Coordinated Control of Intelligent Vehicle Stability and Trajectory Tracking Based on Stability-Region Identification

To solve the conflict between trajectory tracking and stability control for distributed drive electric vehicles under complex driving conditions, an integrated longitudinal and lateral coordinated control strategy based on a hierarchical architecture is proposed in this paper. First, a stability-boundary dataset is constructed using an improved sum-of-squares programming (ISOSP) algorithm. Then, a long short-term memory (LSTM) network is optimized with the sparrow search algorithm (SSA). Finally, a prediction model is established to identify the dynamic stability region in real time. A hierarchical architecture is adopted for the control strategy. The upper layer integrates longitudinal–lateral tracking and stability control to describe the desired motion states accurately. In the middle layer, a stability margin is defined based on the stability region, and a risk factor is introduced to reconstruct the optimization objective. Through this design, the coordinated control of trajectory tracking and vehicle stability is achieved. In the lower layer, the minimization of the tire-workload rate is taken as the objective, and the optimal allocation of four-wheel torque is realized through quadratic programming. Hardware-in-the-loop (HIL) tests based on an NI PXIe-1078 real-time simulator, a host computer, and a domain controller indicate that the proposed strategy achieves good control performance under both variable-speed high-adhesion and high-speed low-adhesion double lane change (DLC) conditions. Especially in the extreme condition of high speed and low adhesion, the root-mean-square errors (RMSEs) of lateral displacement and sideslip angle are controlled within 0.4125 m and 0.0365 rad, respectively. Consequently, the high-precision tracking capability and real-time stability maintenance of the coordinated control strategy under extreme conditions are successfully verified.