In this paper, an improved Model Predictive Control (MPC) controller based on fuzzy adaptive weight control is proposed to solve the problem of autonomous vehicle in the process of path tracking. The controller not only ensures the tracking accuracy, but also considers the vehicle dynamic stability in the process of tracking, i.e., the vehicle dynamics model is used as the controller model. Moreover, the problem of driving comfort caused by the application of classical MPC controller when the vehicle is deviated from the target path is solved. This controller is mainly realized by adaptively improving the weight of the cost function in the classical MPC through the fuzzy adaptive control algorithm. A comparative study which compares the proposed controller with the pure-pursuit controller and the classical MPC controller is made: through the CarSim-Matlab/Simulink co-simulations, the results show that this controller presents better tracking performance than the latter ones considering both tracking accuracy and steering smoothness.

/pdf/path-tracking-control-for-autonomous-vehicles-based-on-an-3h5f73ai4x.pdf

Path Tracking Control for Autonomous Vehicles Based on an Improved MPC

This paper presents a probabilistic decision-making framework for rear-end collision avoidance systems, focusing on modeling the impact of major collision-causing factors on the occurrence of accidents. Decisions on when and how to assist drivers are made using a Bayesian network approach according to collision risk evaluation results, given a prior probabilistic knowledge. The structure of the Bayesian network model is learnt using a K2 algorithm with a practical dataset. To provide adequate response time for drivers, we also predict collision probability in the next monitoring interval using a Kalman filter model. The prediction accuracy is evaluated with different use cases and compared to real scenarios with the obtained dataset. To make our framework more relevant to practical applications, we also discuss the corresponding safety control strategies by classifying collision risk into high and low levels. In addition, the proposed model is evaluated through experiments including simulations and road tests. In the simulations, the algorithms are tested in different scenarios with various configurations of weather conditions, driver response capability, and vehicular dynamics. In order to demonstrate collision avoidance performance, the proposed model is also compared to existing schemes. In the road tests, the algorithm is embedded into an unmanned vehicle with predefined parameters to evaluate the impact of computational complexity on rear-end collision avoidance. Numerical results show that the proposed model provides an accurate estimation for car-following collision risk with a relatively low complexity, taking into account the impacts of vehicle dynamics, driver reaction capacity, and external environment on rear-end collisions.

A Rear-End Collision Risk Evaluation and Control Scheme Using a Bayesian Network Model

Automotive driving safety systems such as an anti-lock braking system (ABS) and an electronic stability program (ESP) assist drivers in controlling the vehicle to avoid road accidents. In this paper, ABS and the ESP, based on the fuzzy logic theory, are integrated for vehicle stability control in complex braking maneuvers. The proposed control algorithm is implemented for a sport utility vehicle (SUV) and investigated for braking on different surfaces. The results obtained for the vehicle software simulator confirm the robustness of the developed control strategy for a variety of road profiles and surfaces.

https://www.mdpi.com/2076-3417/6/12/382/pdf

Design and Simulation of the Robust ABS and ESP Fuzzy Logic Controller on the Complex Braking Maneuvers

A multi-layer integrated controller of active front steering and direct yaw moment is developed in this study. In the upper layer, the corrective steering angle and yaw moment are obtained using Sliding Mode Control (SMC) with combined sliding surface. The corrective yaw moments are applied by electric motors embedded in rear wheels. The desired value for yaw rate and sideslip angle are obtained from a Four-Degrees of Freedom (DOF) non-linear vehicle model. In the lower layer, wheel slip and electric motor torque controllers are designed. A 9-DOF non-linear vehicle model is used for simulations and their results illustrate considerable improvements in vehicle handling.

Integrated AFS/DYC sliding mode controller for a hybrid electric vehicle

A yaw stability control system is proposed to improve the handling and stability of a four-independent-wheel drive Electric Vehicle (EV). The control system comprises an Active Front Steering (AFS) controller together with a direct yaw moment controller based on Sliding Mode Control (SMC) and a dynamic force distribution controller based on the optimal Sequential Quadratic Programming Method (SQPM). The function of the control system is to trace the desired yaw rate and meanwhile to keep the sideslip angle of the body Centre of Gravity be minimised. The optimum torque distribution method is applied to adjust the torque of all four wheels. By measuring the vehicle states, the control algorithm determines the level of vehicle stability and intervenes when necessary through individual wheel traction control to provide added stability and handing predictability. The controller system distributes torque and power to each motor to meet the requirements of each wheel. The effectiveness and validation of the proposed control method are evaluated by experiments and simulations. The results manifest that the designed system can assist drivers in controlling the EV's stability during adverse driving manouevres and enhance its performance.

