Applying reinforcement learning to autonomous driving has garnered widespread attention. However, classical reinforcement learning methods optimize policies by maximizing expected rewards but lack sufficient safety considerations, often putting agents in hazardous situations. This paper proposes a risk-aware reinforcement learning approach for autonomous driving to improve the safety performance when crossing the intersection. Safe critics are constructed to evaluate driving risk and work in conjunction with the reward critic to update the actor. Based on this, a Lagrangian relaxation method and cyclic gradient iteration are combined to project actions into a feasible safe region. Furthermore, a Multi-hop and Multi-layer perception (MLP) mixed Attention Mechanism (MMAM) is incorporated into the actor-critic network, enabling the policy to adapt to dynamic traffic and overcome permutation sensitivity challenges. This allows the policy to focus more effectively on surrounding potential risks while enhancing the identification of passing opportunities. Simulation tests are conducted on different tasks at unsignalized intersections. The results show that the proposed approach effectively reduces collision rates and improves crossing efficiency in comparison to baseline algorithms. Additionally, our ablation experiments demonstrate the benefits of incorporating risk-awareness and MMAM into RL.

--Track testing plays a critical role in the safety evaluation of autonomous driving systems (ADS), as it provides a real-world interaction environment. However, the inflexibility in motion control of object targets and the absence of intelligent interactive testing methods often result in pre-fixed and limited testing scenarios. T o address these limitations, we propose a novel 5G cloud-controlled track testing framework, Real-world Troublemaker . This framework overcomes the rigidity of traditional pre-programmed control by leveraging 5G cloud-controlled object targets integrated with the Internet of Things (IoT) and vehicle teleoperation technologies. Unlike conventional testing methods that rely on pre-set conditions, we propose a dynamic game strategy based on a quadratic risk interaction utility function, facilitating intelligent interactions with the vehicle under test (VUT) and creating a more realistic and dynamic interaction environment. The proposed framework has been successfully implemented at the T ongji University Intelligent Connected V ehicle Evaluation Base. Field test results demonstrate that Troublemaker can perform dynamic interactive testing of ADS accurately and effectively. Compared to traditional methods, Troublemaker improves scenario reproduction accuracy by 65.2%, increases the diversity of interaction strategies by approximately 9.2 times, and enhances exposure frequency of safety-critical scenarios by 3.5 times in unprotected left-turn scenarios. Index T erms --Automated driving systems, track testing, 5G, cloud-controlled object targets, interaction scenarios. HE safety of automated driving systems (ADS) must be ensured prior to their practical implementation, which requires a well-established testing framework [1]. Existing test standards, such as ISO 26262 [2], UN R157 [3], and UN R171 [4], are not sufficient to comprehensively evaluate ADS. According to the driving automation levels defined by SAE J3016 from SAE International, a high-level ADS (i.e., Level 3 or higher) is expected to perform driving tasks independently and autonomously, with the driver no longer retaining continuous control over vehicle movement [5]. While ADS has already been deployed in various countries and regions, numerous ADS traffic incidents highlight that safety testing for high-level ADS remains a critical technical challenge. In comparison to traditional vehicles and advanced driver assistance systems (ADAS), high-level ADS testing faces significant transformations and challenges, particularly in terms of both test subjects and requirements.

Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving, which is increasingly applied in diverse driving scenarios. However, driving is a multi-attribute problem, leading to challenges in achieving multi-objective compatibility for current RL methods, especially in both policy execution and policy iteration. On the one hand, the common action space structure with single action type limits driving flexibility or results in large behavior fluctuations during policy execution. On the other hand, the multi-attribute weighted single reward function result in the agent's disproportionate attention to certain objectives during policy iterations. To this end, we propose a Multi-objective Ensemble-Critic reinforcement learning method with Hybrid Parametrized Action for multi-objective compatible autonomous driving. Specifically, a parameterized action space is constructed to generate hybrid driving actions, combining both abstract guidance and concrete control commands. A multi-objective critics architecture is constructed considering multiple attribute rewards, to ensure simultaneously focusing on different driving objectives. Additionally, uncertainty-based exploration strategy is introduced to help the agent faster approach viable driving policy. The experimental results in both the simulated traffic environment and the HighD dataset demonstrate that our method can achieve multi-objective compatible autonomous driving in terms of driving efficiency, action consistency, and safety. It enhances the general performance of the driving while significantly increasing training efficiency.

