As a typical example of cyber-physical systems, intelligent vehicles are receiving increasing attention, and the obstacle avoidance problem for such has become hot topic discussion. This paper presents simultaneous trajectory planning tracking controller use under cruise conditions based on model predictive control (MPC) approach to address an vehicle. The reference is parameterized as cubic function in time determined by lateral position velocity vehicle yaw angle at start point lane change...

As a typical cyber-physical system (CPS), electrified vehicle becomes hot research topic due to its high efficiency and low emissions. In order develop advanced electric powertrains, accurate estimations of the unmeasurable hybrid states, including discrete backlash nonlinearity continuous half-shaft torque, are great importance. this paper, novel estimation algorithm for simultaneously identifying position torque an powertrain is proposed using approach. System models, dynamics established...

Next-generation vehicle control and future autonomous driving require further advances in dynamic state estimation. This article provides a concise review, along with the perspectives, of recent developments estimation states. The definitions used are first introduced, alternative structures presented. Then, sensor configuration schemes to estimate velocity, sideslip angle, yaw rate roll angle models for summarized, representative approaches discussed. Future concerns perspectives also

In order to improve the computational performance of extended Kalman filter (EKF) for longitudinal and lateral vehicle velocities estimation, a novel scheme EKF implementation is proposed based on field programmable gate array (FPGA) System Programmable Chip (SoPC). A Nios II processor clocked at 100 MHz embedded into FPGA chip. The created by C/C++ program runs in processor. main procedure using FPGA/SoPC technique decomposed three parts: system requirements analysis, hardware design,...

The rapid development of intelligent vehicles has paved the way for active chassis lateral stability, which is a novel issue and critical to vehicle stability handling performance. To obtain vehicles, nonlinear model predictive control (NMPC) method integrating front steering an additional yaw moment proposed. It adopts tire sideslip angle express addresses actuator security constraints properties tire-road force effectively. Moreover, hardware implementation, based on field programmable...

The recognition of driver's braking intensity is great importance for advanced control and energy management electric vehicles. In this paper, the classified into three levels based on novel hybrid unsupervised supervised learning methods. First, instead selecting threshold each level manually, an Gaussian mixture model used to cluster events automatically with brake pressure. Then, a Random Forest trained classify correct state signals vehicle powertrain. To obtain more efficient...

An online energy management controller is presented in this paper for a plug-in hybrid electric vehicle (PHEV), which based on driving conditions recognition and genetic algorithm (GA). The proposed can be used the real-time application. First, studied multimode PHEV modeled four traction operation modes are introduced detail. Second, principal component analysis (PCA) utilized to classify real historical data. Four types of constructed describe representative scenarios. Then, GA applied...

Because pixel values of foggy images are irregularly higher than those captured in normal weather (clear images), it is difficult to extract and express their texture. No method has previously been developed directly explore the relationship between semantic segmentation images. We investigated this propose a generative adversarial network (GAN) for image (FISS GAN), which contains two parts: an edge GAN GAN. The designed generate information from provide auxiliary texture Experiments on...

Connected automated vehicle (CAV) platoon control is becoming increasingly prevalent because of its unique advantages in reducing fuel consumption and improving traffic efficiency. A novel framework for CAV designed this article. First, a model predictive (MPC)-based method proposed to obtain the optimal velocity whole platoon, which both transport efficiency are taken into account optimization process. Then, distributed adaptive triple-step nonlinear strategy investigated from perspective...

Predicting the trajectory of neighboring vehicles is closely related to driving safety intelligent and supports assistance. This article proposes a dual-attention mechanism prediction method based on long short-term memory encoding that coupled with motion trend ego vehicle. The temporal attention maximizes use historical information analyses its validity under different working conditions. A spatial proposed how influence target vehicle's trajectory, combining vehicle free space reduce...

Great advances in simulation-based vehicle system design and development of various driver assistance systems have enhanced the research on improved modeling steering skills. However, little effort has been made developing skill models while capturing uncertainties or statistical properties vehicle-road system. In this paper, a stochastic model predictive control (SMPC) approach is proposed to skill, which effectively incorporates random variations road friction roughness, multipoint preview...

The roundabout is a typical changeable, interactive scenario in which automated vehicles should make adaptive and safe decisions. In this article, an optimization embedded reinforcement learning (OERL) proposed to achieve decision-making under the roundabout. promotion modified actor of Actor–Critic framework, embeds model-based method explore continuous behaviors action space directly. Therefore, can determine macroscale behavior (change lane or not) medium-scale desired acceleration time...

Drivers are being confronted by the task of controlling vehicles together with automation systems before autonomous even fully realized. A novel human-oriented online driving authority optimization shared steering framework is proposed to solve problem allocating between and human driver, in which model predictive control(MPC) method used optimize authority. The merits this that, on one hand, driver workload can be alleviated case that have similar intentions. On other has absolute control...

Piezo-actuated stages are widely applied in the field of high-precision positioning. However, piezo-actuated produce hysteresis between input voltage and output displacement that negatively influences positioning accuracy. In this paper, Bouc-Wen model is established identified using bat-inspired optimization algorithm. Subsequently, based on model, we propose a sliding mode control method with new reaching law to suppress nonlinearity achieve tracking for stages. addition, proposed contains...

Vehicle trajectory prediction plays a vital role in intelligent driving modules and helps vehicles travel safely efficiently complex traffic environments. Several learning-based methods have been developed that accurately identify vehicle behaviour patterns actual data. However, these rely on manually curated structured data are difficult to deploy vehicles. In addition, modular information channels perform detection, tracking, tasks encounter error propagation issues insufficient computing...

Prompted by emerging developments in connected and automated vehicles, parallel steering control, one aspect of driving, has become highly important for intelligent vehicles easing the burden ensuring safety human drivers. This paper presents a control framework an vehicle using moving horizon optimization. The considers lateral stability, collision avoidance actuator saturation describes them as constraints, which can blend operation driver controller effectively. Moreover, road hazard...

It is an important and essential aspect for autonomous ground vehicles to follow the desired path. In this manuscript, a path tracking controller using model predictive control (MPC) method proposed. order describe vehicle motion its dynamics, kinematics dynamics integrated first presented. Then, strategy proposed MPC employed design controller. following, stability analysis carried out it shows that system proven be asymptotically stable theoretically has no static error. validate...

Snow and ice films obscure lane lines during the winter, leading to inaccurate trajectory predictions reducing a driver's ability guide vehicle. The full use of observable information continuously infer trajectories is an urgent issue in prediction tasks. In this paper, neighboring vehicle method based on graph neural networks (GNNs) proposed, line positions attribute high-definition (HD) maps are extracted, snow mask mechanism that simulates instances which covered introduced. Because...