Yaw stability control of a four-independent-wheel drive electric vehicle

In this paper, a fuzzy control method is proposed to improve vehicle yaw stability by integrated yaw moment control and active front steering. This control system is designed by actively controlling the front steering angle and the distribution of braking forces, using feed-forward regulation and feedback revision control strategy, and a fuzzy controller is designed to suppress the output error of yaw rate and side slip angle, which can keep the vehicle to follow the desired trajectories. A simulation based on this control method is performed with a vehicle at two different running conditions, and the simulation results by other different control methods are compared also. The results showed that the presented method can effectively control the yaw rate and side slip angle synchronously, the transient and steady response of vehicle is good, the vehicle yaw stability is improved.

A Fuzzy Control Method to Improve Vehicle Yaw Stability Based on Integrated Yaw Moment Control and Active Front Steering

A yaw stability controller based on generalized predictive control is presented in this paper. The predictive and the desired model of yaw rate are established based on a linearized vehicle model, the future output of yaw rate of the vehicle according to the information of vehicle speed and the steering wheel angle is predicted. Compared with a desired value, a controlling yaw moment is calculated based on the difference between the desired and the actual yaw rate. The predictive control of parameter model applied to the yaw stability control system based on GPC, in the known model situation, can predict the future output of yaw rate of the vehicle precisely and take control action before the yaw instability of vehicle occurs, so this method suits the yaw stability control system of vehicle. The simulation result indicates the yaw rate based on GPC algorithm can track the desired yaw rate well. Compares with the PID control algorithm, the curve of yaw rate has no obvious surge, and the overshoot reduces greatly.

A Research on Generalized Predictive Control for Vehicle Yaw Rate

Based on speed changing and lane changing, it is divided into 6 driving intentions in the 2 dimensions, which are speed-up and lane-changing, keep speed and lane-changing, speed-down and lane-changing, speed-up and keep lane, keep speed and keep lane, and speed-down and lane-changing. Considering the continuity of the vehicle movement, the Gaussian density function is used to improve 2D HMM, based on which the driving intentions were identified. The headway, object speed and lateral acceleration is the input, and output driving intentions. Speed-changing and lane changing or not are chose to the 2 dimensions of C-P2D-HMM's hidden variable. The results of simulation show that the method is right and effective, whose identification accuracy is 98.84%. Otherwise, it can realize prediction by the transition probability to warn the abnormal driving and reduce traffic accidents caused by it.

Driving Intentions Identification Based on Continuous Pseudo 2D Hidden Markov Model

A probability model of automobile rear end collision based on ANFIS(adaptive neural-fuzzy inference systems) was provided, the speed difference of automobiles, the speed of tracing automobile and the distance of automobiles were taken as inputs, and the probability of automobile rear end collision was taken as output. The probability of automobile rear end collision was calculated in different speed difference and distance of automobiles using the model. The probability model provides a new plan for analysing automobile rear end collision, and has directive role for decreasing automobile rear end collision on freeway. 3 tabs, 1 fig, 6 refs.

Automobile rear end collision model on freeway

Established the computational model about the safe distance of vehicles. In order to simulate the dynamic model of rear-end, based on VB software to build a freeway rear-end simulation system. Simulation system provides an important means for in-depth study on rear-end probability. To investigate the non-linear relationship of probability and impact factors of rear-end, established probability of rear-end accident prediction model based on BP neural network. To simulation data obtained by the training and testing samples, the simulation results show that the rear-end based on BP neural network model has a high probability of accuracy, on the rear-end collisions has some practical significance.

Wu Yihu

Papers

A Fuzzy Control Method to Improve Vehicle Yaw Stability Based on Integrated Yaw Moment Control and Active Front Steering

A Research on Generalized Predictive Control for Vehicle Yaw Rate

Driving Intentions Identification Based on Continuous Pseudo 2D Hidden Markov Model

Automobile rear end collision model on freeway

Study on Probabilistic Model of Rear-end Based on BP Neural Network