Search Results

Environmental perception is a crucial subsystem in autonomous vehicles. In order to build safe and efficient traffic transportation, several researches have been proposed to build accurate, robust and real-time perception systems. Camera and LiDAR are widely equipped on autonomous self-driving cars and developed with many algorithms in recent years. The fusion system of camera and LiDAR provides state-of the-art methods for environmental perception due to the defects of single vehicular sensor. Extrinsic parameter calibration is able to align the coordinate systems of sensors and has been drawing enormous attention. However, differ from spatial alignment of two sensors’ data, joint calibration of multi-sensors (more than two sensors) should balance the degree of alignment between each two sensors.

For an electric vehicle driven by four in-wheel motors, the torque of each wheel can be controlled precisely and independently. A closed-loop control method of differential drive assisted steering (DDAS) has been proposed to improve vehicle steering properties based on those advantages. With consideration of acceleration requirement, a three dimensional characteristic curve that indicates the relation between torque and angle of the steering wheel at different vehicle speeds was designed as a basis of the control system. In order to deal with the saturation of motor's output torque under certain conditions, an anti-windup PI control algorithm was designed. Simulations and vehicle tests, including pivot steering test, lemniscate test and central steering test were carried out to verify the performance of the DDAS in steering portability and road feeling.

In this paper, a novel method is proposed to establish the vehicle yaw stability criterion based on the sideslip angle-yaw rate (β-r) phase plane method. First, nonlinear two degrees of freedom vehicle analysis model is established by adopting the Magic Formula of nonlinear tire model. Then, according to the model in the Matlab/Simulink environment, the β-r phase plane is gained. Emphatically, the effects of different driving conditions (front wheels steering angle, road adhesion coefficient and speed) on the stability boundaries of the phase plane are analyzed. Through a large number of simulation analysis, results show that there are two types of phase plane: curve stability region and diamond stability region, and the judgment method of the vehicle stability domain type under different driving conditions is solved.

BBW (Brake-by-wire) can increase the electric and hybrid vehicles performance and safety. This paper proposes a novel mechatronic booster system, which includes APS (active power source), PFE (pedal feel emulator), ECU (electronic control unit). The system is easily disturbed when the system parameters and the outside conditions change. The system performance is weakened. The cascade control technique can be used to solve the problem. This paper develops an adaptive cascade optimum control (ACOC) algorithm based on the novel mechatronic booster system. The system is divided into main loop and servo loop, both of them are closed-loop system. The servo-loop system can eliminate the disturbance which exists in the servo loop. So the robustness of the cascade control system is improved than which of the general closed-loop control system. Different control object is respectively chosen. The control-oriented mathematical model is designed.

Vehicle sideslip angle estimation is of great importance to the vehicle stability control as it could not be measured directly by ordinary vehicle-mounted sensors. As a result, researchers worldwide have carried out comprehensive research in estimating the vehicle sideslip angle. First, as the attitude would affect the acceleration information measured by the IMU directly, different kinds of vehicle attitude estimation methods with multi-sensor fusion are presented. Then, the estimation algorithms of the vehicle sideslip angle are classified into the following three aspects: kinematic model based method, dynamic model based method, and fusion method. The characteristics of different estimation algorithms are also discussed. Finally, the conclusion and development trend of the sideslip angle estimation are prospected.

The control in transient conditions when hydraulic brake and regenerative brake switch mutually is the key technical issue about electric vehicle hybrid brake system, which has a direct influence on the braking feel of driver and vehicle braking comfort. A coordination control system has been proposed, including brake force distribution correction module and motor force compensation module. Brake force distribution correction module has fixed the distribution results in hydraulic brake force intervention condition, hydraulic brake force evacuation condition and regenerative brake force low speed evacuation condition. Motor compensation module has compensated hydraulic system with motor system, which has fast and accurate response, thus the response of whole hybrid system has been improved.

In recent years, intelligent driving technology is being extensively studied. This paper proposes a path planning method for perpendicular parking based on vehicle kinematics model using MPC optimization, which aims to solve the perpendicular parking task. Firstly, in the case of any initial position and orientation of the vehicle, judging whether the vehicle can be parked at one step according to the location of the parking place and the width of the lane, and then calculating the starting position for parking, and use the Bezier curve to connect the initial position and the starting position. Secondly, reference parking path is calculated according to the collision constraints of the parking space. Finally, because the parking path based on the vehicle kinematics model is composed of circle arcs and straight lines, the curvature of the path is discontinuous. The reference parking path is optimized using Model Predictive Control (MPC).

The research and development of data-driven highly automated driving system components such as trajectory prediction, motion planning, driving test scenario generation, and safety validation all require large amounts of naturalistic vehicle trajectory data. Therefore, a variety of data collection methods have emerged to meet the growing demand. Among these, camera-equipped drones are gaining more and more attention because of their obvious advantages. Specifically, compared to others, drones have a wider field of bird's eye view, which is less likely to be blocked, and they could collect more complete and natural vehicle trajectory data. Besides, they are not easily observed by traffic participants and ensure that the human driver behavior data collected is realistic and natural. In this paper, we present a complete vehicle trajectory data extraction framework based on aerial videos. It consists of three parts: 1) objects detection, 2) data association, and 3) data cleaning.

