Search

Radar simulation models can effectively overcome the drawbacks of real vehicle experiment and speed up the development process of intelligent vehicle technologies based on millimeter wave radar via virtual testing. However, there are still many gaps between the radar model using in the virtual driving environment and the real radar. In this paper, a novel simulation model of intelligent vehicle millimeter wave radar is proposed. Based on the analysis of the real radar performance in typical application scenes, the radar model considers the mechanism and characteristics of the vehicle radar synthetically and a systematic radar modeling architecture with innovation is introduced. The highlights of this radar model include the design of the RCS simulation model for radar targets with both high accuracy and real-time performance, the establishment of the quantitative false alarm model, missed detection model and measurement error simulation model. Vast amounts of data collected by real vehicle radar are applied to fetch model parameters and verify the accuracy of the radar model. Simulation results show that the proposed model can reach both high reliability and computational efficiency.

In an autonomous vehicle, the lane following algorithm is an important component, which is a basic function of autonomous driving. However, the existing lane following system has a few shortcomings: first, the control method it adopts requires an accurate system model, and different vehicles have different parameters, which needs a lot of parameter calibration work. The second is that it may fail on road sections where the lateral acceleration requirements of vehicles are large, such as large curves. Third, its decision-making system is defined based on rules, which has disadvantages: it is difficult to formulate, human subjective factors cannot guarantee objectivity, coverage is difficult to guarantee. In recent years, the deep deterministic policy gradient (DDPG) algorithm has been widely used in the field of autonomous driving due to its strong nonlinear fitting ability and generalization performance. However, the DDPG algorithm has overestimated state action values and large cumulative errors, low training efficiency and other issues. Therefore, this paper improves the DDPG algorithm based on the double critic networks and priority experience replay mechanism. Then this paper proposes a lane following method based on this algorithm. Experiment shows that the algorithm can achieve excellent following results under various road conditions.

Visual simultaneous localization and mapping (VSLAM) plays a vital role in the field of positioning and navigation. At the heart of VSLAM is visual odometry (VO), which uses continuous images to estimate the camera’s ego-motion. However, due to many assumptions of the classical VO system, robots can hardly operate in challenging environments. To solve this challenge, we combine the multiview geometry constraints of the classical stereo VO system with the robustness of deep learning to present an unsupervised pose correction network for the classical stereo VO system. The pose correction network regresses a pose correction that results in positioning error due to violation of modeling assumptions to make the classical stereo VO positioning more accurate. The pose correction network does not rely on the dataset with ground truth poses for training. The pose correction network also simultaneously generates a depth map and an explainability mask. Extensive experiments on the KITTI dataset show the pose correction network can significantly improve the positioning accuracy of the classical stereo VO system. Notably, the corrected classical stereo VO system’s average absolute trajectory error, average translational relative pose error, and average translational root-mean-square drift on a length of 100–800 m in the KITTI dataset is 13.77 cm, 0.038 m, and 1.08%, respectively. Therefore, the improved stereo VO system has almost reached the state of the art.

Among the representative algorithms of manifold learning, Hessian locally linear embedding (HLLE) and local tangent space alignment (LTSA) algorithms haven been regarded as two different algorithms. However, in practice, the effects of these two algorithms are very similar and LTSA performs better than HLLE in some applications. This paper tries to account for this phenomenon from a mathematical point of view. There are only two differences between HLLE and LTSA. First, LTSA includes a data point into its neighborhood, while HLLE does not. Second, HLLE and LTSA use different methods to align the local coordinates of manifold. In this paper, we show that, the first difference between HLLE and LTSA is not essential. However, from the viewpoint of data utilization, LTSA does better than HLLE in the neighborhood construction. This may account for why LTSA can perform better than HLLE in some applications. As for the second difference between HLLE and LTSA, we first prove that, the alignment equations used by HLLE and LTSA are exactly the same. Second, we prove that, although HLLE and LTSA uses different methods to solve the alignment equation, their solutions are exactly the same, provided that HLLE adopts the same method as LTSA to construct the neighborhoods. Based on these arguments, we claim that HLLE and LTSA are equivalent to each other. This conclusion can also be verified experimentally by using manifold learning MATLAB demo (MANI), a widely-used experimental platform of manifold learning. When testing HLLE on MANI, if HLLE adopts the same method as LTSA to construct the neighborhoods, the experimental results presented by MANI will be the same as those of LTSA.

