Vision-Based Trajectory Tracking Control for High-Speed Wheeled Mobile Robots

Strategic Insights -

Researchers from Nantong University in China have developed an integrated control framework for high-speed wheeled mobile robots (WMRs) that addresses critical challenges such as multi-source noise coupling, nonholonomic motion constraints, and system uncertainties. The framework combines a dual GRU-enhanced KalmanNet state estimator with an adaptive Extended State Observer and a Nonsingular Terminal Sliding Mode Controller to achieve robust trajectory tracking with global stability and finite-time convergence.

Key Takeaways:

  • The proposed framework establishes a kinematic model and trajectory tracking error dynamics to characterize system behavior under nonholonomic constraints.
  • A dual GRU-enhanced KalmanNet state estimator (DG-KalmanNet) is designed to separately process visual measurements and system dynamics while incorporating error state constraints for physical consistency.
  • An adaptive Extended State Observer (ESO) is constructed based on state estimates to provide real-time disturbance estimation, enabling a Nonsingular Terminal Sliding Mode Controller (NTSMC) to achieve robust trajectory tracking.
  • Comprehensive simulations demonstrate significant performance improvements over traditional PID control, including an 80.0% RMSE reduction, 75.4% faster convergence, and 93.2% disturbance rejection rate.
  • Jingfeng Mao, Chenmeng Zhang, Qiuyue Qin, Aihua Wu, Xudong Zhang, and Junqiang Zheng are the authors of the research, which has been peer-reviewed.

Statistics:

  • 80.0% RMSE reduction achieved by the proposed framework over traditional PID control.
  • 75.4% faster convergence rate achieved by the proposed framework.
  • 93.2% disturbance rejection rate achieved by the proposed framework.
  • The research has been peer-reviewed and published in the journal Nonlinear Dynamics.

Sources:

  • VerticalNews (2025, October 20) - "Researchers from Nantong University Report New Studies and Findings in the Area of Robotics"
  • Nonlinear Dynamics (2025) - "Vision-based Trajectory Tracking Control for Wheeled Mobile Robots Using Dg-kalmannet and Nonsingular Terminal Sliding Mode Control"
  • Nantong University, School of Electrical Engineering and Automation - "Research on Vision-based Trajectory Tracking Control for High-Speed Wheeled Mobile Robots"