Search Results

Abstract Precise controls of vehicle states are crucial to automated vehicles (AVs). Traditional model-based AV control algorithms require complex modeling and controller design, and their accuracy is still affected a lot by various uncertainties. Latest data-driven controls such as artificial neural network (ANN)-based controls can reduce modeling efforts but are usually subject to robustness issues in unseen scenarios. This article proposes to combine a data-driven control and a typical analytical model-formed control to achieve a better AV longitudinal control performance with fewer modeling efforts. The data-driven control can handle the complex modeling, calibration, and controller design, and the analytical model-formed control can guide the direction of the control with better predictability and robustness in unseen scenarios. The proposed controller is experimentally implemented and validated using a real AV.

Abstract Weather conditions such as rain, fog, snow, and dust can adversely impact sensing and perception, limit operational envelopes, and compromise the safety and reliability of advanced driver-assistance systems and autonomous vehicles. Physical testing of an autonomous system in a weather laboratory and on-road is costly and slow and exposes the system to only a limited set of weather conditions. To overcome the limitations of physical testing, a physics-based simulation workflow was developed by coupling computational fluid dynamics (CFD) with optical simulations of camera and lidar sensors. The computational data of various weather conditions can be rapidly generated by CFD and used to assess the impact of weather conditions on the sensors and perception algorithms.

Abstract Rigorous assessment of knock control systems is complicated by the fact that single experiments or simulations give results that are nonrepeatable due to the random arrival of knock events. Assessment of the closed-loop transient response to disturbances, in particular, is often very limited but this is critical for effective controller design and calibration. In this study, recent methods to estimate the statistical properties of the closed-loop response are extended to include the effects of random disturbances in order to excite and quantify both the transient and steady-state performance of the controller. A variety of assessment metrics are developed as well as a new cost function that embeds both the increased knock risk as the spark is advanced, and the cost of lower engine efficiency and Indicated Mean Effective Pressure (IMEP) as the spark is retarded.

Abstract In recent years, to avoid the failure of the onboard perception system, intelligent vehicle infrastructure cooperative systems have been attracting attention in the field of autonomous vehicles. Using the perception technology of roadside sensors to provide supplementary traffic information for autonomous vehicles has become an increasing trend. Several roadside perception solutions select deep learning for three-dimensional (3D) object detection. However, deep learning methods have several issues and lack reliability in practical engineering applications. To tackle this challenge, this study proposes a pedestrian detection algorithm based on roadside Light Detection And Ranging (LiDAR) by combining traditional and deep learning algorithms. To meet real-time demand, Octree with region-of-interest (ROI) selection is introduced and improved to filter the background in each frame, which improves the clustering speed.

Abstract In order to enhance the path-tracking accuracy and adaptability of the electric flatbed vehicle (EFV) in the soft-target vehicle test system, an improved controller is designed based on the linear quadratic regulator (LQR) algorithm. First, the LQR feedback controller is designed based on the EFV dynamics tracking error model, and the genetic algorithm is utilized to obtain the optimal weight coefficient matrix for different speeds. Second, a weight coefficient matrix compensation strategy is proposed to address the changes in the relationship between the vehicle–road position and attitude caused by external disturbances and the state of EFV. An offline parameter table is created to reduce the computational load on the microcontroller of EFV and enhance real-time path-tracking performance. Furthermore, an adaptive preview time control strategy is added to reduce the overshooting caused by control delay. This strategy is based on road curvature and traveling speed.

Abstract This article proposes a control framework which combines the longitudinal and lateral motion control of the path-following task for Autonomous Ground Vehicles (AGVs). In terms of lateral motion control, a modified kinematics model is introduced to improve the performance of path following, and Brain Emotional Learning–Based Intelligent Controller (BELBIC) is applied to control the heading direction. In terms of longitudinal motion control, a safe speed is derived from the road condition, and a Proportional-Integral (PI) controller is implemented to force the AGV to drive at the desired speed. In addition, for a better performance of path-following and driving stability, Particle Swarm Optimization (PSO) algorithm is used to tune the parameters of BELBIC. In this article, a Carsim and Simulink joint simulation is provided to verify the effectiveness of the modified model and the control framework.

Abstract The concept of making a two-wheeled self-stabilizing vehicle can be a possibility soon. These vehicles use control moment gyroscopes (CMGs) to provide enough torque for the vehicle to prevent it from rolling and falling to the ground. CMGs can be used with different numbers and configurations. In this article, the aim is to offer a design procedure for a double gyroscope system, which can be used for any two-wheel vehicle to be self-stabilized. The procedure is based on using optimization algorithms in reaching the optimum double gyroscope configuration for a certain two-wheel vehicle to reach a zero-degree roll angle in the least time possible, which is the novel part of the procedure. A design procedure for a double gyroscope with the yaw axis as a spinning axis for a two-wheel vehicle is offered. This procedure has been tested for both a small two-wheel robot and a two-wheel enclosed vehicle.

