Multimodal end-to-end autonomous driving has shown promising advancements in recent work. By embedding more modalities into end-to-end networks, the system's understanding of both static and dynamic aspects of the driving environment is enhanced, thereby improving the safety of autonomous driving. In this paper, we introduce METDrive, an end-to-end system that leverages temporal guidance from the embedded time series features of ego states, including rotation angles, steering, throttle signals, and waypoint vectors. The geometric features derived from the perception sensor data and the time series features of ego state data jointly guide the waypoint prediction with the proposed temporal guidance loss function. We evaluated METDrive on the CARLA leaderboard benchmarks, achieving a driving score of 70%, a route completion score of 94%, and an infraction score of 0.78.

Alibaba Cloud's centralized gateways relied heavily on high-capacity switching ASICs, but the abrupt halt of Tofino chip evolution in Jan 2023 forced us to seek alternatives that can meet the requirements of performance, supply-chain security, code reuse, and resource efficiency. After evaluating multiple options, we developed Albatross, our 3rd gen cloud gateway based on FPGA and x86 CPUs. Albatross delivers FPGA-based packet-level load balancing to the host CPUs to prevent CPU core overload, manages large reorder buffers under high-latency jitters (100μs) during complex cloud service processing, and resolves head-of-line (HOL) blocking from packet losses or software exceptions in CPUs. To avoid being overloaded by heavy hitters due to anomalies or attacks, it also implements a two-stage rate limiter for millions of tenants with only 2MB of FPGA memory. To maximize resource utilization, Albatross uses containerization to host multiple gateway instances and designs a BGP proxy to lessen the BGP peering overhead on uplink switches caused by high-density container deployments. After hundreds of man-months of development, a single Albatross node can process 80~120Mpps of cloud network traffic with an average latency of 20μs, reducing gateway and sandbox infra costs by 50%.

To promote the development of self-driving cars and ensure the safety of their functions, testing is an indispensable part, especially for functioning tests under critical scenarios. However, existing natural driving datasets mainly contain data under regular scenarios with a limited proportion of critical edge driving scenarios, which makes it difficult to extract useful critical scenario data from large-scale natural driving data, and test the performance of autonomous driving algorithms under critical scenarios becomes a challenge. To address this challenge, this paper proposes a deep learning-based β-VAE generative modeling framework (BLA-VAE), which combines BiLSTM and Attention mechanism to efficiently and reasonably generate vehicle trajectory data under critical scenarios, and use the data generated by the model to train autonomous driving prediction algorithms. The results show that the generated critical trajectory data has a stronger generalization ability and effectively improves the prediction ability of the automatic driving trajectory prediction algorithm in dangerous scenarios.

With the rapid development of a new generation of information and communication technologies such as artificial intelligence, big data, and the Internet of Things, the automotive industry is rapidly evolving in the direction of electrification, intelligence, and interconnection, and the research and application of autonomous driving technology has become a focus of much attention. Trajectory planning technology, as a core element of self-driving cars, directly affects the safety and comfort of the vehicle and other major technical performance indicators. Aiming at traditional trajectory planning algorithms’ low efficiency and static obstacle avoidance, this paper proposes a trajectory planning method for self-driving vehicles based on NSGA-II. The method employs an efficient spatial sampling-based approach to generate a set of feasible paths connecting the initial state and the sampled terminal state, while the trajectory at the lane change is optimized using a fifth-degree polynomial to obtain a smooth lane change trajectory. The trajectories generated by traditional methods may face control instability in the control phase, and this method enhances the real-time performance by accurately calculating the control quantities with better consideration of vehicle tracking control. Based on the timeliness, comfort, and safety as the optimization objectives, a multi-objective optimization model is constructed and solved using the NSGA-II algorithm to obtain a satisfactory vehicle path. Finally, the effectiveness of the trajectory planning method proposed in this paper is verified by simulation and analysis experiments, and the next research direction is prospected.

Social media platforms have emerged as the primary channels for the general public to access and share information. However, the rapid dissemination of news has led to the emergence of a significant amount of unverified content, posing a serious threat to media credibility and network security. The current solutions primarily focus on detecting fake news by extracting and fusing features from images and text, but they have not fully utilized the relevance within and between modalities, resulting in suboptimal fusion effects. In this paper, we propose a multimodal fusion framework via multi-attention mechanism (MFMA), which considers not only the semantic and relevance features of images, textual content, and Optical Character Recognition (OCR) text from the news, but also the multimodal relevance features between them. First, we extract text within images (OCR text) to address the issue of inadequate utilization of the visual modality in traditional methods. Second, we select more robust feature extractors to capture the independent characteristics of each modality and use a pre-trained FcaNet model to extract more comprehensive image quality features. Additionally, two relevance extraction modules are designed to achieve feature fusion within and between modalities. Finally, the combined features are fed into a classifier to determine the authenticity of the news. The experimental results and analysis indicate that the model we proposed effectively enhances the performance of fake news detection.

