Search Results

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.

With the development of intelligent and electric vehicles, higher requirements are put forward for the active braking and regenerative braking ability of the braking system. The traditional braking system equipped with vacuum booster has difficulty meeting the demand, therefore it has gradually been replaced by the integrated braking system. In this paper, a novel Integrated Braking System (IBS) is presented, which mainly contains a pedal feel simulator, a permanent magnet synchronous motor (PMSM), a series of transmission mechanisms, and the hydraulic control unit. As an integrative system of mechanics-electronics-hydraulics, the IBS has complex nonlinear characteristics, which challenge the accurate pressure control. Furthermore, it is a completely decoupled braking system, the pedal force doesn’t participate in pressure-building, so it is necessary to precisely identify driver’s braking intention.

With the development of cellular communication technology and for the sake of reducing drag resistance, the multi-lane platoon technology will be more prosperous in the future. In this article, the cooperative vehicle platoon method on the public road is represented. The method’s architecture is mainly composed of the following parts: decision-making, path planning and control command generation. The decision-making uses the finite state machine to make decision and judgment on the cooperative lane change of vehicles, and starts to execute the lane change step when the lane change requirements are met. In terms of path planning, with the goal of ensuring comfort, the continuity of the vehicle state and no collision between vehicles, a fifth-order polynomial is used to fit every vehicle trajectory. In terms of control command generation module, a model predictive control algorithm is used to solve the multi-vehicle centralized optimization control problem.

The installation of the Electronic Braking System (EBS) could effectively improve braking response speed, shorten braking distance, and ensure driving safety of commercial vehicles. However, during longitudinal deceleration control process, the commercial vehicles face not only challenges such as large inertia mass and random road gradient resistance of the vehicle layer, but also non-linear characteristics of the EBS actuator layer. In order to solve these problems, this paper proposes a commercial vehicle’s longitudinal deceleration precise control strategy considering vehicle-actuator dynamic characteristics. First, longitudinal dynamics of commercial vehicle is analyzed, and so is the EBS’ non-linear response hysteresis characteristics. Then, we design the dual layer deceleration control strategy. In vehicle layer, the recursive least squares with forgetting factor and Kalman filtering are comprehensively applied to dynamically estimate the vehicle mass and driving road slope.

Semi-active suspension system (SASS) could enhance the ride comfort of the vehicle across different operating conditions through adjusting damping characteristics. However, current SASS are often calibrated based on engineering experience when selecting parameters for its controller, which complicates the achievement of optimal performance and leads to a decline in ride comfort for the vehicle being controlled. Linear quadratic constrained optimal control is a crucial tool for enhancing the performance of semi-active suspensions. It considers various performance objectives, such as ride comfort, handling stability, and driving safety. This study presents a control strategy for determining optimal damping force in SASS to enhance driving comfort. First, we analyze the working principle of the SASS and construct a seven-degree-of-freedom model.

The electric vehicles and the intelligent vehicles put forward to new requirements for the brake system, such as the vacuum-independent braking, automatic or active braking, and regenerative braking, which are the key link for the vehicle’s safety and economy. However, the traditional vacuum brake booster is no longer able to meet these requirements. In this article, a novel integrated power-assisted actuator of brake system is proposed to satisfy the brake system requirements of the electric vehicles and intelligent vehicles. The electronic brake booster system is designed to achieve the function of boosting pedal force of driver, being independent on vacuum source, supplying autonomous or active braking. It is mainly composed of a permanent magnet synchronous motor (PMSM), a two-stage reduction transmission (gears and a ball screw), a servo body, and a reaction disk. The scheme design and power-assisted braking control are the key for the electronic actuator.

As a novel assist actuator of brake system, the electromechanical brake (EMB) booster has played a significant role in the battery electric vehicles and automatic driving vehicles. It has advantages of independent to vacuum source, active braking, and tuning pedal feeling compared with conventional vacuum brake booster. In this article, a novel EMB booster system is proposed, which is consisted of a permanent magnet synchronous motor (PMSM), a two-stage reduction by gears and ball screw, a servo body, and a reaction disk. Together with the hydraulic control unit, it has two working modes: active braking for automatic drive and passive braking for driver intervention. The structure and work principle of the electric brake booster system is first introduced. The precise control from pedal force to hydraulic pressure is the key for such a power-assisted brake actuator. We translate the control problem of force feedback control to position tracking control.

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.