Abstract The present article addresses the gain scheduling of proportional-integral-differential (PID) controllers using fuzzy set theory coupled with a metaheuristic optimization technique to control the vehicle nonlinear suspension system. The nonlinearities of the vehicle suspension system are due to the asymmetric piecewise dampers, quadratic tire stiffness, and the cubical spring stiffness. Conventional PID controller suffers from the low performance subject to modeling nonlinearities, while fuzzy logic controller (FLC), as a universal approximator, has the capacity to deal with the nonlinear, stochastic, and complex models. However, finding the optimal Mamdani FLC rules is still a challenging task in addition to a proper architecture of the membership functions (MFs). As a remedy to this drawback, particle swarm optimization (PSO) technique is employed in this article to improve the efficiency of the FLC-based PID controllers.

Abstract The steering centers of four wheels for passenger car do not coincide, which may result in tire wear and the unharmoniously movement of the vehicle. In this article, an optimization control method for Four Wheel Independent Steering (4WIS) electric vehicle based on the coincidence degree of steering centers is proposed, to improve the driving performance. The nonlinear vehicle model of the four-wheel independent steering vehicle is established, and the formula of the wheel steering center is derived. The coincidence degree of wheel steering centers is defined as the evaluation index, to describe and evaluate the performance of the coordination for wheels’ movement. Meanwhile, the structure design of 4WIS system and the establishment of Direct-Current (DC) steering motor model are carried out, and the Model Predictive Control (MPC) controller for steering actuator is designed.

Abstract The article analyzes the nonlinear optimal control problem for powertrains in hybrid electric vehicles, which comprise a diesel engine, a hybrid (doubly)-excited synchronous machine (generator/motor), and an AC/DC converter. In generator functioning mode, the diesel engine provides torque for the turn motion of the synchronous machine’s rotor. Next, the AC output voltage of the hybrid excited synchronous machine is turned into DC voltage with the use of AC to DC converters and is distributed through a DC voltage bus while also being used for charging the vehicle’s batteries. The dynamic model of the HEV powertrain, being initially expressed in a nonlinear and multivariable state-space form, undergoes approximate linearization around a temporary operating point that is recomputed at each time-step of the control method. The linearization relies on first-order Taylor series expansion and on the associated Jacobian matrices.

Abstract In this article, compared with traditional Remote Parameter Control (RPC), the iterative process is improved based on linear transfer function (TF) estimation of the nonlinear dynamic system. In the improved RPC, the iteration coefficient is designed according to the convergence condition of the nonlinear iterative process, so that the convergence level, convergence speed, and iteration stability could be improved. The difference between the traditional and the improved RPC iterative process is discussed, the RPC iterative process of the nonlinear system is analyzed, and channel decoupling for Multi-Input Multi-Output (MIMO) system based on eigen-decomposition of the system TF and linear TF estimation is introduced. It assumes that the eigenvector matrix of the system TF remains the same, and the linear TF in the iterative process is estimated and updated, which is used for iterative calculation.

Abstract An integrated vehicle dynamics control system aiming to improve vehicle handling and stability by coordinating active front steering (AFS), direct yaw control (DYC), and electric differential system is developed in this article. First, an electric differential system for electric vehicle, composed of two sets of bi-PMS, in-wheel motors connected in parallel and supplied by a single five-leg inverter, one on the front axle and one on the rear axle, is designed. However, each set is controlled by a proposed sliding mode backstepping control, which has replaced the hysteresis controllers in the conventional direct torque control (DTC), can obviously reduce the torque ripple, and provide better speed tracking performance using sliding mode speed controllers.

Abstract The latest-generation spark-ignition (SI) engines implement high-tumble flow design to achieve unprecedented high brake thermal efficiency of over 40%, which will continue to play an important role in both conventional and future electrified vehicles. To maximize the potential of high-tumble SI engines, there is a clear need for in-cylinder flow and flame analysis conducted timely in a realistic environment. For the first time, this study meets this need by performing innovative endoscopic imaging of flow fields and flame inside the cylinder of a selected production engine using a particle image velocimetry (PIV) laser and high-speed camera system operated at 35 kHz. Through this time-resolved, two-dimensional measurement of the realistic in-cylinder phenomenon, many new findings have been achieved.

