Search

Positioning and mapping technology is a difficult and hot topic in autonomous driving environment sensing systems. In a complex traffic environment, the signal of the Global Navigation Satellite System (GNSS) will be blocked, leading to inaccurate vehicle positioning. To ensure the security of automatic electric campus vehicles, this study is based on the Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain (LEGO-LOAM) algorithm with a monocular vision system added. An algorithm framework based on Lidar-IMU-Camera (Lidar means light detection and ranging) fusion was proposed. A lightweight monocular vision odometer model was used, and the LEGO-LOAM system was employed to initialize monocular vision. The visual odometer information was taken as the initial value of the laser odometer. At the back-end opti9mization phase error state, the Kalman filtering fusion algorithm was employed to fuse the visual odometer and LEGO-LOAM system for positioning. The visual word bag model was applied to perform loopback detection. Taking the test results into account, the laser radar loopback detection was further optimized, reducing the accumulated positioning error. The real car experiment results showed that our algorithm could improve the mapping quality and positioning accuracy in the campus environment. The Lidar-IMU-Camera algorithm framework was verified on the Hong Kong city dataset UrbanNav. Compared with the LEGO-LOAM algorithm, the results show that the proposed algorithm can effectively reduce map drift, improve map resolution, and output more accurate driving trajectory information.

Nowadays, most trajectory prediction algorithms have difficulty simulating actual traffic behavior, and there is still a problem of large prediction errors. Therefore, this paper proposes a multi-object trajectory prediction algorithm based on lane information and foresight information. A Hybrid Dilated Convolution module based on the Channel Attention mechanism (CA-HDC) is developed to extract features, which improves the lane feature extraction in complicated environments and solves the problem of poor robustness of the traditional PINet. A lane information fusion module and a trajectory adjustment module based on the foresight information are developed. A socially acceptable trajectory with Generative Adversarial Networks (S-GAN) is developed to reduce the error of the trajectory prediction algorithm. The lane detection accuracy in special scenarios such as crowded, shadow, arrow, crossroad, and night are improved on the CULane dataset. The average F1-measure of the proposed lane detection has been increased by 4.1% compared to the original PINet. The trajectory prediction test based on D2-City indicates that the average displacement error of the proposed trajectory prediction algorithm is reduced by 4.27%, and the final displacement error is reduced by 7.53%. The proposed algorithm can achieve good results in lane detection and multi-object trajectory prediction tasks.

For nonlinear systems, both the cubature Kalman filter (CKF) and square-root cubature Kalman filter (SCKF) can get good estimation performance under Gaussian noise. However, the actual driving environment noise mostly has non-Gaussian properties, leading to a significant reduction in robustness and accuracy for distributed vehicle state estimation. To address such problems, this paper uses the square-root cubature Kalman filter with the maximum correlation entropy criterion (MCSRCKF), establishing a seven degrees of freedom (7-DOF) nonlinear distributed vehicle dynamics model for accurately estimating longitudinal vehicle speed, lateral vehicle speed, yaw rate, and wheel rotation angular velocity using low-cost sensor signals. The co-simulation verification is verified by the CarSim/Simulink platform under double-lane change and serpentine conditions. Experimental results show that the MCSRCKF has high accuracy and enhanced robustness for distributed drive vehicle state estimation problems in real non-Gaussian noise environments.

Vehicle detection is one of the most challenging research works on environment perception for intelligent vehicle. The commonly used object detection network is too large and can only be realized in real-time on a high-performance server. Based on YOLOv3-tiny, the feature extraction was realized using light-weighted networks such as DarkNet-19 and ResNet-18 to improve accuracy. The K -means algorithm was used to cluster nine anchor boxes to achieve multi-scale prediction, especially for small targets. For automotive applicable scenarios, the proposed vehicle detection network was executed in an embedded device. The KITTI data sets were trained and tested. Experimental results show that the average accuracy is improved by 14.09% compared with the traditional YOLOv3-tiny, reaching 93.66%, and can reach 13 fps on the embedded device.

With the development of deep learning, the performance of object detection has made great progress. However, there are still some challenging problems, such as the detection accuracy of small objects and the efficiency of the detector. This study proposes an accurate and fast single shot multibox detector, which includes context comprehensive enhancement (CCE) module and feature enhancement module (FEM). To integrate more efficient information when aggregating context information, the conv4_3 and fc_7 feature maps are merged to design the CCE module. To obtain more fine‐grained feature information, this study presents a FEM and special feature enhancement module (FEM‐s) module that can fuse different receptive field sizes to better adapt to the scale change of the object. Compared to existing methods based on deep learning, the proposed method helps to gradually produce more detailed feature maps with better performance. Under the premise of ensuring real‐time speed, the authors network can achieve 81.2 mean average precision on the PASCAL VOC 2007 test with an input size of 320 × 320 on a single Nvidia 2080Ti GPU.