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-speed vehicle is prone to instability under bad road conditions, causing many safety accidents such as tail-flicking and overturning. Stability control could assist vehicle to drive safely and stably by adjusting the additional yaw moment. However, most of the existing stability control strategies directly invoke the information of the sideslip angle of the centroid that is difficult to obtain on the vehicle, and carry out complex controller design, which deviates from the actual application. In order to achieve a complete set of stability control architecture oriented to practical applications, this paper designs a hierarchical vehicle stability control strategy based on differential braking and state estimation technology.

Traffic accidents avoidance is one of the main advantages for automated vehicles. As one of the main causes of vehicle collision accidents, lane changing of the ego vehicle in case that the obstacle vehicles appear in the blind spot with uncertain motion intentions is one of the main goals for the automated vehicle. An intention-aware lane changing collision assistance strategy basing on traffic situation assessment in the complex traffic scenarios is proposed in this paper. Typical Regions of Interest (ROI) within the detection range of the blind spots are selected basing on the road topology structures and state space consisting of the ego vehicle and the obstacle vehicles. Then the motion intentions of the obstacle vehicles in ROI are identified basing on Gaussian Mixture Models (GMM) and the corresponding motion trajectories are predicted basing on the state equation.

Sloped medians provide a run-off area for errant vehicles so that they can be safely stopped off-road with or without barriers placed in the sloped median. However, in order to optimize the design of sloped medians and the containment barriers, it is essential to accurately model the behavior of vehicles on such sloped terrain surfaces. In this study, models of a vehicle fleet comprising a small sedan and a pickup truck and sloped terrain surface are developed in CarSim™ to simulate errant vehicle behavior on sloped median. Full-scale crash tests were conducted using the vehicle fleet driven across a 9.754 meters wide median with a 6:1 slope at speeds ranging from 30 to 70 km/h. Measured data such as the lateral accelerations of the vehicle as well as chassis rotations (roll and pitch) were synchronized with the vehicle motion obtained from the video data.

Tire modeling plays an important role in the development of an Active Vehicle Safety System. As part of a larger project that aims at developing an integrated chassis control system, this study investigates the performance of a 19” all-season tire on ice for a sport utility vehicle. A design of experiment has been formulated to quantify the effect of operational parameters, specifically: wheel slip, normal load, and inflation pressure on the tire tractive performance. The experimental work was conducted on the Terramechanics Rig in the Advanced Vehicle Dynamics Laboratory at Virginia Tech. The paper investigates an approach for the parameterization of the Dugoff tire model based on the experimental data collected. Compared to other models, this model is attractive in terms of its simplicity, low number of parameters, and easy implementation for real-time applications.

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.

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.

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.

Electric vehicle (EV) has been regarded as not only an effective solution for environmental issues but also a more controllable and responsible device to driving forces with electric motors and precise torque measurement. For electric vehicle equipped with four in-wheel motors, its tire longitudinal forces can be generated independently and individually with fully utilized tire adhesion at each corner. This type of the electric vehicles has a distributed drive system, and often regarded as an over-actuated system since the number of actuators in general exceeds the control variables. Control allocation (CA) is often considered as an effective means for the control of over-actuated systems. The in-vehicle network technology has been one of the major enablers for the distributed drive systems. The vehicle studied in this research has an electrohydraulic brake system (EHB) on front axle, while an electromechanical brake system (EMB) on rear axle.

Minimum energy consumption with maximum comfort driving experience define the ideal human mobility. Recent technological advances in most Advanced Driver Assistance Systems (ADAS) on electric vehicles not only present a significant opportunity for automated eco-driving but also enhance the safety and comfort level. Understanding driving styles that make the systems more human-like or personalized for ADAS is the key to improve the system comfort. This research focuses on the personalized and green adaptive cruise control for intelligent electric vehicle, which is also known to be MyEco-ACC. MyEco-ACC is based on the optimization of regenerative braking and typical driving styles. Firstly, a driving style model is abstracted as a Hammerstein model and its key parameters vary with different driving styles. Secondly, the regenerative braking system characteristics for the electric vehicle equipped with 4-wheel hub motors are analyzed and braking force distribution strategy is designed.

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.

Roundabouts are one of the most complex traffic environments in urban roads, and a key challenge for intelligent driving decision-making. Deep reinforcement learning, as an emerging solution for intelligent driving decisions, has the advantage of avoiding complex algorithm design and sustainable iteration. For the decision difficulty in roundabout scenarios, this paper proposes an artificial potential field based Soft Actor-Critic (APF-SAC) algorithm. Firstly, based on the Carla simulator and Gym framework, a reinforcement learning simulation system for roundabout driving is built. Secondly, to reduce reinforcement learning exploration difficulty, global path planning and path smoothing algorithms are designed to generate and optimize the path to guide the agent.