Model predictive control is one of the main methods used in path tracking for autonomous vehicles. To improve the path tracking performance of the vehicle, a path tracking method based on model predictive control with variable predictive horizon is proposed in this paper. Based on the designed model predictive controller for path tracking, the response analysis of path tracking control system under the different predictive horizons is carried out to clarify the influence of predictive horizon on path tracking accuracy, driving comfort and real-time of the control algorithm. Then, taking the lateral offset, the steering frequency and the real-time of the control algorithm as comprehensive performance indexes, the particle swarm optimization algorithm is designed to realize the adaptive optimization for the predictive horizon. The effectiveness of the proposed method is evaluated via numerical simulation based on Simulink/CarSim and hardware-in-the-loop experiment on an autonomous driving simulator. The obtained results show that the optimized predictive horizon can adapt to the different driving environment, and the proposed path tracking method has good comprehensive performance in terms of path tracking accuracy of the vehicle, driving comfort and real-time.
Reasonably foreseeable misuse by persons, as a primary aspect of safety of the intended functionality (SOTIF), has a significant effect on cooperation performance for lane keeping. This paper presents a novel human–machine cooperative control scheme with consideration of SOTIF issues caused by driver error. It is challenging to balance lane keeping performance and driving freedom when driver error occurs. A safety evaluation strategy is proposed for safety supervision, containing assessments of driver error and lane departure risk caused by driver error. A dynamic evaluation model of driver error is designed based on a typical driver model in the loop to deal with the uncertainty and variability of driver behavior. Additionally, an extension model is established for determining the cooperation domain. Then, an authority allocation strategy is proposed to generate a dynamic shared authority and achieve an adequate balance between lane keeping performance and driving freedom. Finally, a model predictive control (MPC)-based controller is designed for calculating optimal steering angle, and a steer-by-wheel (SBW) system is employed as an actuator. Numerical simulation tests are conducted on driver error scenarios based on the CarSim and MATLAB/Simulink software platforms. The simulation results demonstrate the effectiveness of the proposed method.
16 August 2024 in IEEE Transactions on Vehicular Technology
In view of the generalized functional safety problems faced by intelligent vehicles, this paper focuses on vehicle driving safety and functional insufficiency of the steering system, and proposes a path tracking coordinated control method with TD3 reinforcement learning based on vehicle danger recognition. Based on the parameters of vehicle driving stability, the concept of vehicle danger level (DL) is established by integrating the parameters of path tracking accuracy. Affinity propagation (AP) clustering algorithm is used to cluster the vehicle driving status under different road adhesion coefficients, speeds and curvatures. The results of DL recognition are added to the design of TD3 reinforcement learning reward function, and the coordination control of automatic steering and differential braking under different conditions is realized, so as to achieve high-precision path tracking control under the premise of ensuring vehicle safety. The results of CarSim/Simulink co-simulation and hardware-in-loop test show that the vehicle DL can be more accurately recognized by using AP clustering algorithm and the reinforcement learning control strategy combined with DL recognition is superior to the traditional fixed parameter MPC controller and the reinforcement learning control strategy without considering the clustering method in improving the path tracking accuracy and lateral stability of the vehicle. The training convergence speed is improved in both the variable curvature road and the docking road, in which the functional insufficiency problem of the steering system is fully alleviated in the variable curvature road, and the energy loss caused by the additional yaw moment is less in the docking road.
This paper presents a fault-tolerant human-machine shared scheme for collision avoidance considering driver error and actuator fault. A fault-tolerant method of trajectory planning and decision-making is developed for dealing with the actuator fault. We calculate the remainder trajectory tracking capability of the faulted actuator and utilise the motion redundancy in the system to generate feasible fault-tolerant trajectories for collision avoidance. In addition, an assessment criterion of driver error is conducted to supervise the driver's steering response to the potential collision and actuator fault. The shared system dynamically adjusts the driving authority based on the driver error. A model predictive control (MPC) algorithm is employed for tracking the fault-tolerant trajectory. Simulation and hardware-in-the-loop (HIL) experiment results demonstrate the effectiveness of the presented approach, reducing traffic accidents due to driver error and actuator fault.
5 July 2023 in Transactions of the Institute of Measurement and Control
The control goal of the vehicle platoon is to maintain the same speed and desired distance. Most current studies are based on simplified vehicle models, and the leader’s state is also rarely considered. However, under complex working conditions, such as low adhesion or curves, the lateral stability of the platoon will be difficult to guarantee, and tracking errors of desired speed and spacing may further increase. To solve the above problems, a new hierarchical coordinated control strategy is proposed. Taking distributed drive electric vehicles (DDEVs) as research objects, the upper control level establishes a stability situation assessment model according to the vehicle’s dynamic characteristics. At the medium control level, variable weight model predictive control (MPC) coordinates conflicts between longitudinal tracking and lateral stability. A correction term is also introduced to revise the prediction model. At the same time, the weight of different control objectives of the leader and following vehicle was adjusted, respectively. Torque distribution is carried out at the lower level controller. Finally, the control strategy is tested on a hardware-in-the-loop (HIL) platform. The results show that the proposed control strategy can ensure lateral stability while improving the tracking performance of the vehicle platoon.
1 January 2009 in Journal of Mechanical Engineering