Wall following navigation uses the wall to guide the robot or vehicle to move from one position to another and always keep a certain distance from the wall in this process. It is of great significance in some aspects, such as rapid disease detection and auxiliary equipment detection of tunnel. This paper proposes an automatic wall following navigation method based on lidar to solve the existing problems in the tunnel scenes. Firstly, the mathematical model of spatial coordinate transformation among vehicle, point cloud, and the wall is established, and the RANSAC algorithm is used to improve the quality of point cloud of lidar. Then, according to the kinematic model of the autonomous vehicle, an improved pure pursuit wall following algorithm is proposed for lateral vehicle control, and the wall following mathematical model is established. Finally, the algorithm is verified in the two wall-following navigation cases under the tunnel wall, which shows that this method has a good tracking effect and stability.

In the real traffic environment, lane changing is a common behavior that causes accident frequently. In order to supplement the shortcomings of human behavior, make the vehicle achieve more reliable lane changing operation and improve the rationality and safety of vehicle lane changing, this paper presents a longitudinal and lateral feedback control method of automatic driving for lane changing scene. In this paper, the relationship model between time to collision and lane changing time is established, and the relationship between lane changing safety threshold is given, which improves the driving safety of lane changing scene. Then the trajectory planning model is established by polynomial curve method, and the vehicle control is achieved by linear quadratic regulator and proportional-integral-derivative control. Finally, simulation system is established based on Simulink and Prescan software. The experimental results verify the effectiveness of the control method.

In order to improve the robustness of the autonomous vehicle path planning algorithm and reduce the number of turns in the planned path, this paper proposes an adaptive ant colony algorithm path planning method. The algorithm optimizes the initial pheromone matrix based on the environment map, reduces the blindness of the initial ant colony in pathfinding, and improves the convergence speed. Then an adaptive heuristic function is used, which adaptively adjusts according to the different proportions of the heuristic function in the algorithm process, so as to avoid the algorithm being trapped in local optimum. The pheromone is updated according to the corners of the planned route, reducing the acute angle of the route and unnecessary turns to further optimize the route. The simulation results show that the proposed algorithm achieves good results. The simulation results show that the improved adaptive ant colony algorithm has faster convergence speed, higher path planning quality, and improved stability of planned paths than classical ant colony algorithms and other adaptive ant colony algorithms.

The application of V2X technology has promoted autonomous driving from autonomous vehicles to connected vehicles, so various V2X test methods have gradually become an important research direction. Generally V2X testing for the cooperative connected and automated mobility includes a test framework, infrastructure deployment, and use cases. These three parts of the V2X testing affect each other and determine the performance of different test methods. Firstly, this article reviews the related research of V2X performance testing and analyzes the usual techniques in the testing framework. Then RSU deployment is introduced as an example of facility deployment. Finally, the typical use cases and their performance indicators are summarized.

Self-driving and connected vehicles, communicating with one another and with the road infrastructure are expected to revolutionize the automotive industry and our life in the future. We propose a distributed heuristic algorithm based on 5G-V2X technology to solve the motion planning problem of industrial vehicles, especially passing through intersections in industrial parks. Autonomous industrial vehicles must not only ensure that vehicles do not collide with each other through intersections, but also ensure the safety of pedestrians. So this case demands highly on the communication and mutual cooperation among vehicles. To solve this problem, we employ 5G-V2X technology to ensure low delay and highly reliable communications. Then, we propose a distributed heuristic algorithm to solve the mutual cooperation problem among vehicles. Specifically speaking, intersection safety information system will download LDM (Local Dynamic Map) information to vehicle closest to the intersection, and then our solution will give higher priority to paths that have more vehicles and no pedestrians. Starting with highest priority approach, our solution sets a time period for the vehicle to establish a timetable for it to cross the intersection. Preliminary experiments results showed that on the premise of ensuring the safety of pedestrians, the industrial vehicles can pass through the intersection smoothly and have the lowest delay at the same time.

Project management for virtual enterprise is a challenging task, current project system cannot support it very well because of the gap between enterprises. After analyzing the characteristics of virtual enterprise, the project domain was defined for supporting the virtual enterprise project management system. Then we discuss the information sharing mechanism between domains based on public, protected and primate library, and present a system architecture based on grid service. Experiments show that the proposed approach can be used in distributed project management environment, such as networked manufacture system.