With the rapid development of intelligent transportation system, the research on vehicle stability can be a theoretical basis for realizing autonomous driving technology. The previous stability control strategies have not taken into account the tire force saturation factor, the slip rate, and the robustness of the control system sufficiency. According to the characteristic that the torque of each wheel can be distributed independently, a torque distribution algorithm under emergency conditions is proposed. The proposed torque distribution algorithm is constructed using three hierarchical controllers. The upper controller attempts to judge whether the vehicle is in stable state using the phase plane method. Also, it judges whether the wheels are slipping. The middle controller aims to calculate the demands for the desired traction force and yaw moment, whereas the lower controller is designed to translate those virtual signals into actual actuator commands. When designing the middle controller, a sliding mode control method is utilized to guarantee system stability and robustness by taking into account various factors, including lateral wind, and sensor noise. For the lower controller, the control allocation optimization method is utilized to determine an appropriate control input for each in-wheel motor by considering the road conditions, adhesion utilization, and maximum output torque of the motor. The numerical simulation studies are conducted to evaluate the performance of the torque distribution algorithm. Comparison results indicate that the proposed algorithm presents better performance to distribute the appropriate torque for each wheel and ensure the stability of the vehicle under emergency conditions.

A novel pedestrian detection system based on vision in urban traffic situations is presented to help the driver perceive the pedestrian ahead of the vehicle. To enhance the accuracy and to decrease the time spent on pedestrian detection in such complicated situations, the pedestrian is detected by dividing their body into several parts according to their corresponding features in the image. The candidate pedestrian leg is segmented based on the gentle AdaBoost algorithm by training the optimized histogram of gradient features. The candidate pedestrian head is located by matching the pedestrian head and shoulder model above the region of the candidate leg. Then the candidate leg, head and shoulder are combined by parts constraint and threshold adjustment to verify the existence of the pedestrian. Finally, the experiments in real urban traffic circumstances were conducted. The results show that the proposed pedestrian detection method can achieve pedestrian detection rate of 92.1% with the average detection time of 0.2257 s.

In this paper, with the aim of meeting the requirements of car following, safety, comfort, and economy for adaptive cruise control (ACC) system, an ACC algorithm based on model predictive control (MPC) using constraints softening is proposed. A higher-order kinematics model is established based on the mutual longitudinal kinematics between the host vehicle and the preceding vehicle that considers the changing characteristics of the inter-distance, relative velocity, acceleration, and jerk of the host vehicle. Performance indexes are adopted to represent the multi-objective demands and constraints of the ACC system. To avoid the solution becoming unfeasible because of the overlarge feedback correction, the constraint softening method was introduced to improve robustness. Finally, the proposed ACC method is verified in typical car-following scenarios. Through comparisons and case studies, the proposed method can improve the robustness and control precision of the ACC system, while satisfying the demands of safety, comfort, and economy.

Pedestrian detection and tracking is the key to autonomous vehicle navigation systems avoiding potentially dangerous situations. Firstly, the probability distribution of colour information is established after a pedestrian is located in an image. Then the detected results are utilized to initialize a Kalman filter to predict the possible position of the pedestrian centroid in the future frame. A Camshift tracking algorithm is used to track the pedestrian in the specific search window of the next frame based on the prediction results. The actual position of the pedestrian centroid is output from the Camshift tracking algorithm to update the gain and error covariance matrix of the Kalman filter. Experimental results in real traffic situations show the proposed pedestrian tracking algorithm can achieve good performance even when they are partly occluded in inconsistent illumination circumstances.

In order to detect the obstacle from the large amount of 3D LIDAR data in hybrid cross-country environment for unmanned ground vehicle, a new graph approach based on Markov random field was presented. Firstly, the preprocessing method based on the maximum blurred line is applied to segment the projection of every laser scan line in x-y plane. Then, based on K-means clustering algorithm, the same properties of the line are combined. Secondly, line segment nodes are precisely positioned by using corner detection method, and the next step is to take advantage of line segment nodes to build an undirected graph for Markov random field. Lastly, the energy function is calculated by means of analyzing line segment features and solved by graph cut. Two types of line mark are finally classified into two categories: ground and obstacle. Experiments prove the feasibility of the approach and show that it has better performance and runs in real time.