On the dual-motor electric vehicle, which is driven by two electric motors mounted on the front and rear axles respectively, longitudinal dynamic control and electro-dynamic braking can be achieved by controlling the torque of front and rear axle motors respectively. Suspension displacement is related to the wheel torque, thus the pitch of vehicle body can be influenced by changing the torque distribution ratio. The pitch of the body has a great influence on the vehicle comfort, which occurs mainly during acceleration and braking progress. Traditionally active suspension is adopted to control the pitch of body. Instead, in this paper an ideal torque distribution strategy is developed to limit the pitch during acceleration and braking progress. This paper first explores the relationship between the torque distribution and the body pitch through the real vehicle test, which reveals the feasibility of the vehicle comfort promotion by optimizing the torque distribution coefficient.

In this paper, by analyzing multiple electro-hydraulic brake system schemes in detail, the idea of dual-motor electro-hydraulic brake system is proposed. As a new solution, the dual-motor electro-hydraulic brake system can actively simulate pedal feel, make the most of pedal power (from the driver), and reduce the maximum power output of each active power source remarkably, which is a distinctive innovation compared to most current electro-hydraulic brake systems. Following the proposed concept, a general research thought and method is conceived, and then a dual-motor electro-hydraulic brake system is designed. Finally, the simulation model is set up in AMESim software and its feasibility is simulated and verified.

To research the dynamic response of active power source of electronic hydraulic brake system, the paper proposes a restricted distribution control strategy. Building control strategy model and active power source model to simulation with Matlab/Simulink and AMEsim, and bench test is conducted on different driving cycles, which proves that the dynamic response of active power source is fit and controllable by adjusting PID parameters.

As one of the essential parts of automatic parking system (APS), the parking motion control module directly affects the system performance and driver experience. Therefore, it is necessary to design a simple, robust and efficient trajectory tracking algorithm which adapt to the various parking conditions. Firstly, considering the predictability and the ability of dealing with various system constraints, the model predictive control (MPC) lateral controller is designed. Then, the second lateral controller based on linear quadratic regulator (LQR) algorithm is designed, which has the excellent capability of balancing the multiple performances of the system. Finally, Stanley lateral controller is designed as the benchmark for horizontal comparison. Parallel and vertical parking simulation environments are proposed to verify the effectiveness of the designed lateral controllers, and the advantages and shortcomings of each control algorithm are horizontally analyzed and summarized.

Visual sensors are widely used in autonomous vehicles (AVs) for object detection due to the advantages of abundant information and low-cost. But the performance of visual sensors is highly affected by low light conditions when AVs driving at nighttime and in the tunnel. The low light conditions decrease the image quality and the performance of object detection, and may cause safety of the intended functionality (SOTIF) problems. Therefore, to analyze the performance limitations of visual sensors in low light conditions, a controlled light experiment on a proving ground is designed. The influences of low light conditions on the two-stage algorithm and the single-stage algorithm are compared and analyzed quantificationally by constructing an evaluation index set from three aspects of missing detection, classification, and positioning accuracy.

Recent researches in autonomous driving mainly consider the uncertainty in perception and prediction modules for safety enhancement. However, obstacles which block the field-of-view (FOV) of sensors could generate blind areas and leaves environmental uncertainty a remaining challenge for autonomous vehicles. Current solutions mainly rely on passive obstacles avoidance in path planning instead of active perception to deal with unexplored high-risky areas. In view of the problem, this paper introduces the concept of information entropy, which quantifies uncertain information in the blind area, into the motion planning module of autonomous vehicles. Based on model predictive control (MPC) scheme, the proposed algorithm can plan collision-free trajectories while actively explore unknown areas to minimize environmental uncertainty. Simulation results under various challenging scenarios demonstrate the improvement in safety and comfort with the proposed perception-aware planning scheme.

With the development of brake-by-wire technology, electro-hydraulic composite braking technology came into being. This technology distributes the total braking force demand into motor regenerative braking force and hydraulic braking force, and can achieve a high energy recovery rate. The existing composite braking control belongs to single-channel control, i.e., the four wheel braking pressures are always the same, so the hydraulic braking force distribution relationship of the front and rear wheels does not change. For single-axle-driven electric vehicles, the additional regenerative braking force on the driven wheels will destroy the original braking force distribution relationship, resulting in reduced braking efficiency of the driven wheels, which are much easier to lock under poor road adhesion conditions.

Many learning-based methods estimate ego-motion using visual sensors. However, visual sensors are prone to intense lighting variations and textureless scenarios. 4D radar, an emerging automotive sensor, complements visual sensors effectively due to its robustness in adverse weather and lighting conditions. This paper presents an end-to-end 4D radar-visual odometry (4DRVO) approach that combines sparse point cloud data from 4D radar with image information from cameras. Using the Feature Pyramid, Pose Warping, and Cost Volume (PWC) network architecture, we extract 4D radar point features and image features at multiple scales. We then employ a hierarchical iterative refinement approach to supervise the estimated pose. We propose a novel Cross-Modal Transformer (CMT) module to effectively fuse the 4D radar point modality, image modality, and 4D radar point-image connection modality at multiple scales, achieving cross-modal feature interaction and multi-modal feature fusion.

Accurate and reliable localization in GNSS-denied environments is critical for autonomous driving. Nevertheless, LiDAR-based and camera-based methods are easily affected by adverse weather conditions such as rain, snow, and fog. The 4D Radar with all-weather performance and high resolution has attracted more interest. Currently, there are few localization algorithms based on 4D Radar, so there is an urgent need to develop reliable and accurate positioning solutions. This paper introduces RIO-Vehicle, a novel tightly coupled 4D Radar/IMU/vehicle dynamics within the factor graph framework. RIO-Vehicle aims to achieve reliable and accurate vehicle state estimation, encompassing position, velocity, and attitude. To enhance the accuracy of relative constraints, we introduce a new integrated IMU/Dynamics pre-integration model that combines a 2D vehicle dynamics model with a 3D kinematics model.