A cloud-edge combined control system with MPC parameter optimization for path tracking of unmanned ground vehicle

As a new carrier to carry out intelligent task, the unmanned ground vehicle (UGV) is an important component of the intelligent transportation system (ITS) in the future. Most of traditional UGV path tracking control methods are deployed in the edge-side (on-board computing platform) with restricted data, which severely limits the improvement of UGVs’ path tracking performance. Therefore, this paper proposes a novel cloud-edge combined control system with MPC parameter optimization based on cloud brain control center (CBCC) applied in future ITS, which consists of edge-side control module and cloud-side optimization module. The proposed control system can optimize control parameters iteratively in CBCC by making the utmost of big data generated by UGVs to markedly enhance the control effectiveness. In CBCC, the path tracking performance is quantitatively evaluated from the aspects of path tracking accuracy, vehicle stability, and control stability. Also, an optimization algorithm is established by using SVR theory. Based on this, the cloud-side optimization module optimizes the control parameters of the edge-side control module by collecting and processing the big data generated by UGVs while driving. Besides, the designed edge-side control module is based on MPC algorithm and innovatively introduces a compensator which obviously reduces the error caused by the inaccuracy of the prediction model. To verify the effectiveness of the proposed cloud-edge combined control system, numerous simulation experiments are carried out. The results shows that the proposed cloud-edge combined control system can improve UGV’s path tracking performance and have strong robustness at different speeds.