Automated driving is a promising tool for reducing traffic accidents. While some companies claim that many cutting-edge automated driving functions have been developed, how to evaluate the safety of automated vehicles remains an open question, which has become a crucial bottleneck. Scenario-based testing has been introduced to test automated vehicles, and much progress has been achieved. While data-driven and knowledge-based approaches are hot research topics, this survey is mainly about Data-Driven Scenario Generation (DDSG) for automated vehicle testing. Rather than describe the contributions of every study respectively, in this survey, methodologies from various studies are anatomized as solutions for several significant problems and compared with each other. This way, scholars and engineers can quickly find state-of-the-art approaches to the issues they might encounter. Furthermore, several critical challenges that might hinder DDSG are described, and responding solutions are presented at the end of this survey.

Merge scenarios on highway are often challenging for autonomous driving, due to its lack of sufficient tacit understanding on and subtle interaction with human drivers in the traffic flow. This, as a result, may impose serious safety risks, and often cause traffic jam with autonomous driving. Therefore, human-like autonomous driving becomes important, yet imperative. This paper presents an interaction-aware decision-making and planning method for human-like autonomous driving in merge scenarios. Rather than directly mimicking human behavior, deep inverse reinforcement learning is employed to learn the human-used reward function for decision-making and planning from naturalistic driving data to enhance interpretability and generalizability. To consider the interaction factor, the reward function for planning is utilized to evaluate the joint trajectories of the autonomous driving vehicle (ADV) and traffic vehicles. In contrast to predicting trajectories of traffic vehicles with the fixed trajectory of ADV given by the upstream prediction model, the trajectories of traffic vehicles are predicted by responding to the ADV's behavior in this paper. Additionally, the decision-making module is employed to reduce the solution space of planning via the selection of a proper gap for merging. Both the decision-making and planning algorithms follow a “sampling, evaluation, and selection” framework. After being verified through experiments, the results indicate that the planned trajectories with the presented method are highly similar to those of human drivers. Moreover, compared to the interaction-unaware planning method, the interaction-aware planning method behaves closer to human drivers.

The steering feedback torque (SFT) is a key part of driving simulator and steer-by-wire system, which provides driver with desired road feel and vehicle motion dynamics. Therefore, accurately modeling of SFT is of great significance for driver to get better steering feel. Since SFT can be affected by many linear or nonlinear factors, it is appropriate to model SFT using data-driven method. In this article, we adopt artificial neural network (ANN) and Gaussian process regression (GPR) to build the SFT model, and analyze the performance. Considering the fact that the contributing factors for SFT may vary under different driving conditions, we employ K-Means to precluster the training dataset to improve the model accuracy. The model training and validation processes are mainly data-driven, and the results show that GPR and ANN can achieve similar prediction accuracy with the mean square error to be around 0.10. Since the GPR model can be trained much faster than ANN model, it is more suitable for real-time application. It is further demonstrated that using preclustered data based on K-Means for model training can significantly improve its accuracy without sacrificing its computational efficiency.

Autonomous driving technology is considered the trend of future transportation. Millimeter-wave radar, with its ability for long-distance detection and all-weather operation, is a key sensor for autonomous driving. The development of various technologies in autonomous driving relies on extensive simulation testing, wherein simulating the output of real radar through radar models plays a crucial role. Currently, there are numerous distinctive radar modeling methods. To facilitate the better application and development of radar modeling methods, this study first analyzes the mechanism of radar detection and the interference factors it faces, to clarify the content of modeling and the key factors influencing modeling quality. Then, based on the actual application requirements, key indicators for measuring radar model performance are proposed. Furthermore, a comprehensive introduction is provided to various radar modeling techniques, along with the principles and relevant research progress. The advantages and disadvantages of these modeling methods are evaluated to determine their characteristics. Lastly, considering the development trends of autonomous driving technology, the future direction of radar modeling techniques is analyzed. Through the above content, this paper provides useful references and assistance for the development and application of radar modeling methods.

Modeling driving behavior plays a pivotal role in advancing the development of human-like autonomous driving. In light of this, this paper proposes a car-following behavior modeling method with sample-based deep inverse reinforcement learning (DIRL). Due to the challenges associated with feature extraction and the limited fitting capacity of linear functions, traditional IRL, which employs feature-based linear functions to represent reward functions, exhibits low modeling accuracy. Accordingly, DIRL leverages deep neural networks to represent reward functions. However, the requirement for reinforcement learning to determine the optimal policy for DIRL's reward function makes the training and inference processes computationally resource-intensive and inefficient. To address this issue, this paper proposes the sample-based DIRL. Through solution space discretization, sample-based DIRL streamlines the integration calculation of the partition function into a summation, resulting in improved computational efficiency. Specifically, it is a three-stage framework: sampling candidate trajectories, evaluating candidate trajectories, and selecting the trajectory with the highest reward. In order to evaluate DIRL at both the level of driving behavior and the reward function, the MPC-based virtual driver with the explicit reward function is utilized to collect driving data for training and assessing the convergence of the learned reward function. The experimental results confirm that the proposed method can accurately model the car-following behavior, and acquire the driver's reward function from the driving data.