10 July 2024 in IEEE Transactions on Intelligent Vehicles
In this paper, a novel Enhanced Kinematic (E-Kinematic) model for Heavy-Duty Buses (HDBs) is suggested and employed to construct a robust Model Predictive Control (MPC) system for efficient path tracking. The E-Kinematic model is derived from actual vehicle yaw motion data, with its efficacy validated at both low and high speeds through frequency domain analysis. This model is then utilized in the development of a robust MPC system for the improved path tracking performance. To enhance the path tracking performance of HDBs, a new reference trajectory is introduced within the delay frame to account for the vehicle's inherent lateral motion delay. This approach prompts the vehicle to adhere to the reference trajectory based on its anticipated future state, effectively considering lateral motion delay of the vehicle. Furthermore, the output constraints of the MPC controller are designed to take into account the geometric characteristics of the vehicle, such as sidewalls and overhangs, to prevent potential lane boundary intrusion. Techniques of constraint tightening and smoothing are applied to ensure robust control in the presence of model uncertainty. The performance of the proposed system is comprehensively validated through simulations and real vehicle experiments over various curvatures.
7 August 2024 in IEEE Transactions on Intelligent Vehicles
This paper explores the consistent and reliable hands-off detection performance to overcome the limitations of rule-based methods in determining driver's steering intent, a critical component of Level 2 autonomous driving systems. Driver steering states have been distinguished based on torque sensor analysis with steering dynamics models. In this study, limitations and key causes arising from differences in steering dynamics models are identified when applied to various vehicles, leading to accuracy degradation in commercialized vehicles. To address the irregularities between hands-on and hands-off characteristics across different vehicles, an LSTM (Long Short-Term Memory) based hands-off detection model is implemented first with additional inputs from forward cameras and in-vehicle sensors, some of which have not been utilized in existing rule-based methods. The Permutation Feature Importance technique is used to extract critical input features for hands-off detection, and the performance of the optimized model is verified to validate the importance of the detected features. Next, the newly identified significant signals are then used to enhance the existing rule-based method. Through experiments, the enhanced rule-based method is compared with the existing rule-based approach and, additionally, compared with learning-based and optimized learning-based methods. Finally, an optimized strategy considering resource constraints for implementation is discussed.