In modern industrial production, trajectory tracking control of multi-degree-of-freedom robotic arms entails safety and efficiency. This study focuses on a two-degree-of-freedom manipulator, developing a mechanical dynamics model and implementing a parallel Linear Active Disturbance Rejection Controller (LADRC) for joint control. To enhance robustness and responsiveness, a hybrid adaptive control method is introduced, integrating adaptive laws (AL) for online tuning of parameters and offline optimization using the Deep Deterministic Policy Gradient (DDPG) algorithm. This improves tracking control efficiency and effectiveness. Additionally, offline reinforcement learning refines parameters without adding real-time computational demands. Finally, semantic web principles ensure interpretability and transparency of the control flow. Compared to traditional LADRC, the proposed method shows superior anti-interference capabilities and dynamic performance.
The improvement of the partially integrated reinforcement learning-model predictive control (RL-MPC) system is developed in the paper by introducing the Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithms. This framework differs from the traditional ones, which completely substitute the MPC prediction model; instead, an RL agent refines predictions through feedback correction and thus maintains interpretability while improving robustness. Most importantly, the study details two configuration paradigms: decoupled (offline policy application) and coupled (online policy update) and tests them for their effectiveness in trajectory tracking tasks within simulation and real-life experiments. A decoupled framework based on TD3 showed significant improvements in control performance compared to the rest of the implemented paradigms, especially concerning Integral of Time-weighted Absolute Error (ITAE) and mean absolute error (MAE). This work also illustrated the advantages of partial integration in balancing adaptability and stability, thus making it suitable for real-time applications in robotics.
1 January 2026 in International Journal of Data Warehousing and Mining
To address adaptability limitations in conventional model predictive control, this paper proposes a data-driven dual-channel (D-Channel) adaptive framework for wheeled mobile robots. By extending the traditional single-channel architecture into a parallel dual-network configuration and integrating an offline reinforcement learning channel, the proposed method improves control precision and robustness. The D-Channel structure refines predictive outputs, while the reinforcement learning module enhances adaptability to dynamic disturbances. Comprehensive simulations and hardware-in-the-loop experiments show that the D-Channel radial basis function neural networks-model predictive control outperforms single-channel counterparts. The results demonstrate improved tracking accuracy, faster convergence, and reduced steady-state error, confirming the effectiveness of combining data-driven learning with predictive optimization for complex control tasks.