Abstract Connected and automated vehicles have attracted more and more attention, given the benefits in safety and efficiency. This research proposes a novel model predictive control method in order to improve energy efficiency and ensure a safe spacing between vehicles. The proposed algorithm focuses on mixed traffic flow, which is more realistic than one that only includes autonomous vehicles. A high-fidelity energy loss model of an electric vehicle is adopted to improve the control’s performance. A data-driven car-following model using machine learning is integrated in the framework of model predictive control to predict the behavior of human-driven vehicles. Its effectiveness in increasing energy efficiency is validated under two driving cycles.

Abstract Recognition of the necessity of connected and automated vehicles (CAVs) in transportation systems is gaining momentum. CAVs can improve the transportation network efficiency and safety by sharing information and cooperative control. This article addresses the problem of coordinating CAVs at highway on-ramps to achieve smooth traffic flow. We develop a multi-agent reinforcement learning (MARL) method based on value decomposition and centralized control to coordinate CAVs. The simulation results show that the proposed collaborative decision-making framework can effectively coordinate dynamic traffic flows and improve the metrics by more than 10% compared to the baseline methods under high traffic demand scenarios.

Abstract The millimeter-wave radar has good weather robustness, but currently lacks performance in object classification. With the advent of imaging radar, three-dimensional (3D) point clouds of objects can be obtained. Based on 3D radar point clouds, an support vector machine (SVM algorithm using 3D features is proposed to solve poor radar classification performance. First, a new 29-feature vector is proposed from many perspectives, such as shape features, statistical features, and other features. Then the SVM classifier with four different kernel functions and other machine learning methods are used to achieve multi-objective classification. Finally, experiments are carried out on three types of datasets collected by ourselves, and the results show that the algorithm achieves a 95.1% classification accuracy, which is 15.7% higher than the traditional 2D radar point cloud.

Abstract Advances made in advanced driver assistance systems such as antilock braking systems (ABS) have significantly improved the safety of road vehicles. ABS enhances the braking and steerability of a vehicle under severe braking conditions. However, ABS performance degrades on rough roads. This is largely due to noisy measurements, the type of ABS control algorithm used, and the excitation of complex dynamics such as higher-order tire mode shapes that are neglected in the control strategy. This study proposes a model-free intelligent control technique with no modelling constraints that can overcome these unmodelled dynamics and parametric uncertainties. The double deep Q-learning network (DDQN) algorithm with the temporal convolutional network is presented as the intelligent control algorithm. The model is initially trained with a simplified single-wheel model.

Abstract During certain driving scenarios, low-speed engine vibrations get propagated to the driveline and affect the drivability of a vehicle. To reduce the impact of these vibrations, a locked torque converter lockup clutch (TCC) is allowed to temporarily slip to increase the damping in the driveline. However, the initial slow dynamics of the fluid path of the torque converter cause the vehicle to feel sluggish. In this article, we design a model predictive controller (MPC) that optimally controls the torque request from the actuator (i.e., engine or e-motor) and the lockup clutch capacity for reducing this sluggishness. The study is conducted for a light-duty vehicle and uses an experimentally validated, detailed full-order model (FOM) for developing and validating a computationally efficient, reduced-order driveline model (ROM).

Abstract The aim of this study is to achieve the target transient posture of a vehicle according to the user’s steering operation. The target behavior was hypothesized to be a roll mode in the diving pitch, even during steering inputs on rough surfaces, in order to improve subjective evaluation. As a result of organizing the issues of feedforward control (FF) and feedback control (FB), we hypothesized that it would be appropriate to follow the ideal posture. The model following damping control (MFDC) was newly proposed by the authors as a solution to a control algorithm based on model-following control. The feature employs skyhook control (SH), which follows the deviation between the behavior of the reference model, which generates a target behavior with no input from the road surface, and the actual behavior of the vehicle. Numerical analyses were performed to verify the followability of the target behavior and the effect of roll damping performance.

Abstract Super duplex stainless steel (SDSS) is a type of stainless steel made of chromium (Cr), nickel (Ni), and iron (Fe). In the present work, a 1.6 mm wide thin sheet of SDSS is joined using gas tungsten arc welding (GTAW). The ideal parameter for a bead-on-plate trial is found, and 0.216 kJ/mm of heat input is used for welding. As an outcome of the welding heating cycle and subsequent cooling, a microstructural study revealed coarse microstructure in the heat-affected zone and weld zone. The corrosion rate for welded joints is 9.3% higher than the base metal rate. Following the corrosion test, scanning electron microscope (SEM) analysis revealed that the welded joint’s oxide development generated a larger corrosive attack on the weld surface than the base metal surface. The percentages of chromium (12.5%) and molybdenum (24%) in the welded joints are less than those in the base metal of SDSS, as per energy dispersive X-ray (EDX) analysis.