Cooperative perception enabled by Vehicle-to-Everything communication has shown great promise in enhancing situational awareness for autonomous vehicles and other mobile robotic platforms. Despite recent advances in perception backbones and multi-agent fusion, real-world deployments remain challenged by hard detection cases, exemplified by partial detections and noise accumulation which limit downstream detection accuracy. This work presents Diffusion on Reinforced Cooperative Perception (DRCP), a real-time deployable framework designed to address aforementioned issues in dynamic driving environments. DRCP integrates two key components: (1) Precise-Pyramid-Cross-Modality-Cross-Agent, a cross-modal cooperative perception module that leverages camera-intrinsic-aware angular partitioning for attention-based fusion and adaptive convolution to better exploit external features; and (2) Mask-Diffusion-Mask-Aggregation, a novel lightweight diffusion-based refinement module that encourages robustness against feature perturbations and aligns bird's-eye-view features closer to the task-optimal manifold. The proposed system achieves real-time performance on mobile platforms while significantly improving robustness under challenging conditions. Code will be released in late 2025.

Internet of Vehicles (IoV) is a typical extension of Internet of Things (IoT). Specifically, Federated Learning (FL) is capable of alleviating the knowledge sharing and privacy protection problems of IoV, and further enhancing the driving experience and service quality. However, dueto the scanty data results of new environment and the high-cost of expert data-labeling, posing an imminent challenge of how to reinforcement the vehicles’ data. In this letter, a data reinforcement mechanism is proposed to utilize the vehicles’ unlabeled dataset sufficiently and enhance the vehicle collaboration ultimately. Particularly, the dataset distribution characteristics of vehicles’ datasets are calculated to measure the dataset similarity. Furthermore, the labeling models are distributed to vehicles to empower the unlabeled data with the assistance of dataset distribution characteristics. Experimental results show that the proposed data reinforcement mechanism is capable of labeling the unlabeled data accurately and improving the performance of FL.

Collaborative perception in multi-agent system enhances overall perceptual capabilities by facilitating the exchange of complementary information among agents. Current mainstream collaborative perception methods rely on discretized feature maps to conduct fusion, which however, lacks flexibility in extracting and transmitting the informative features and can hardly focus on the informative features during fusion. To address these problems, this paper proposes a novel Anchor-Centric paradigm for Collaborative Object detection (ACCO). It avoids grid precision issues and allows more flexible and efficient anchor-centric communication and fusion. ACCO is composed by three main components: (1) Anchor featuring block (AFB) that targets to generate anchor proposals and projects prepared anchor queries to image features. (2) Anchor confidence generator (ACG) is designed to minimize communication by selecting only the features in the confident anchors to transmit. (3) A local-global fusion module, in which local fusion is anchor alignment-based fusion (LAAF) and global fusion is conducted by spatial-aware cross-attention (SACA). LAAF and SACA run in multilayers, so agents conduct anchor-centric fusion iteratively to adjust the anchor proposals. Comprehensive experiments are conducted to evaluate ACCO on OPV2V and Dair-V2x datasets, which demonstrate ACCO's superiority in reducing the communication volume, and in improving the perception range and detection performances. Code can be found at: https://github.com/sidiangongyuan/ACCO.

Cooperative perception has emerged as a promising solution to overcome the limitations of individual sensing in autonomous driving. However, its performance in real-world scenarios is often inconsistent due to dynamic environments and fluctuating wireless communication quality. In particular, the quality of service (QoS) in both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) links is frequently affected by physical constraints, while limited communication and computation resources further exacerbate system latency and degrade perception accuracy. To address these challenges, we propose a novel communication-sensing-computation integrated cooperative perception framework for connected vehicular networks. This framework considers V2V and V2I cooperation and introduces a unified optimization strategy that simultaneously handles resource allocation, fusion method selection, and cooperative agent selection. We formulate this as a mixed-integer nonlinear programming (MINLP) problem and decompose it into two subproblems, which are efficiently solved using a block coordinate descent method. To enable adaptive and scalable decision-making, we design a deep reinforcement learning (DRL)-based joint resource allocation scheme for V2I, and extend it with a federated learning (FL) variant for decentralized V2V scenarios. Extensive multi-factor simulations demonstrate that our method significantly improves perception accuracy, reduces latency, and enhances robustness under diverse network conditions. These results validate the effectiveness and practicality of our proposed framework in real-world cooperative driving environments.

With cutting-edge sensors and learning algorithms developed for vehicular perception, breakthrough advancements have been made in the perception-based end-to-end autonomous driving in recent years. However, the reliability of autonomous driving systems could be compromised by the vulnerability of perception module to occlusion. To address this issue, the integration of vehicle-to-vehicle communication enabled perception data sharing in the dynamic driving task has been proposed and has yielded notable results, as demonstrated by COOPERNAUT, a cooperative system based on distributed lidar perception. In this paper, we introduce ICOP, an end-to-end driving system based on multi-agent camera cooperative perception, to select sensor sharing nodes and to fuse intermediate image data features for learning a driving policy. In the ICOP system, each agent encodes image information into Bird’s Eye View (BEV) representations individually, and these representations are then transmitted as payloads of V2X (vehicle-to-everything) messages via wireless connection, thus enables capturing global spatial interactions among agents to form comprehensive BEV perception information used for final control decision-making. Supported by our designed mechanism of vehicle-to-vehicle communication and transformer block to achieve acceptable image sensory data size for transmission, the experiments suggest that the proposed cooperative perception driving system achieves better results than lidar-based systems in challenging driving situations compared to prior works.