Search Results

This paper proposed a novel fault-tolerant control method based on control allocation via dynamic constrained optimization for electric vehicles with XBW systems. The total vehicle control command is first derived based on interpretation on driver's intention as a set of desired vehicle body forces, which is further dynamically distributed to the control command of each actuator among vehicle four corners. A dynamic constrained optimization method is proposed with the cost function set to be a linear combination of multiple control objectives, such that the control allocation problem is transformed into a linear programming formulation. An analytical yet explicit solution is then derived, which not only provides a systematic approach in handling the actuation faults, but also is efficient and real-time feasible for in-vehicle implementation. The simulation results show that the proposed method is valid and effective in maintaining vehicle operation as expected even with faults.

In this paper, we present a model predictive controller for the autonomous vehicle lane-change maneuver. Firstly, an optimal trajectory is generated by polynomial, then, utilize it as the reference trajectory of the controller. It is well known that vehicle with nonholonomic constraints can not be feedback stabilized through continuously differentiable, time-invariant control laws. One of the advantages of MPC is the ability to handle constraints in a straightforward way. Quadratic programming is used to solve a linear MPC by successive linearization of an error model of the vehicle. Due to that the vehicle dynamics model is used, in order to prevent optimal solution cannot be obtained within the prescribed time, the relaxation factor in the objective function.

This paper presents a unified novel function-based brake control architecture, which is designed based on a top-down approach with functional abstraction and modularity. The proposed control architecture includes a commands interpreter module, including a driver commands interpreter to interpret driver intention, and a command integration to integrate the driver intention with senor-guided active driving command, state observers for estimation of vehicle sideslip, vehicle speed, tire lateral and longitudinal slips, tire-road friction coefficient, etc., a commands integrated control allocation module which aims to generate braking force and yaw moment commands and provide optimal distribution among four wheels without body instability and wheel lock or slip, a low-level control module includes four wheel pressure control modules, each of which regulates wheel pressure by fast and accurate tracking commanded wheel pressure.

High-precision and real-time ego-motion estimation is vital for autonomous vehicle. There is a lot GPS-denied maneuver such as underground parking lot in urban areas. Therefore, the localization system relying solely on GPS cannot meets the requirements. Recently, lidar odometry and visual odometry have been introduced into localization systems to overcome the problem of missing GPS signals. Compared with visual odometry, lidar odometry is not susceptible to light, which is widely applied in weak-light environments. Besides, the autonomous parking is highly dependent on the geometric information around the vehicle, which makes building map of surroundings essential for autonomous vehicle. We propose a lidar inertial odometry and mapping. By sensor fusion, we compensate for the drawback of applying a single sensor, allowing the system to provide a more accurate estimate.

Highway traffic safety has been the most serious problem in current society, statistics show that about 70% to 90% of accidents are caused by driver operational errors. The autonomous emergency braking (AEB) is one of important vehicle intelligent safety technologies to avoid or mitigate collision. The AEB system applies the vehicle brakes when a collision is eminent in spite of any reaction by the driver. In some technologies, the system forewarns the driver with an acoustic signal when a collision is still avoidable, but subsequently applies the brakes automatically if the driver fails to respond. This paper presents the development and implementation of a rear-end collision avoidance system based on hierarchical control framework which consists of threat assessment layer, wheel slip ratio control layer and integrated-electro-hydraulic brake (IEHB) actuator control layer.

Performance testing and evaluation always plays an important role in the developmental process of a vehicle, which also applies to autonomous vehicles. The complex nature of an autonomous vehicle from architecture to functionality demands even more quality-and-quantity controlled testing and evaluation than ever before. Most of the existing testing methodologies are task-or-scenario based and can only support single or partial functional testing. These approaches may be helpful at the initial stage of autonomous vehicle development. However, as the integrated autonomous system gets mature, these approaches fall short of supporting comprehensive performance evaluation. This paper proposes a novel hierarchical and systematic testing and evaluation approach to bridge the above-mentioned gap.

In order to improve drivers’ acceptance to advanced driver assistance systems (ADAS) with better adaptation, drivers’ driving behavior should play key role in the design of control strategy. Adaptive cruise control systems (ACC) have many factors that can be influenced by different driving behavior. It is important to recognize drivers’ driving behavior and take human-like parameters to the adaptive cruise control systems to assist different drivers effectively via their driving characteristics. The paper proposed a method to recognize drivers’ behavior and intention based on Gaussian Mixture Model. By means of a fuzzy PID control method, a personalized ACC control strategy was designed for different kinds of drivers to improve the adaptabilities of the systems. Several typical testing scenarios of longitudinal case were created with a host vehicle and a traffic vehicle.

