Search

This paper presents a novel model predictive adaptive cruise control strategy of intelligent electric vehicles based on deep reinforcement learning algorithm for driver characteristics. Firstly, the influence mechanism of factors such as inter-vehicle distance, relative speed and time headway (THW) on the driver's behavior in the process of car following is analyzed by the correlation coefficient method. Then, the driver behavior in the process of car following is learned from the natural driving data, the car following model is established by the deep deterministic policy gradient (DDPG) algorithm, and the output acceleration of the DDPG model is used as the reference trajectory of the ego vehicle's acceleration. Next, in order to reflect the driver behavior and achieve multi performance objective optimization of adaptive cruise control of intelligent electric vehicles, the model predictive controller (MPC) is designed and used for tracking the desired acceleration produced by the car following DDPG model. Finally, the performance of the proposed adaptive cruise control strategy is evaluated by the experimental tests, and the results demonstrate the effectiveness of proposed control strategy. [ABSTRACT FROM AUTHOR]

Advanced driving assistance systems (ADAS) such as adaptive cruise control (ACC), traffic jam assistance, and collision warning have been developed to enhance driving comfort and reduce the driving burden in car-following situations. Although these systems provide automated driving to ensure safety, those do not harmonize the intentions of the driver by reflecting individual drivers' characteristics. To ensure that system reflects driver intention, we propose a personalized longitudinal speed planning algorithm in car-following situations, which system mimics personal driving styles. Individual driving styles were characterized by designing a pedal behavior prediction model and time headway distribution prediction model. The pedal behavior prediction model is an ensemble tree-based classifier that estimates the driver's current driving state, i.e., accelerating, cruising, or braking. Then, the driver-specific time headway distribution is estimated based on the polynomial model. These two prediction models were applied to the existing sampling-based speed planning algorithm and implemented with MATLAB/Simulink. The entire speed planning algorithm was simulated using vehicle simulation software. The simulation results showed that the actual driver's driving style was successfully reproduced. [ABSTRACT FROM AUTHOR]

An eight-degree-of-freedom vehicle dynamic model with electromechanical coupling was established for a four-wheel-independent-drive electric vehicle (4WID-EV). Based on the single-point preview optimal curvature theory, an adaptive fuzzy PID driver model with lateral acceleration feedback was designed, and the control of vehicle trajectory tracking was achieved in the driver-vehicle-road closed-loop coupling model. With the sideslip angle and yaw rate as control variables, the upper layer of a fuzzy sliding mode controller and the lower layer of an optimal distribution controller of the yaw moment were designed. The optimal longitudinal forces of four driving wheels were determined to achieve vehicle-handling stability. J-turn, fishhook, and snake-shaped pile simulations were carried out in MATLAB/Simulink. The results showed that the fuzzy sliding mode controller significantly improved the driving stability of the system, and it had a better anti-chattering ability than the sliding mode control strategy. The established lateral acceleration feedback adaptive fuzzy PID driver model had good trajectory tracking ability. Integration of the two controllers can better achieve both trajectory tracking and driving stability of a 4WID-EV. [ABSTRACT FROM AUTHOR]

Lane marker detection is indispensable for a lane-keeping-control algorithm. However, it is impossible to detect lane markers when the curvature of the lane the vehicle is travelling on is large or when there is another car in front of the vehicle with short distance. For lane marker detection, it is desirable to set a preview point close to the vehicle. Therefore, by analyzing the block diagram of driver-vehicle system, we propose a method to reduce preview distance without lane tracking performance deterioration by increasing preview points from the conventional one point to two points. Furthermore, it is revealed that driving along a corner with constant curvature without steady-state deviation and arbitrary design of tracking dynamic characteristics become possible by increasing preview points. [ABSTRACT FROM AUTHOR]

Research and development involving intelligent vehicles of today is geared to safe, driver-friendly and sensitive vehicles that provide a driver with a pleasant and convenient driving environment while preventing him or her from possible risks of accident. In developing convenient and safe vehicles, research on drivers' driving patterns, reactions and state characteristics depending on road conditions in actual field is essential in order to devise more driver-friendly intelligent vehicles. This paper describes how a driver-vehicle interaction (DVI) field database is built in order to obtain a driver's input in normal road driving condition on highways, country roads, and city roads, and his or her state information, as well as data on the vehicle and traffic conditions. And the newly built database is compared with the RDCW FOT database established by UMTRI of the US for analysis to suggest that the driving tendencies of drivers in Korea and the road driving conditions are not the same as those in the US, reconfirming the need to establish a DVI field database, which will be used for the development of intelligent vehicles suitable for the Korean environment. The DVI data collected from actual driving in field are anticipated to be widely utilized as basic data for research on various intelligent driving safety systems, advanced driver assistance systems (ADAS) and human-vehicle interface (HVI) that are suitable for the driving environment in Korea. [ABSTRACT FROM AUTHOR]

A new comprehensive driver model is presented for critical maneuvering conditions with more accurate dynamic control performance. In order to achieve a safe maneuvering mode, a new path planning scheme to maintain stability of the vehicle was designed. A new steering strategy, considering the errors of vehicle position and yaw angle between the real track and the planned path, was established to obtain the steering angle. Therefore, the vehicle can be adjusted to accurately follow the desired path with the driver model, and the stability of the vehicle and the smoothness of the steering angle input were comprehensively considered. Simulation results were used to validate the control performance in comparison with the optimal preview driver model proposed by Macadam. [ABSTRACT FROM AUTHOR]