Enhancing MPC-Based MCA Through Deep Learning for Adaptive Tuning

High-fidelity motion cueing in driving simulators is essential for delivering a realistic and immersive user experience. However, the trade-off between motion accuracy and computational efficiency often hinders achieving this. Fixed-horizon Model Predictive Control (MPC)-based Motion Cueing Algorithm (MCA) frameworks frequently struggle to adapt to rapid dynamic changes in vehicle behaviour, resulting in suboptimal simulator responses. Their reliance on worst-case horizon tuning can result in inefficient platform usage and increased computational load, limiting computational efficiency and practical deployment. This study presents an adaptive MPC-based MCA designed to enhance the fidelity of motion platforms used in vehicle dynamic simulations. The proposed method dynamically adjusts the MPC prediction horizon to improve overall simulation performance while minimising motion sensation error. Within the simulation environment, the prediction horizon is adaptively updated at each simulated control step according to recent tracking-performance metrics, enabling responsiveness to varying vehicle dynamic models and driving scenarios. The system was developed and implemented using Python and MATLAB environments, with Long Short-Term Memory (LSTM) networks employed to enhance the adaptability and precision of prediction horizon adjustments. Due to safety constraints, the proposed framework was evaluated exclusively within a simulation environment and compared against both classical MPC-based MCA and RL MPC-based MCA. Experimental results demonstrate that the proposed adaptive framework improves workspace utilisation and substantially reduces computational load compared with the classical and RL-based MPC-based MCA approaches, while maintaining competitive motion cueing tracking performance. The adaptive system effectively enhances linear displacement (LD), ensuring better alignment of motion cues with platform constraints. While minor trade-offs were observed in root mean square error (RMSE) and correlation coefficients (CCs) for sensed angular velocity (SAV) and sensed specific force (SSF), the framework improves workspace utilisation and computational efficiency while maintaining competitive motion cueing performance. Furthermore, the adaptive LSTM-MPC framework substantially reduces computational load, achieving approximately 44.26 times faster execution compared with the classical MPC-based MCA and approximately 30.03 times faster execution compared with the RL MPC-based MCA. These findings highlight the potential of integrating deep learning (DL) with MPC to optimise the trade-off between motion cueing performance, platform utilisation, and computational efficiency in driving simulators.