Lane detection and tracking play a key role in autonomous driving, not only in the LKA System but help estimate the pose of the vehicle. While there has been significant development in recent years, traditional outdoor SLAM algorithms still struggle to provide reliable information in challenging dynamic environments such as lack of roadside landscape or surrounding vehicles at almost the same speed or on the road in the woods. On the structured road, lane markings as static semantic features may provide a stable landmark assist in robust localization. As most of the current lane detection work mainly on separated images ignoring the relationship between adjacent frames, we propose a pixel-level lane tracking method for autonomous vehicles. In this paper, we introduce a deep network to detect and track lane features. The network has two parallel branches. One branch detects the lane position, while the other extracts the point description on a pixel level.

Autonomous driving technology, as the product of the fifth stage of the information technology revolution, is of great significance for improving urban traffic and environmentally friendly sustainable development. Autonomous driving can be divided into three main modules. The input of the decision module is the perception information from the perception module and the output of the control strategy to the control module. The deep reinforcement learning method proposes an end-to-end decision-making system design scheme. This paper adopts the Deep Deterministic Policy Gradient Algorithm (DDPG) that incorporates the Priority Experience Playback (PER) method. The framework of the algorithm is based on the actor-critic network structure model. The model takes the continuously acquired perception information as input and the continuous control of the vehicle as output.

Most of the Advanced Driver Assistance System (ADAS) applications are aiming at improving both driving safety and comfort. Understanding human drivers' driving styles that make the systems more human-like or personalized for ADAS is the key to improve the system performance, in particular, the acceptance and adaption of ADAS to human drivers. The research presented in this paper focuses on the classification and identification for personalized driving styles. To motivate and reflect the information of different driving styles at the most extent, two sets, which consist of six kinds of stimuli with stochastic disturbance for the leading vehicles are created on a real-time Driver-In-the-Loop Intelligent Simulation Platform (DILISP) with PanoSim-RT®, dSPACE® and DEWETRON® and field test with both RT3000 family and RT-Range respectively.

The limitation of drivers' attention and perception may bring collision dangers, Autonomous Emergency Braking (AEB) can help drivers to avoid the potential collisions through active braking. Since the positive effect of it, motor corporations have begun to equip their vehicles with the system, and regulatory agencies in various countries have introduced test standards. At this stage, the actuator of AEB usually adopts Electronic Stability Program (ESP), but it poor performance of continuous working period and active pressure built-up for all wheels limits its implements. Electromechanical brake booster can realize power assisted brake without relying on the vacuum source and a variety of specific power curves. Moreover it can achieve the active braking with a rapid response, which make it can fulfill requirements of automotive electric and intelligent development.

With rapid increase of vehicles on the road, safety concerns have become increasingly prominent. Since the leading cause of many traffic accidents is known to be by human drivers, developing autonomous vehicles is considered to be an effective approach to solve the problems above. Although trajectory tracking plays one of the most important roles on autonomous driving, handling the coupling between trajectory-tracking control and ESP under certain driving scenarios remains to be challenging. This paper focuses on trajectory-tracking control considering the role of ESP. A vehicle model is developed with two degrees of freedom, including vehicle lateral, and yaw motions. Based on the proposed model, the vehicle trajectory is separated into both longitudinal and lateral motion. The coupling effect of the vehicle and ESP is analyzed in the paper. The lateral trajectory-tracking algorithm is developed based on the preview follower theory.

When automobile is at the threat of collisions, steering usually needs a shorter longitudinal distance than braking to avoid collision, especially at a high speed. In emergency steering evasion, the vehicle may be out of the road or colliding with obstacles ahead when the driver’s steering torque is excessive or insufficient. In view of the above problems, this paper presents an emergency steering evasion torque assistance system based on optimized trajectory. First, a feasible steering evasion area is established which treats the paths of excessive and insufficient steering as boundary conditions in this paper. An optimized trajectory is derived from the lateral acceleration of the vehicle and the time to the adjacent lane as optimization conditions. Second, a two degree of freedom vehicle model is used to represent dynamics of the vehicle.

Adaptive Cruise Control (ACC) includes three modes: cruise control, car following control, and autonomous emergency braking. Among them, the car following control mode is mainly used to manage the speed and vehicle spacing approach the preceding vehicle within the range of smooth acceleration changes. In addition, although the motion information signal of the preceding vehicle can be collected by auxiliary equipment, it is still a random variable and normally regarded as a disturbance to affect the performance of vehicle controller. Therefore, this paper proposed an ACC strategy considering the disturbance of the preceding vehicle and multi-objective optimization.