The driving interaction--a critical yet complex aspect of daily driving--lies at the core of autonomous driving research. However, real-world driving scenarios sparsely capture rich interaction events, limiting the availability of comprehensive trajectory datasets for this purpose. To address this challenge, we present InterHub, a dense interaction dataset derived by mining interaction events from extensive naturalistic driving records. We employ formal methods to describe and extract multi-agent interaction events, exposing the limitations of existing autonomous driving solutions. Additionally, we introduce a user-friendly toolkit enabling the expansion of InterHub with both public and private data.

Four-dimensional (4D) radar--visual odometry (4DRVO) integrates complementary information from 4D radar and cameras, making it an attractive solution for achieving accurate and robust pose estimation. However, 4DRVO may exhibit significant tracking errors owing to three main factors: 1) sparsity of 4D radar point clouds; 2) inaccurate data association and insufficient feature interaction between the 4D radar and camera; and 3) disturbances caused by dynamic objects in the environment, affecting odometry estimation. In this paper, we present 4DRVO-Net, which is a method for 4D radar--visual odometry. This method leverages the feature pyramid, pose warping, and cost volume (PWC) network architecture to progressively estimate and refine poses. Specifically, we propose a multi-scale feature extraction network called Radar-PointNet++ that fully considers rich 4D radar point information, enabling fine-grained learning for sparse 4D radar point clouds. To effectively integrate the two modalities, we design an adaptive 4D radar--camera fusion module (A-RCFM) that automatically selects image features based on 4D radar point features, facilitating multi-scale cross-modal feature interaction and adaptive multi-modal feature fusion. In addition, we introduce a velocity-guided point-confidence estimation module to measure local motion patterns, reduce the influence of dynamic objects and outliers, and provide continuous updates during pose refinement. We demonstrate the excellent performance of our method and the effectiveness of each module design on both the VoD and in-house datasets. Our method outperforms all learning-based and geometry-based methods for most sequences in the VoD dataset. Furthermore, it has exhibited promising performance that closely approaches that of the 64-line LiDAR odometry results of A-LOAM without mapping optimization.

Interaction between the background vehicles (BVs) and automated vehicles (AVs) in scenario-based testing plays a critical role in evaluating the intelligence of the AVs. Current testing scenarios typically employ predefined or scripted BVs, which inadequately reflect the complexity of human-like social behaviors in real-world driving scenarios, and also lack a systematic metric for evaluating the comprehensive intelligence of AVs. Therefore, this paper proposes an evolving scenario generation method that utilizes deep reinforcement learning (DRL) to create human-like BVs for testing and intelligence evaluation of AVs. Firstly, a class of driver models with human-like competitive, cooperative, and mutual driving motivations is designed. Then, utilizing an improved "level-k" training procedure, the three distinct driver models acquire game-based interactive driving policies. And these models are assigned to BVs for generating evolving scenarios in which all BVs can interact continuously and evolve diverse contents. Next, a framework including safety, driving efficiency, and interaction utility are presented to evaluate and quantify the intelligence performance of 3 systems under test (SUTs), indicating the effectiveness of the evolving scenario for intelligence testing. Finally, the complexity and fidelity of the proposed evolving testing scenario are validated. The results demonstrate that the proposed evolving scenario exhibits the highest level of complexity compared to other baseline scenarios and has more than 85% similarity to naturalistic driving data. This highlights the potential of the proposed method to facilitate the development and evaluation of high-level AVs in a realistic and challenging environment.

Vehicle control is one of the most critical challenges in autonomous vehicles (AVs) and connected and automated vehicles (CAVs), and it is paramount in vehicle safety, passenger comfort, transportation efficiency, and energy saving. This survey attempts to provide a comprehensive and thorough overview of the current state of vehicle control technology, focusing on the evolution from vehicle state estimation and trajectory tracking control in AVs at the microscopic level to collaborative control in CAVs at the macroscopic level. First, this review starts with vehicle key state estimation, specifically vehicle sideslip angle, which is the most pivotal state for vehicle trajectory control, to discuss representative approaches. Then, we present symbolic vehicle trajectory tracking control approaches for AVs. On top of that, we further review the collaborative control frameworks for CAVs and corresponding applications. Finally, this survey concludes with a discussion of future research directions and the challenges. This survey aims to provide a contextualized and in-depth look at state of the art in vehicle control for AVs and CAVs, identifying critical areas of focus and pointing out the potential areas for further exploration.