tracking Control of Autonomous Vehicles Considering Parametric Uncertainties and Tire Slip

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • Danyang Li,
  • Youqun Zhao,
  • Shuo Guo,
  • Fen Lin,
  • Tao Xu

摘要

This paper proposes an adaptive-neural-network based robust hierarchical path-tracking controller for autonomous four-wheel-independent-drive electric vehicles (4WID-EVs) with parametric uncertainties and external disturbances. Firstly, considering the uncertain tire cornering stiffness and longitudinal speed, a control-oriented mismatched norm bounded uncertain system model of 4WID-EVs is established by using Takagi–Sugeno (T–S) fuzzy modeling approach. Secondly, an adaptive integral sliding mode controller combined with radial basis function neural network (RBFNN) is proposed, in which an improved RBFNN is used to approximate uncertain dynamics to improve tracking performance and reduce chattering. A sufficient condition for the asymptotic stability of sliding mode dynamics is given based on linear matrix inequality. According to Lyapunov theory, it has been proved that the estimation errors are bounded and finally converge near the origin. Further, a novel torque vectoring algorithm is introduced to allocate longitudinal driving force and additional yaw moment, aiming to reduce tire load rate and slip energy consumption, in which the weights assigned to the two objective functions are determined by taking into account the customized vehicle stability index and slip rate. Finally, the simulation results conducted on the CarSim-Simulink platform confirm the outstanding tracking and energy-efficient performance of the proposed controller.