Abstract Visual odometry provides planetary exploration rovers with accurate knowledge of their position and orientation, which needs effective feature tracking results, especially in barren sandy terrains. In this paper, a stereovision based odometry algorithm is proposed for a lunar rover, which is composed of corner extraction, feature tracking and motion estimation. First, a morphology based image enhancement method is studied to guarantee enough corners are extracted. Second, a Random Sample Consensus (RANSAC) algorithm is proposed to make a robust estimation of the fundamental matrix, which is the basic and critical part of feature matching and tracking. Then, the 6 degrees of freedom rover position and orientation is estimated by the RANSAC algorithm. Finally, experiments are performed in a simulated lunar surface environment using a prototype rover, which have confirmed the feasibility and effectiveness of the proposed method.

Lane departure warning system (LDWS) has been regarded as an efficient method to lessen the damages of road traffic accident resulting from driver fatigue or inattention. Lane detection is one of the key techniques for LDWS. To overcome the contradiction between complexity of algorithm and the real-time requirement for vehicle onboard system, this paper introduces a new lane detection method based on intelligent CCD parameters regulation. In order to improve the real-time capability of the system, a CCD parameters regulating method is proposed which enhances the contrast between lane line and road surfaces and reduces image noise, so it lays a good foundation for the following lane detection. Hough transform algorithm is improved by selection and classification of seed points. Finally the lane line is extracted through some restrictions. Experimental results verify the effectiveness of the proposed method, which improves not only real-time capability but also the accuracy of the system.

Ignoring the driver’s corrective actions is the main reason for false warnings in the lane-departure prediction method.We proposed a lane-departure prediction (LDP) method based on a support vector machine (SVM) and improved gated recurrent unit (GRU) models. The driver’s visual distraction state was analyzed by using a radial basis function (RBF) based SVM model. The vehicle’s lateral deviation was predicted by using a GRU model. The characteristic parameters of the GRU model were extracted from vehicle time series data using the time to lane crossing (TLC) model and the vehicle-road model. Considering that the farther the vehicle deviates from the lane centerline, the higher its deviation risk, a lateral deviation risk (LDR) loss function was proposed to improve the accuracy of the GRU model. By combining the SVM model and LDR-GRU model, the proposed LDP method can predict the future trajectory of the vehicle and adaptively adjust the safety boundary according to the driver’s state. Naturalistic driving data from 52 drivers were collected to train and validate the adaptive LDP method. Finally, we compared the proposed LDR-GRU-SVM model with the TLC model, GRU model, LDR-GRU model, and GRU-SVM model. Experimental results show that the TLC model presents the highest false warning rate of 23.1% within a prediction time of 1s, while the proposed method is able to reduce the false warning rate to 1.2%. [ABSTRACT FROM AUTHOR]

This paper presents a control method for a WIP vehicle in multi-obstacle environment based on the improved artificial potential field. Firstly, an improved artificial potential field (IAPF) is developed, where a safe distance is introduced to the existing repulsive potential field to solve the security issue, while the probable local minima caused by the obstacle around the target can also be eliminated simultaneously. Next, an obstacle avoidance controller is designed based on the IAPF, where the nonholonomic constraint and underactuated characteristic of the WIP vehicle are fully considered, and the stability condition of the system is analyzed by means of the related control theory. Moreover, to further improve the control performance, a key parameter that play an important role in the controller is adjusted by taking advantage of fuzzy logic, and detailed analyses are given to demonstrate its necessity and effectiveness. Finally, considering a motion environment that contains dense obstacles, narrow corridor and an obstacle near the target, numerical simulations are conducted to validate the proposed method, whose results indicate that the method has a good performance to control the WIP vehicle in multi-obstacle environment. [ABSTRACT FROM AUTHOR]

With the increasing development of intelligent vehicles, the automatic parking system came into being, it could help people improve the driving safety and reduce the car accidents. From this point of view, it is greatly necessary to serve the automatic parking research. The three stages of the automatic parking system include parking space detection, the kinematics model building and the navigation controller design. Firstly, the laser radar sensor is applied to obtain the distance information around the vehicle, then the median filtering algorithm and the least squares method are employed to process the laser data. The next step is to detect the parking space by using K-Means clustering and threshold segmentation method. The second stage is to build car kinematics model by employing the Arman steering theory. Thirdly, the navigation controller design and simulation are accomplished based on the fuzzy logic control theory. The parallel automatic parking simulations are shown by using the Matlab toolbox. Experimental results show that the parking space detection method has perfect performance and the navigation controller design algorithm has good feasibility. [ABSTRACT FROM AUTHOR]

