In open-pit mines, long-term map management is crucial for route-planning of autonomous mining trucks during haulage. However, degraded scenarios with low-texture mountains may cause mapping discontinuity after rasterization. Moreover, the high-frequency environmental changes may lead to inter-session matching failures, resulting in significant mapping inaccuracies. To address the above issues, we propose a pose reference and information density based long-term mapping method for degraded scenarios. We introduce adaptive information compensation to ensure the even distribution of map information after the mapping process. Sequentially, we utilize poses corresponding to central and query sessions along with the information density model to achieve inter-session matching. Outdated information pruning is then employed to update the map. Furthermore, we evaluate the map quality assessing overlap and utilization rates under field tests, and the results suggest that our proposed methods yield over an 8% improvement in overlap rate compared to state-of-the-art methods.

Although pre-built LiDAR maps have been widely used for location estimation, the high maintenance cost of pre-built maps hinders their expansion in practical application. Lightweight maps with global consistency and extensive coverage, such as OpenStreetMap (OSM), provide a low-cost potential alternative for prior reference. However, OSM exhibits significant differences in precision and structure with on-board perception, leading to incompatibility and poor performance with the existing descriptor matching method. Thus, this paper proposes a planar descriptor based on building boundary directions that is tailored for OSM-perception unification. Based on the proposed descriptor, OSM can be transformed into a prior map with the potential to replace pre-built maps, suitable for location estimation in urban scenes. To evaluate the effectiveness of replacing pre-built LiDAR maps, we conducted experiments in the urban environment sequences of KITTI. The results indicate that the proposed method achieves the best performance on location estimation accuracy utilizing OSM compared to other feature descriptors.

Motion planning and control of connected and autonomous vehicles (CAVs) for improving traffic efficiency and safety in intersections still meets many challenges due to its dynamic and complex nature. In this article, an innovative collision-free and time-optimal multivehicle motion planning method for the CAVs at unsignalized intersection scenarios is proposed. We systematically analyze the regularity of intersection crossing mode and summarize the overall conflict scenario. To eliminate the vehicles potential collision, a learning-based iterative optimization (LBIO) algorithm is designed to solve the collision-free trajectories generating problem iteratively and offline. The terminal constraint set, terminal cost, and global safe constraints of the LBIO are constructed and updated from the historical data in previous iterations. The algorithm can finally converge to time-optimal trajectories for multivehicle only after several iterations. To apply the trained trajectories into the continuous intersection traffic flow, an online cluster-based motion planning (CBMP) algorithm is developed to coordinate the vehicle velocities and movements in the cooperative control area surrounding the intersection. With an LTV-MPC algorithm for the low-level control, the proposed approach is validated on the SUMO in typical intersection scenarios. The results show that the proposed method allows the potentially conflicting vehicles passing the intersection simultaneously and quickly without waiting, and significantly improves the overall traffic efficiency.

Vehicle detection, tracking and motion forecasting are critical for intelligent vehicle sensing system. In this paper, we propose a single-stage deep neural network (DNN) called TAPNet, which combines consecutive frames of LiDAR scans and high-definition (HD) maps to jointly reason about Bird's Eye View (BEV) detection and trajectory prediction of vehicles. In our proposed method, an auxiliary past learning task is developed which can guide the backbone to exploit temporal information from training data by learning the motion history of vehicles. Moreover, We introduce a novel incremental trajectory loss function that can reduce the regressing varience and generate smooth trajectories. Experimental results on large-scale public dataset show that our proposed TAPNet outperforms other state-of-the-art models that jointly reason about BEV detection and motion forecasting.

Visual Odometry and Simultaneous Localization and Mapping (SLAM) are widely used in autonomous driving. In the traditional keypoint-based visual SLAM systems, the feature matching accuracy of the front end plays a decisive role and becomes the bottleneck restricting the positioning accuracy, especially in challenging scenarios like viewpoint variation and highly repetitive scenes. Thus, increasing the discriminability and matchability of feature descriptor is of importance to improve the positioning accuracy of visual SLAM. In this paper, we proposed a novel adaptive-scale triplet loss function and apply it to triplet network to generate adaptive-scale descriptor (ASD). Based on ASD, we designed our monocular SLAM system (ASD-SLAM) which is an deep-learning enhanced system based on the state of art ORB-SLAM system. The experimental results show that ASD achieves better performance on the UBC benchmark dataset, at the same time, the ASD-SLAM system also outperforms the current popular visual SLAM frameworks on the KITTI Odometry Dataset.

Preceding target vehicle (PTV) motion recognition play a pivotal role in autonomous vehicles. Motion states such as yaw rate, longitudinal and lateral velocity are critical for ego vehicle decision-making and control. However, lateral states of a PTV can hardly be measured directly by common onboard sensors and the PTV lateral state estimation has been seldom addressed in existing literatures. In this paper, a novel estimation scheme based on multiple neural network ensemble is proposed for PTV lateral state estimation. First, PTV lateral kinematics is presented based on vehicle-road relationship and a novel PTV lateral motion model is constructed to interpret the PTV lateral motion. Then, neural network observer with the PTV lateral kinematics as prior knowledge is designed and training data are collected in simulation environment. The neural network observer is trained using Levenberg-Marquardt backpropagation with Bayesian regularization (LMBR) to improve the generalization capability. Finally, to further improve the performance of the neural network estimation method, multiple neural network observers are integrated by weighted averaging strategy. The effectiveness of proposed approach is verified through hardware-in-the-Ioop (HiL) experiments conducted in designed verification scenarios, and compared with model-based method and other three learning methods. The experiment results reveal that the proposed method outperforms other typical methods and achieves accurate estimation of the PTV lateral states.

To achieve fast and accurate positioning control, a controller based on a visual servo employing a multi-rate Kalman filter was implemented and experimentally evaluated. Although a visual servo is expected to achieve robust positioning control by eliminating positional errors due to operation environments, applying visual information to positioning control faces three challenges, namely, lower sampling speed, longer delay, and lower positional accuracy than those possible by using a conventional position encoder. To overcome these problems, a multi-rate Kalman filter with a time-delay compensation technique is employed to combine visual information with encoder-based positional information. Two models describing a positioning-control experimental system using a one-axis linear stage with a camera were investigated to determine the optimum structure of the Kalman filter. Evaluation of the experimental system showed that the designed controller achieves high-precision (±10 µm) positioning control within approximately 10-ms settling time while simultaneously adjusting the environmental positional errors.

Among many vehicle states, body slip angle is one of the most important information for vehicle motion control. Due to the high costs to measure body slip angle with specific devices, it is necessary to investigate estimation methods using existing cheap sensors. From the viewpoint of sensor configuration, gyroscope, steering angle sensor, etc. are often employed for body slip angle estimation; in this research, two pieces of information provided by vision system are also utilized as additional measurements. Nevertheless, the sampling rate of normal camera is much slower compared to the other kinds of onboard sensors; for electric vehicles (EVs), motors' control period is shorter than the sampling time of cameras, which also brings multi-rate issue. Moreover, the time delay caused by image processing is usually too long to be neglected. In this paper, single-rate and multi-rate Kalman filters considering measurement delay are designed for body slip angle estimation, and a body slip angle controller is designed with the estimated result as feedback. First of all, vehicle model and visual model as well as the multi-rate and delay issues are explained; then, single-rate and multi-rate Kalman filters are designed for body slip angle estimation; and then, body slip angle controllers with single-rate and multi-rate estimators are compared followed with simulations and experimental results; finally, conclusion and future works are presented.