Terrain information can significantly impact load power demand, and in turn, on battery life and system efficiency of a hybrid energy storage system (ESS) with battery and supercapacitor. Taking terrain information ahead into consideration for proactive power management is one of the most important ways to improve battery life and overall system efficiency. However, since terrain information is typically available from commercial geographic information systems database, it is by nature inaccurate with uncertainties with respect to the requirements of power management. This is often worsening when combining with commercially low-quality global positioning systems. This paper proposes a novel power management strategy to cope with the inaccuracy and uncertainties of the terrain information with the aim to improve battery life, while maintaining overall system performance. First, the impact of terrain inaccuracy on battery life and system efficiency is analyzed based on two different hybrid ESSs with semiactive topologies. Then, a power management control strategy is developed that actively distributes the power between battery and supercapacitor with adaptation to terrain inaccuracy and uncertainties. The objective of the proposed power management control strategy is to minimize the total cost of the system, including the cost for battery life and energy. Finally, simulation is conducted that has verified the effectiveness of the proposed control strategy.

Millimeter-wave radar has been widely used in intelligent vehicle target detection. However, there are three difficulties in radar-based target tracking in curves. First, there are massive data association calculations with poor accuracy. Second, the lane position relationship of target-vehicle cannot be identified accurately. Third, the target tracking algorithm has poor robustness and accuracy. A target tracking algorithm framework on curved road is proposed herein. The following four algorithms are applied to reduce data association calculations and improve accuracy. (1) The data rationality judgment method is employed to eliminate target measurement data outside the radar detection range. (2) Effective target life cycle rules are used to eliminate false targets and clutter. (3) Manhattan distance clustering algorithm is used to cluster multiple data into one. (4) The correspondence between the measurement data received by the radar and the target source is identified by the nearest neighbor (NN) data association. The following three algorithms aim to derive the position relationship between the ego-vehicle and the target-vehicles. (1) The lateral speed is obtained by estimating the state of motion of the ego-vehicle. (2) An algorithm for state compensation of target motion is presented by considering the yaw motion of the ego-vehicle. (3) A target lane relationship recognition model is built. The improved adaptive extended Kalman filter (IAEKF) is used to improve the target tracking robustness and accuracy. Finally, the vehicle test verifies that the algorithms proposed herein can accurately identify the lane position relationship. Experiments show that the framework has higher target tracking accuracy and lower computational time.

In manifold learning, the aim of alignment is to derive the global coordinate of manifold from the local coordinates of manifold’s patches. At present, most of manifold learning algorithms assume that the relation between the global and local coordinates is locally linear and based on this linear relation align the local coordinates of manifold’s patches into the global coordinate of manifold. There are two contributions in this paper. First, the nonlinear relation between the manifold’s global and local coordinates is deduced by making use of the differentiation of local pullback functions defined on the differential manifold. Second, the method of local linear iterative alignment is used to align the manifold’s local coordinates into the manifold’s global coordinate. The experimental results presented in this paper show that the errors of noniterative alignment are considerably large and can be reduced to almost zero within the first two iterations. The large errors of noniterative/linear alignment verify the nonlinear nature of alignment and justify the necessity of iterative alignment.

In this paper, a simple and efficient rule based energy management system for battery and supercapacitor hybrid energy storage system (HESS) used in electric vehicles is presented. The objective of the proposed energy management system is to focus on exploiting the supercapacitor characteristics and on increasing the battery lifetime and system efficiency. The role of the energy management system is to yield battery reference current, which is subsequently used by the controller of the DC/DC converter. First, a current controller is designed to realize load current distribution between battery and supercapacitor. Then a voltage controller is designed to ensure the supercapacitor SOC to fluctuate within a preset reasonable variation range. Finally, a commercial experimental platform is developed to verify the proposed control strategy. In addition, the energy efficiency and the cost analysis of the hybrid system are carried out based on the experimental results to explore the most cost-effective tradeoff.