Search Results

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.

An autonomous vehicle is a comprehensive intelligent system that includes environment sensing, vehicle localization, path planning and decision-making control, of which environment sensing technology is a prerequisite for realizing autonomous driving. In the early days, vehicles sensed the surrounding environment through sensors such as cameras, radar, and lidar. With the development of 5G technology and the Vehicle-to-everything (V2X), other information from the roadside can also be received by vehicles. Such as traffic jam ahead, construction road occupation, school area, current traffic density, crowd density, etc. Such information can help the autonomous driving system understand the current driving environment more clearly. Vehicles are no longer limited to areas that can be sensed by sensors. Vehicles with different autonomous driving levels have different adaptability to the environment.

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.

Velocity prediction on hilly road can be applied to the energy-saving predictive control of intelligent vehicles. However, the existing methods do not deeply analyze the difference and diversity of road slope driving characteristics, which affects prediction performance of some prediction method. To further improve the prediction performance on road slope, and different road slope driving features are fully exploited and integrated with the common prediction method. A rolling prediction-based multi-scale fusion prediction considering road slope transition driving characteristics is proposed in this study. Amounts of driving data in hilly sections were collected by the advanced technology and equipment. The Markov chain model was used to construct the velocity and acceleration joint state transition characteristics under each road slope transition pair, which expresses the obvious driving difference characteristics when the road slope changes.

Autonomous driving technology is more and more important nowadays, it has been changing the living style of our society. As for autonomous driving planning and control, vehicle dynamics has strong nonlinearity and uncertainty, so vehicle dynamics and control is one of the most challenging parts. At present, many kinds of specific vehicle dynamics models have been proposed, this review attempts to give an overview of the state of the art of vehicle dynamics models for autonomous driving. Firstly, this review starts from the simple geometric model, vehicle kinematics model, dynamic bicycle model, double-track vehicle model and multi degree of freedom (DOF) dynamics model, and discusses the specific use of these classical models for autonomous driving state estimation, trajectory prediction, motion planning, motion control and so on.

Intelligent driving, aimed for collision avoidance and self-navigation, is mainly based on environmental sensing via radar, lidar and/or camera. While each of the sensors has its own unique pros and cons, camera is especially good at object detection, recognition and tracking. However, unpredictable environmental illumination can potentially cause misdetection or false detection. To investigate the influence of illumination conditions on detection algorithms, we reproduced various illumination intensities in a photo-realistic virtual world, which leverages recent progress in computer graphics, and verified vehicle detection effect there. In the virtual world, the environmental illumination is controlled precisely from low to high to simulate different illumination conditions in the driving scenarios (with relative luminous intensity from 0.01 to 400). Sedan cars with different colors are modelled in the virtual world and used for detection task.

Tire-road friction condition is crucial to the safety of vehicle driving. The emergence of autonomous driving makes it more important to estimate the friction limit accurately and at the lowest possible excitation. In this paper, an early detection method of tire-road friction coefficient based on pneumatic trail under cornering conditions is proposed using an intelligent tire system. The previously developed intelligent tire system is based on a triaxial accelerometer mounted on the inner liner of the tire tread. The friction estimation scheme utilizes the highly sensitive nature of the pneumatic trail to the friction coefficient even in the linear region and its approximately linear relationship with the excitation level. An indicator referred as slip degree indicating the utilization of the road friction is proposed using the information of pneumatic trail, and it is used to decide whether the excitation is sufficient to adopt the friction coefficient estimate.

Unmanned Ground Vehicle (UGV) has a wide range of applications in the military, agriculture, firefighting and other fields. Path planning, as a key aspect of autonomous driving technology, plays an essential role for UGV to accomplish the established driving tasks. At present, there are many global path planning algorithms in grid maps on unstructured roads, while general grid maps do not consider the specific elevation or ground type difference of each grid, and unstructured roads are generally considered as flat and open roads. On the contrary, the unmanned off-road is always a bumpy road with undulating terrain, and meanwhile, the landform is complex and the types of features are diverse. In order to ensure the safety and improve the efficiency of autonomous driving of UGV in off-road environment, this paper proposes a global off-road path planning method for UGV based on the raw image of remote sensing map. Firstly, the raw image is gridded.

This paper addresses the issues of long-term signal loss in localization and cumulative drift in SLAM-based online mapping and localization in autonomous valet parking scenarios. A GPS, INS, and SLAM fusion localization framework is proposed, enabling centimeter-level localization with wide scene adaptability at multiple scales. The framework leverages the coupling of LiDAR and Inertial Measurement Unit (IMU) to create a point cloud map within the parking environment. The IMU pre-integration information is used to provide rough pose estimation for point cloud frames, and distortion correction, line and plane feature extraction are performed for pose estimation. The map is optimized and aligned with a global coordinate system during the mapping process, while a visual Bag-of-Words model is built to remove dynamic features.

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.

With vehicle platooning becoming an important research field in recent years, it is now imperative to introduce platoons as part of the dynamic environment, considering overtaking and merging possibilities. This article studies optimal speed trajectories and longitudinal control with optimized energy efficiency for an autonomous vehicle with several preceding platoons and full terrain information. It aims at improving the energy efficiency of vehicles with Advanced Driver Assistance Systems (ADAS). A forward discrete dynamic programming (DDP) algorithm with distance as the discretization basis is used to derive speed trajectories in the trade-off between air drag reduction and energy saved by utilizing the road slope information. The problem is decomposed into decisions whether to overtake or to merge into the nearest platoon with the assumption of sufficient distance among platoons.

This paper describes a novel recognition and classification method of vehicle targets in urban road based on a vehicle-mounted Velodyne HDL64E light detection and ranging (LIDAR) system. The autonomous vehicle will choose different driving strategy according to the surrounding traffic environments to guarantee that the driving is safe, stable and efficient. It is helpful for controller to provide the efficient stagey to know the exact type of vehicle around. So this method concentrates on reorganization and classification the type of vehicle targets so that the controller can provide a safe and efficient driving strategy for autonomous ground vehicles. The approach is targeted at high-speed ground vehicle, so real-time performance of the method plays a critical role. In order to improve the real-time performance, some methods of data preprocessing should be taken to simplify the large-size long-range 3D point clouds.

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.

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.

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.

With the rapid development of science and technology, the automobile industry is developing rapidly, and intelligent networking and autonomous driving have become new research hotspots. The safety and efficiency of vehicle driving has always been an important research topic in the transportation field. Due to reducing the participation of drivers, autonomous vehicles can reduce traffic accidents caused by human factors. While the development of intelligent networking can achieve information sharing between vehicles, and improve driving efficiency to a certain extent. Based on the game theory and the minimum safe distance condition, this paper establishes a lane changing decision model of intelligent network-connected autonomous vehicles, puts forward a game payoff function and analyzes the game strategy.

Autonomous driving in real-world urban traffic must cope with dynamic environments. This presents a challenging decision-making problem, e.g. deciding when to perform an overtaking maneuver or how to safely merge into traffic. The traditional autonomous driving algorithm framework decouples prediction and decision-making, which means that the decision-making and planning tasks will be carried out after the prediction task is over. The disadvantage of this approach is that it does not consider the possible impact of ego vehicle decisions on the future states of other agents. In this article, a decision-making and planning method which considers longitudinal interaction is represented. The method’s architecture is mainly composed of the following parts: trajectory sampling, forward simulation, trajectory scoring and trajectory selection. For trajectory sampling, a lattice planner is used to sample three-dimensionally in both the time horizon and the space horizon.