To enhance the active safety and realize the autonomy of intelligent vehicle on highway curved road, a lane changing trajectory is planned and tracked for lane changing maneuver on curved road. The kinematics model of the intelligent vehicle with nonholonomic constraint feature and the tracking error model are established firstly. The longitudinal and lateral coupling and the difference of curvature radius between the outside and inside lane are taken into account, which is helpful to enhance the authenticity of desired lane changing trajectory on curved road. Then the trajectory tracking controller of closed-loop control structure is derived using integral backstepping method to construct a new virtual variable. The Lyapunov theory is applied to analyze the stability of the proposed tracking controller. Simulation results demonstrate that this controller can guarantee the convergences of both the relative position tracking errors and the position tracking synchronization. [ABSTRACT FROM AUTHOR]

Unmanned Ground Vehicles (UGVs) that can drive autonomously in cross-country environment have received a good deal of attention in recent years. They must have the ability to determine whether the current terrain is traversable or not by using onboard sensors. This paper explores newmethods related to environment perception based on computer image processing, pattern recognition, multisensors data fusion, andmultidisciplinary theory. Kalman filter is used for low-level fusion of physical level, thus using the D-S evidence theory for high-level data fusion. Probability Test and Gaussian Mixture Model are proposed to obtain the traversable region in the forward-facing camera view for UGV. One feature set including color and texture information is extracted from areas of interest and combined with a classifier approach to resolve two types of terrain (traversable or not). Also, three-dimension data are employed; the feature set contains components such as distance contrast of three-dimension data, edge chain-code curvature of camera image, and covariance matrix based on the principal component method. This paper puts forward one new method that is suitable for distributing basic probability assignment (BPA), based on which D-S theory of evidence is employed to integrate sensors information and recognize the obstacle. The subordination obtained by using the fuzzy interpolation is applied to calculate the basic probability assignment. It is supposed that the subordination is equal to correlation coefficient in the formula. More accurate results of object identification are achieved by using the D-S theory of evidence. Control on motion behavior or autonomous navigation for UGV is based on the method, which is necessary for UGV high speed driving in crosscountry environment. The experiment results have demonstrated the viability of the new method. [ABSTRACT FROM AUTHOR]

Automotive collision avoidance system, which aims to enhance the active safety of the vehicle, has become a hot research topic in recent years. However, most of the current systems ignore the active protection of pedestrian and other vulnerable groups in the transportation system. An advanced emergency braking control system is studied by taking into account the pedestrians and the vehicles. Three typical braking scenarios are defined and the safety situations are assessed by comparing the current distance between the host vehicle and the obstacle with the critical braking distance. To reflect the nonlinear time-varying characteristics and control effect of the longitudinal dynamics, the vehicle longitudinal dynamics model is established in CarSim. Then the braking controller with the structure of upper and lower layers is designed based on sliding mode control and the single neuron PID control when confronting deceleration or emergency braking conditions. Cosimulations utilizing CarSim and Simulink are finally carried out on a CarSim intelligent vehicle model to explore the effectiveness of the proposed controller. Results display that the designed controller has a good response in preventing colliding with the front vehicle or pedestrian. [ABSTRACT FROM AUTHOR]

In this paper, off-road path recognition and navigation control method are studied to realize intelligent vehicle autonomous driving in unstructured environment. Firstly, the traversable path is achieved by vision and laser sensors. The vehicle steering and driving coupled dynamic model is established. Secondly, a coordinated controller for steering and driving is proposed via the back-stepping variable structure control method, which can be used to deal with the unmatched uncertainties of the control system model. To reduce the chattering phenomenon caused by variable structure, the boundary layer approach is introduced. The results of simulation and off-road experiment show the effectiveness and robustness of the proposed controller. [ABSTRACT FROM AUTHOR]

Automotive collision avoidance system, which aims to enhance the active safety of the vehicle, has become a hot research topic in recent years. However, most of the current systems ignore the active protection of pedestrian and other vulnerable groups in the transportation system. An advanced emergency braking control system is studied by taking into account the pedestrians and the vehicles. Three typical braking scenarios are defined and the safety situations are assessed by comparing the current distance between the host vehicle and the obstacle with the critical braking distance. To reflect the nonlinear time-varying characteristics and control effect of the longitudinal dynamics, the vehicle longitudinal dynamics model is established in CarSim. Then the braking controller with the structure of upper and lower layers is designed based on sliding mode control and the single neuron PID control when confronting deceleration or emergency braking conditions. Cosimulations utilizing CarSim and Simulink are finally carried out on a CarSim intelligent vehicle model to explore the effectiveness of the proposed controller. Results display that the designed controller has a good response in preventing colliding with the front vehicle or pedestrian.