Weiqiang Liang

Acquiring valid signals for collision risk during driving is essential for the design of safety assistance or self-driving systems. Currently, there is a gap in accessible models that offer rational alerts for diverse driving scenarios. This article introduces a generalized, yet concise framework called the potential damage risk (PODAR) model for estimating collision risk and issuing warnings of hazard cases. The PODAR model is devised by connecting collision risk with potential collision damage across both spatial and temporal dimensions in a meaningful physical way, which includes four key components: trajectory prediction, damage estimation, spatiotemporal attenuation, and attention simulation. An empirical model featuring six adjustable parameters is presented and calibrated using a publicly available dataset for validation. With predefined fixed risk thresholds, the PODAR model demonstrates the ability to issue valid warnings for potential collisions in both longitudinal and lateral directions, negating the need for manual driving situation classification. The study investigates the performance of the PODAR model in a range of dynamic driving situations through numerical simulations, such as side-pass, car-following, and an unsignaled left turn. Additionally, three demonstrative cases derived from the InD dataset, which features realistic driving scenarios, are also presented. The results reveal that the PODAR model is effective in estimating risk and detecting collisions, providing reliable signals for potential collisions. In addition, the PODAR model, as a generalized framework, has the ability to incorporate existing metrics and exhibits impressive scalability to integrate new advancements in trajectory prediction and human-like risk perception, thanks to its modular structure.

This paper proposes a novel LiDAR inertial odometry (LIO) incorporating vehicle motion characteristics (VMC) tailored for ground vehicles. While most advanced LIO systems are designed for 6 degrees of freedom (DOF) SE(3), which are not ideally suited for ground vehicles, this paper investigates the performance of the vehicle-LiDAR-IMU system by considering the vehicle motion characteristics. The system combines IMU propagation, LiDAR measurements, ground surface measurements and 3 dimension (3D) vehicle kinematic model measurements within an iterated Kalman filter framework. To ensure a robust system bootstrapping, the temporal and spatial parameters of the vehicle-LiDAR-IMU system are calibrated first. Then, in addition to the IMU preintegration and LiDAR measurements, constraints are established between the ground surface and the vehicle pose by calculating the normal of the ground beneath the vehicle in the local point cloud map. Moreover, measurements of the 3D vehicle kinematic model with angular velocity and velocity constraints are adopted. Ground surface is considered in the 3D kinematic model for vehicle angular velocity calculation. The results from simulations and vehicle experiments demonstrate that the proposed method improves accuracy compared with state-of-the-art LiDAR SLAM methods while maintaining a real-time implementation capability for vehicles.

For autonomous vehicles, Simultaneous localization and mapping (SLAM) is one of the fundamental capabilities. Accurate and reliable SLAM are important for autonomous vehicles. In this work, we propose a novel LiDAR odometry and mapping method assisted by semantic segmentation and moving object segmentation. First, to acquire semantic information of point clouds and distinguish moving objects, a framework for segmenting LiDAR point clouds is proposed. Then an effective method for integrating semantic information and moving object information into feature-based LiDAR SLAM is proposed. With the assistance of semantic information and moving object information, moving points are filtered out, and semantic constrains are added in feature extraction and pose estimation to improve the localization accuracy. The experiment results on public datasets show that, compared to the baseline, the average relative pose estimation error of our proposed method is reduced by21.4% in rotation and 29.4% in translation.

Eco-driving incorporating multiple signalized intersections simultaneously has been proven to substantially benefit connected vehicles (CVs) in energy performance. However, ignoring the dynamic variation of waiting queues before downstream intersections may prevent CVs from following the obtained speed profile on security grounds. In this article, the dynamic variation of the waiting queue is modeled and predicted based on shockwave theory and data-driven-based traffic flow prediction. To formulate the waiting queues as additional time-varying constraints for optimization problems, an extended traffic signal model is constructed based on the prediction. Furthermore, a hierarchical optimization framework is proposed, under which the hybrid optimization problem is decomposed into a discrete problem and a continuous one. Monte Carlo simulation demonstrates that if the proposed eco-driving approach is implemented, failure to follow the reference speed profile decreases by 79.4%. Also, the fuel consumption can be saved by over 4% compared with approaches ignoring the waiting queue.