Intelligent vehicles (IVs) have gained worldwide attention due to their increased convenience, safety advantages, and potential commercial value. Despite predictions of commercial deployment by 2025, implementation remains limited to small-scale validation, with precise tracking controllers and motion planners being essential prerequisites for IVs. This paper reviews state-of-the-art motion planning methods for IVs, including pipeline planning and end-to-end planning methods. The study examines the selection, expansion, and optimization operations in a pipeline method, while it investigates training approaches and validation scenarios for driving tasks in end-to-end methods. Experimental platforms are reviewed to assist readers in choosing suitable training and validation strategies. A side-by-side comparison of the methods is provided to highlight their strengths and limitations, aiding system-level design choices. Current challenges and future perspectives are also discussed in this survey.

Developing autonomous driving technologies necessitates addressing safety and cost concerns. Both academic research and commercial applications of autonomous driving vehicles require extensive simulation and real-world testing. The challenge lies in effectively transferring driving knowledge from the virtual simulation world to the reality world, known as the reality gap (RG). This gap arises due to differences in lighting, textures, vehicle dynamics, and agents' behaviors between the two environments. To address this issue, researchers have explored three main approaches: sim2real, digital twins (DTs), and parallel intelligence (PI) technologies. This paper reviews these solutions and examines their applications and innovations in autonomous driving. Furthermore, we delve into the state-of-the-art algorithms, models, and involved simulators, and discuss the developmental process from sim2real to DTs and PI. The presentation also sheds light on the challenges and future perspectives in the development of sim2real, DTs, and PI in the field of autonomous driving.

End-to-end autonomous driving provides a simple and efficient framework for autonomous driving systems, which can directly obtain control commands from raw perception data. However, it fails to address stability and interpretability problems in complex urban scenarios. In this paper, we construct a two-stage end-to-end autonomous driving model for complex urban scenarios, named HIIL (Hierarchical Interpretable Imitation Learning), which integrates interpretable BEV mask and steering angle to solve the problems shown above. In Stage One, we propose a pretrained Bird's Eye View (BEV) model which leverages a BEV mask to present an interpretation of the surrounding environment. In Stage Two, we construct an Interpretable Imitation Learning (IIL) model that fuses BEV latent feature from Stage One with an additional steering angle from Pure-Pursuit (PP) algorithm. In the HIIL model, visual information is converted to semantic images by the semantic segmentation network, and the semantic images are encoded to extract the BEV latent feature, which are decoded to predict BEV masks and fed to the IIL as perception data. In this way, the BEV latent feature bridges the BEV and IIL models. Visual information can be supplemented by the calculated steering angle for PP algorithm, speed vector, and location information, thus it could have better performance in complex and terrible scenarios. Our HIIL model meets an urgent requirement for interpretability and robustness of autonomous driving. We validate the proposed model in the CARLA simulator with extensive experiments which show remarkable interpretability, generalization, and robustness capability in unknown scenarios for navigation tasks.

Motion planning is one of the most significant part in autonomous driving. Learning-based motion planning methods attract many researchers' attention due to the abilities of learning from the environment and directly making decisions from the perception. The deep Q-network, as a popular reinforcement learning method, has achieved great progress in autonomous driving, but these methods seldom use the global path information to handle the issue of directional planning such as making a turning at an intersection since the agent usually learns driving strategies only by the designed reward function, which is difficult to adapt to the driving scenarios of urban roads. Moreover, different motion commands such as the steering wheel and accelerator are associated with each other from classic Q-networks, which easily leads to an unstable prediction of the motion commands since they are independently controlled in a practical driving system. In this paper, a conditional deep Q-network for directional planning is proposed and applied in end-to-end autonomous driving, where the global path is used to guide the vehicle to drive from the origination to the destination. To handle the dependency of different motion commands in Q-networks, we take use of the idea of fuzzy control and develop a defuzzification method to improve the stability of predicting the values of different motion commands. We conduct comprehensive experiments in the CARLA simulator and compare our method with the state-of-the-art methods. Experimental results demonstrate the proposed method achieves better learning performance and driving stability performance than other methods.

In autonomous driving, many learning-based methods for motion planing have been proposed in literature, which can predict motion commands directly from the sensory data of the environment, but these methods can neither predict multiple motion commands, such as steering angle, accelerator and brake, nor balance errors among different motion commands. In this paper, we propose a deep cascaded neural network for predicting multiple motion commands which can be trained in an end-to-end manner for autonomous driving. The proposed deep cascaded neural network consists of a convolutional neural network (CNN) and three long short-term memory (LSTM) units, fed with images from a front-facing camera installed at the vehicle. As the outputs, the proposed model can predict thee motion planning commands simultaneously including steering angle, acceleration, and brake to enable the autonomous driving. In order to balance errors among different motion commands and improve prediction accuracy, we propose a new network training algorithm, where three independent loss functions are designed to separately update the weights in the three LSTMs connected to three motion commands. We conduct comprehensive experiments using the data from a driving simulator and compare our method with the state-of-the-art methods. Simulation results demonstrate the proposed motion planning model achieves better accuracy performance than other models.

Automatic overtaking is a challenging task for self-driving vehicles. Traditional rule-based methods for overtaking in autonomous driving heavily rely on many predefined rules and are difficult to apply in complex driving scenarios. Learning-based methods usually use convolutional networks, recurrent networks, and multilayer perceptrons, etc., to extract features from environments, but they fail to effectively represent geometric and interactive information among traffic participants. Classic graph convolutional networks (GCNs) have the ability of represent graph-structural information but are limited to stable relationship representation due to the fixed adjacency matrix when applied in autonomous driving. In this paper, we propose a novel dynamic graph learning method based on a graph convolutional network with a trainable adjacency matrix (TAM-GCN) to enable the learning of dynamic relationships among different nodes in an ever-changing driving scene. In addition, we develop a planning method for overtaking strategy in autonomous driving, where the proposed TAM-GCN is used to extract the spatial graph-structural features, select appropriate overtaking time, and generate efficient overtaking actions. The proposed model is trained using the imitation learning method. We conduct comprehensive experiments in both closed-loop and open-loop testing in the CARLA simulator and compare our method with state-of-the-art methods. Experimental results demonstrate the proposed method achieves better accuracy, safety and overtaking performance than existing methods.