2 May 2022 in IEEE Internet of Things Journal
Speed planning system is generally equipped for intelligent and connected vehicles (ICVs). Under the circumstances of autonomous driving, an energy-optimal speed trajectory is usually desired, particularly on urban arterial roads with complex traffic conditions involved. However, the existing speed planning solutions in the literature have not dealt with the problem of time consuming. Also, the ego vehicle could not perfectly track a precalculated speed reference because of the dynamically varying traffic. Thus, optimal speed planning cannot always be guaranteed. In this article, a fast optimal speed planning system for complex urban driving situations is established through an adaptive hierarchical control framework. In the planning layer, dynamic programming (DP) and the interior-point optimizer are jointly used to compute the global speed trajectory with access to signal phase and timing (SPaT) information. The computational burden is greatly alleviated based on a weighted orientation graph assumption and problem decomposition. The following layer utilizes the Informer, which is a transformer-based model, to predict preceding vehicle speed. Then, a target-switching model-predictive controller (MPC) is adopted for global speed trajectory following and adaption. The proposed approach significantly reduces speed planning computation time compared to previous solutions. Simulation results based on real road traffic scenes manifest that 22.0% of energy is saved compared with human driving.
20 December 2022 in IEEE Transactions on Automation Science and Engineering
This paper presents a novel interactive motion planning approach for left-turning of autonomous vehicles at uncontrolled intersections. A typical left-turning scenario that consists of agent vehicles and an autonomous ego vehicle is established. The autonomous ego vehicle aims to cross the uncontrolled intersection quickly and safely when meeting with the agent vehicles. A modified obstacle reciprocal collision avoidance (MORCA) prediction model is proposed to predict the trajectory of the agent vehicles with the considerations of longitudinal and lateral interaction-aware behaviors. The parameters of the MORCA prediction model are optimized using particle swarm optimization (PSO) with the inD datasets. Based on MORCA, a partially observable Markov decision process (POMDP) framework is established. The action and state spaces of the POMDP are extended reasonably to satisfy the requirement of real-time application. The simulation results show that the prediction precision is improved by 15% using the MORCA compared with the obstacle reciprocal collision avoidance (ORCA) prediction model. Meanwhile, the results manifest that the proposed MORCA-based POMDP planning method improves 43.8% in commuting efficiency compared with a traditional rule-based method, nearly as good as the vehicle-to-vehicle (V2V) communication is equipped. Note to Practitioners —The motivation of this article is to establish a safe and efficient planning framework for the left-turning of autonomous vehicles at uncontrolled intersections. Rule-based approaches were widely used in the previous studies but they are not optimal. In this paper, the lateral movements of vehicles at the intersection are considered for the first time. A MORCA prediction model is established and optimized to formulate a POMDP planning framework. The CARLA simulation demonstrates the effectiveness of the proposed MORCA-based POMDP planner. In future work, we will migrate the algorithm to a real-world test platform for experimentation.
13 February 2025 in IEEE Transactions on Transportation Electrification
In dynamic traffic flow conditions, lane-changing maneuvers hold significant potential for achieving energy and time efficiency. However, existing research often overlooks the influence of a global reference speed trajectory, especially in urban settings with multiple signalized intersections. To address this gap, this study proposes an eco-driving strategy for connected and automated vehicles (CAVs) that integrates deep reinforcement learning (DRL) and model predictive control (MPC), considering the impact of a guided speed profile with good synergy. A three-stage speed planning framework, following a coarse-smooth-optimization manner, is introduced to efficiently generate an energy-saving guided speed profile. After that, the guided speed profile is delivered into DRL, serving as a network input together with information on surrounding human driver vehicles (HDVs). The DRL adopts a soft actor-critic (SAC) algorithm integrating with an MPC controller, which can generate control outputs for both lane-changing and car-following maneuvers based on the DRL decisions and guided speed profile. Additionally, the MPC also certifies decisions for vehicle safety. Simulation results indicate that compared to benchmark methods, the proposed strategy achieves energy savings of up to 23.6% while maintaining high computational efficiency, which is accompanied by a smaller time delay approaching intersections and ensuring vehicle safety.
3 June 2024 in IEEE Internet of Things Journal
Pedestrian trajectory prediction is crucial across various domains, but remains challenging due to complex spatial interactions. Existing graph convolutional network (GCN) methods show promise but often fail to capture these dynamics effectively. To address this limitation, a sparse directed attention GCN (SDAGCN) is proposed to handle both social interactions among pedestrians and self-interactions within individuals. Traditional GCN-based methods often model social interactions as undirected or dense graphs. However, due to the field of view and awareness of collision avoidance of pedestrians, they tend to focus unilaterally on specific neighbors. To reflect this, SDAGCN constructs a sparse and directed spatial graph that considers these attributes innovatively. Furthermore, the attention weights of pedestrians toward their neighbors are closely tied to spatial conflicts. The conflicts are deeply influenced by relative velocity and distance. Therefore, these attributes are leveraged to calculate the attention weights. These two components form the sparse directed attention (SDA) mechanism, which effectively discerns the influence of neighbors on a target pedestrian in various situations. Additionally, the self-interaction of each pedestrian is significantly influenced by their speed. To capture variations in self-interaction across different states, SDAGCN employs a single-layer perceptron with the square of pedestrian speed as input. Experiments conducted on the ETH and UCY data sets demonstrate that our method outperforms other GCN-based spatial interaction methods, showcasing its potential in accurately predicting pedestrian trajectories by effectively handling complex social and self-interactions.
21 June 2024 in IEEE Sensors Journal
This paper proposes the LiDAR Map LiDAR-Visual-Inertial Localization (LM-LVIL) system, integrating LiDAR, visual, and inertial sensors within a pre-constructed LiDAR map. The key innovation is cross-modal fusion between camera images and point cloud maps via direct projection. Unlike traditional methods aligning 3D points triangulated from camera with the point cloud, our system projects map points into the camera frame to minimize photometric error, similar to direct methods in visual Simultaneous Localization and Mapping (SLAM). The system uses an iterated error state Kalman filter (IESKF) framework, incorporating IMU (Inertial Measurement Unit) integration, visual measurements, and LiDAR measurement for precise pose estimation. LiDAR measurement aligns points by ensuring scan points lie on a local plane in the map. Visual measurements include photometric measurement, projection measurement, 3D point alignment, and 2D-3D line measurement. Experimental results show that LM-VIL (LiDAR Map Visual-Inertial Localization) achieves competitive accuracy indoors compared to state-of-the-art methods. The LM-LVIL system improves accuracy in both indoor and outdoor scenarios compared to the LM-LIL (LiDAR Map LiDAR-Inertial Localization) system and the LiDAR localization baseline method. Our localization system balances accuracy and real-time performance, demonstrating application potential.
4 April 2024 in IEEE Transactions on Vehicular Technology
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.