Lane change maneuver of high-speed automated vehicles is complicated since it involves highly nonlinear vehicle dynamics, which is critical for the driving safety and handling stability. Addressing this challenge, we present the dynamic modeling and control of high-speed automated vehicles for lane change maneuver. A nonlinear single-track vehicle dynamics model and a multi-segment lane change process model are employed. Variable time-steps are utilized for the vehicle model discretization to ensure a long enough prediction horizon while maintaining model fidelity and computational feasibility. Accordingly, the control of lane change maneuver is addressed in two successive stages. First, by considering the lane change maneuver as primarily a longitudinal control problem, velocity profiles are determined to ensure the longitudinal safety of this maneuver. Then, the associated lateral control is generated with a model predictive controller, taking the handling stability envelope, coupled tire forces and environmental constraints into account. Simulations demonstrate the real-time ability and stable-handling capability of the proposed approach.

In complex and dynamic urban traffic scenarios, the accurate prediction of trajectories of surrounding traffic participants (vehicles, pedestrians, etc) with interactive behaviours plays an important role in the navigation and the motion planning of the ego vehicle. In this paper, based on the graph neural network (GNN), we propose a hierarchical GNN framework to model interactions of heterogeneous traffic participants (vehicles, pedestrians and riders) combined with LSTM to predict their trajectories. The proposed framework consists of two modules with two GNNs for interactive events recognition (IER) and trajectory prediction (TP). The IER module is used to recognise interactive events between traffic participants and the ego vehicle. With the recognised results as the input, the TP module is built for interactive trajectory prediction. In addition, to realise the multi-step prediction, a long short-term memory network (LSTM) is combined with GNN in the TP module. The proposed hierarchical framework is verified by the naturalistic driving data collected from the urban traffic environment. Comparative results with state-of-the-art methods indicate that the hierarchical GNN framework obtains an outstanding performance in the recognition of interactive events and the prediction of interactive behaviours.

Effectively predicting interactive behaviors of traffic participants in the urban road is the key to successful decision-making and motion planning of intelligent vehicles. In this article, based on the data collected from vehicle on-board sensors, a graph-neural-network-based multitask learning framework (GNN-MTLF) is proposed to accurately predict trajectories of traffic participants with interactive behaviors. The interactive behavior considered in this research includes interactive events and trajectories that are modeled as spatial-temporal graphs using the GNN. Under the GNN-MTLF, the prediction process contains two main parts: recognition of interactive events and prediction of interactive trajectories. An integrated loss function is designed for multitask learning with the purpose of prediction and recognition. The proposed framework is verified using naturalistic driving data in the urban road. Experimental results show a superior performance of the GNN-MTLF compared to baseline methods and the potential for improving the road mobility.

The path planning of unmanned differential steering vehicles (UDSVs) in the off-road environment not only needs to consider the non-complete constraints of vehicles but also faces the challenges of complex off-road terrains and obstacles. In this paper, an integrated path planning system is proposed to handle the influence of kinematic vehicle model, off-road terrains and obstacles systematically for the path planning of UDSVs. To improve the planning efficiency, a Pre-planning is designed and carried out using the Voronoi diagram established in the 3D environment with obstacles. By combining the potential field functions (PFF) related to passable obstacles and 3D terrains, an integrated PFF is defined to represent the movement cost of UDSV in the nonlinear optimal control (NOC) problem. Based on the NOC, a channel path planning (CPP) problem is formulated to avoid the untraceable path caused by the traditional line path planning (LPP). Simulation results show that the proposed system can plan a feasible path fast with the constraints from vehicle kinematics, obstacle avoidance and off-road terrains.

Driver model adaptation (DMA) provides a way to model the target driver when sufficient data are not available. Traditional DMA methods running at the model level are restricted by the specific model structures and cannot make full use of the historical data. In this paper, a novel DMA framework based on transfer learning (TL) is proposed to deal with the adaptation of driver models in lane-changing scenarios at the data level. Under the proposed DMA framework, a new TL approach named DTW-LPA that combines dynamic time warping (DTW) and local Procrustes analysis (LPA) is developed. Using the DTW, the relationship between the datasets for different drivers can be found automatically. Based on this relationship, the LPA can transfer the data in the historical dataset to the dataset of a newly-involved driver (target driver). In this way, sufficient data can be obtained for the target driver. After the data transferring process, a proper modeling method, such as the Gaussian mixture regression (GMR), can be applied to train the model for the target driver. Data collected from a driving simulator and realistic driving scenes are used to validate the proposed method in various experiments. Compared with the GMR-only and GMR-MAP methods, the DTW-LPA shows better performance on the model accuracy with much lower predicting errors in most cases.

Learning-based methods have gained increasing attention in the intelligent vehicle community for developing highly autonomous vehicles and advanced driving assistance systems (ADAS). However, traditional offline learning methods lack the ability to adapt to individual driving behavior. To overcome this limitation, a combined learning framework (CLF) based on the Natural Actor Critic (NAC) learning and general regression neural network (GRNN) is developed in this paper. GRNN can be trained offline based on the historical data, while NAC is carried out online. In this way, the general behavior learned by the offline module can be reused and adjusted by the online module to capture the driver-specific behavior. Driving data collected from human drivers through a driving simulator are used to test the proposed learning framework. The complex overtaking behavior is selected to formulate the learning problem and test scenarios. Experimental results show that the proposed system performs well on learning driver-specific behavior for overtaking, and compared with the Gaussian mixture model-maximum-a-posterior method, CLF shows a more flexible performance when newly-involved drivers are considered.