Steering torque feedback, or steering feel, is widely regarded as an important aspect of driver interface to road feel. To generate a steering feel with the appropriate level of fidelity required by a driver-vehicle system or a driving simulator, it is essential to gain a good understanding of various important influencing factors of steering torque feedback. This paper presents a comprehensive study and analysis of internal and external factors that strongly affect steering torque feedback. A steering torque feedback model with sufficient fidelity is established and verified as the base for this study. The individual- and collective-level influences of these factors on steering torque feedback are analyzed in both time domain and frequency domain, with guidelines provided on how to properly use these influencing factors to control their negative effects in modeling steering torque feedback.

Brake-by-wire (BBW) system has drawn a great attention in recent years as driven by rapidly increasing demands on both active brake controls for intelligent vehicles and regenerative braking controls for electric vehicles. However, unlike conversional brake systems, the reliability of the brake-by-wire systems remains to be challenging due to its lack of physical connection in case of system failure. There are various causes for the failure of a BBW system, such as failure of brake controller, loss of sensor signals, failure of communication or even power supply, to name a few. This paper presents a fault-tolerant control under novel control architecture. The proposed control architecture includes a driver command interpreter module, a command integration module, a control allocation module, a fault diagnosis module and state observers. The fault-tolerant control is designed based on a quadratic optimal control method with consideration of actuator constraints.

With the rapid development of modern economy and society, traffic congestion has become an increasingly serious problem. Vehicle cooperative driving can alleviate traffic congestion and improve road traffic capacity. Compare with vehicle separate control, cooperative driving combines various vehicle systems, and highly integrates information on obstacle location, vehicle status and driving intention. Then the controller uniformly issues instructions to ensure the orderly driving of the platoon. In the cooperative driving platoon, the displacement difference and the speed difference between vehicles have a certain relationship, which reduces the possibility of traffic accidents and then improves the safety of driving. In the process of cooperative driving, if there are multiple vehicles whose speeds don’t meet the current lane requirements, or if there are obstacles ahead, multi-vehicle lane change measures must be taken.

Effectively detecting road boundaries in real time is critical to the applications of autonomous vehicles, such as vehicle localization, path planning and environmental understanding. To precisely extract the road boundaries from the 3D-LiDAR data, a dedicated algorithm consisting of four steps is proposed in this paper. The steps are as follows: Firstly, the 3D-LiDAR data is pre-processed by employing the RANSAC method, the ground points are quickly separated from the original 3D-LiDAR point cloud to reduce the disturbance from the obstacles on the road, this greatly decreases the size of the point cloud to be processed. Secondly, based on the principle of 3D-LiDAR scanning, the ground points are divided into scan layers. And the road boundary points of each scan layer are detected by using three spatial features based on sliding window.

In the field of automatic driving, the combination of 3D LIDAR and inertial measurement unit (IMU) is a common sensor configuration scheme in laser point-cloud localization, high-precision map making and point-cloud target detection. So it is critical to calibrate LIDAR and IMU accurately. At present, due to the large volume and high cost of 3D LIDAR with high-line-number(Such as 64 lines or 128 lines), the configuration scheme of using multiple low-line-number 3D LIDARs appears in the automatic driving vehicle sensing system. However, the common calibration methods are not suitable for multi 3D LIDARs and IMU parameters calibration on autonomous vehicle, which have the disadvantages of cumbersome implementation and low accuracy. In this paper, a joint calibration test platform composed of dual LIDARs and IMU is assembled, and a method of precise automatic calibration based on GPS/RTK data is proposed.

It’s hard to achieve complete self-driving using hand-crafting generalized decision-making rules, while the end-to-end self-driving system is low in complexity, does not require hand-crafting rules, and can deal with complex situations. Modular-based self-driving systems require multi-task fusion and high-precision maps, resulting in high system complexity and increased costs. In end-to-end self-driving, we usually only use camera to obtain scene status information, so image processing is very important. Numerous deep learning applications benefit from multi-task learning, as the multi-task learning can accelerate model training and improve accuracy with combine all tasks into one model, which reduces the amount of calculation and allows these systems to run in real-time. Therefore, the approach of obtaining rich scene state information based on multi-task learning is very attractive. In this paper, we propose an approach to multi-task learning for semantics, geometry and motion.