Qingchao Liu

In recent years, the autonomous driving technology has witnessed rapid global development, offering effective solutions to increasingly severe challenges related to traffic congestion and road safety. Among various paradigms, end-to-end autonomous driving has emerged as a promising alternative to traditional modular systems, due to its streamlined architecture, enhanced decision consistency, and superior generalization capabilities. This survey provides a comprehensive review of the evolution and core technologies of end-to-end autonomous driving. It emphasizes the applications and developments of imitation learning (IL), reinforcement learning (RL), and other paradigms. Furthermore, it highlights the emerging paradigm empowered by foundation models, such as large language models (LLMs) and vision–language models (VLMs), and systematically categorizes recent advances in planning, reasoning, data generation, and scene understanding. In light of persistent challenges, such as multimodal fusion complexity, low sample efficiency, and safety risks, this survey summarizes the representative research efforts and corresponding solutions. Finally, it outlines future directions, including the integration of world models (WMs) for unified data generation and inference optimization, the advancement of foundation model architectures toward modular design, sparse activation mechanisms, and knowledge distillation, and the realization of deployable, transferable, and unified multimodal frameworks. This survey aims to serve as a comprehensive theoretical and technical reference for researchers in end-to-end autonomous driving, facilitating its evolution toward higher performance, stronger generalization, and enhanced safety assurance.

Increasing global food production to address challenges from population growth, labor shortages, and climate change necessitates a significant enhancement of agricultural sustainability. Autonomous agricultural machinery, a recognized application of precision agriculture, offers a promising solution to boost productivity, resource efficiency, and environmental sustainability. This study presents a systematic review of autonomous driving technologies for agricultural machinery based on 506 rigorously selected publications. The review emphasizes three core aspects: navigation reliability assurance, motion control mechanisms for both vehicles and implements, and actuator fault-tolerance strategies in complex agricultural environments. Applications in farmland, orchards, and livestock farming demonstrate substantial potential. This study also discusses current challenges and future development trends. It aims to provide a reference and technical guidance for the engineering implementation of intelligent agricultural machinery and to support sustainable agricultural transformation.

In an autonomous vehicle-mixed traffic flow (AV-MTF) environment, accurately predicting vehicle speeds is essential for vehicle and traffic operation and management. However, existing research has not achieved high-precision vehicle speed prediction in mixed autonomous traffic environments. To address this, we proposed a car-following speed prediction and anomaly detection method based on the attention long short-term memory (LSTM)–Transformer model. We first employ a multihead attention-enhanced LSTM network to dynamically classify vehicle categories in the AV-MTF environment based on vehicle motion states. We propose a novel Transformer-based model that embeds classification labels and car-following state information, enabling precise speed prediction in AV-MTF environments. Additionally, the anomaly detection algorithm is proposed to identify abnormal speeds in car-following situations, covering both constant and instant offsets. The proposed models were trained and tested using the OpenACC dataset, and the effectiveness of the attention LSTM–Transformer-based speed prediction model and anomaly detection algorithm is validated. Results show that the classification model achieves an accuracy of 95.57%. Compared to baseline models, the speed prediction model considering vehicle category labels effectively reduces the prediction errors by more than 6.8% in all horizons. This car-following speed anomaly detector achieves over 99% accuracy for constant speed offsets and nearly 90% detection rate for small instant speed anomalies. The findings of this study provide valuable insights for vehicle and traffic operation and management in future AV-MTF environments.

The representation form of multimodal motion prediction results is critical to the efficiency of the prediction-planning workflow. However, most existing methods generate multiple sets of trajectories for each independent agent to cover diverse modalities, overlooking interactions among agents during the prediction period, making it challenging to achieve scene-level consistency in multi-agent predictions. This paper introduces MliG, a scene-level multimodal conditional motion prediction framework based on Multi-Layer Interaction Graph. The interaction graph designed explicitly represent the interaction behaviors of multi-agents over future periods, guiding conditional trajectory prediction to achieve planning-friendly prediction result representation. First, an Interaction-Mask-based determination strategy is introduced to obtain ground truth interaction labels, enabling data-driven implicit relationship learning, and the generated training labels can support the accurate construction of the interaction graph. Second, scene simplification and modality decoupling using the interaction graph make it easier to fuse information and represent driving scenarios efficiently. Based on the multi-layer design, the complex interactions between agent pairs are decomposed into different group and modality layers, ensuring the diversity of interactions while improving the efficiency of conditional predictions. Extensive experiments on the Argoverse 2, Argoverse 1, and INTERACTION Datasets demonstrate that the proposed MliG achieves high prediction accuracy and significantly improves the scene-level consistency of trajectory prediction modalities for multi-agents in the same driving scenario.

The length of time for drivers to take over conditionally automated driving vehicles (CADV) is often influenced by numerous factors, especially the mixed traffic flow environment. To analyze the influencing factors of driver’s takeover time in the mixed traffic flow environment, we study a real-vehicle takeover experiment with the CADV and radar video integrated machine provided by Jiangsu University. DeepGBM algorithm and Shapley additive explanation (SHAP) are utilized to predict and analyze the takeover time based on the data obtained from the real-vehicle experiment. The results show that the DeepGBM algorithm performs a better accuracy in predicting the takeover time compared with the other algorithms. Moreover, the predicting effect of DeepGBM in the scene of average takeover time is better than the shorter and longer ones. On the other hand, when taking over CADV in the intersection area, the driver pays more attention to the vehicle’s speed. While in the non-intersection area, the driver is more attentive to the longitudinal distance difference with the vehicle ahead. This study further found that CADVs are subject to significant lateral interference for the takeover process in intersection areas, significantly impacting the driver’s takeover time and vehicle safety. This study can provide a theoretical reference for automated driving companies to design takeover times.