SV2V-RSim is introduced, a large-scale, multi-modal, near-realistic simulation dataset engineered to elevate agent diversity and realism, and the Select Vehicles Adaptively (SVA) module, which optimizes collaborator selection to balance perception performance against communication bandwidth constraints.
Abstract
Vehicle-to-Vehicle (V2V) cooperative perception enhances autonomous driving by enabling vehicles to share information beyond their direct line of sight. However, existing V2V datasets are limited by a small number of participating agents, static collaborator selection strategies, and a significant domain gap between simulated and real-world environments. To overcome these challenges, we introduce SV2V-RSim, a large-scale, multi-modal, near-realistic simulation dataset engineered to elevate agent diversity and realism. Additionally, we present the Select Vehicles Adaptively (SVA) module, which optimizes collaborator selection to balance perception performance against communication bandwidth constraints. Our dataset is generated using the Unreal Engine 5-based simulator that integrates high-fidelity 3D assets, diverse environments, and intricate traffic scenarios. All vehicles within a specified range of the ego vehicle are equipped with sensor suites, enabling dynamic and adaptive collaborator selection. SV2V-RSim encompasses four maps, four weather conditions, six time periods from sunrise to night, 203K LiDAR frames, 402K RGB frames, and 788K annotated 3D bounding boxes across 17 object classes, supporting a range of cooperative perception tasks such as 3D object detection, segmentation, and depth estimation. Benchmarking on recent cooperative perception algorithms demonstrates that SVA achieves a superior performance-bandwidth trade-off, while sim-to-real experiments and No-Reference Image Quality Assessment validate the dataset's high realism and practical effectiveness. Our dataset and code will be publicly available.
Cooperative perception can improve the situational awareness of connected and autonomous vehicles by exchanging complementary sensing information among nearby agents. However, systematic multi-vehicle cooperation also increases vehicle-to-everything (V2X) communication demand, processing overhead, and operational resou...
M. Alrashidi, Wajih Abdallah· Italian National Conference...· 0 citations
End-to-end autonomous driving in urban environments requires robust decision-making under partial observability and complex multi-agent interactions. Severe occlusions and dense traffic at intersections limit the perception capability of single-agent systems, motivating recent efforts on Vehicle-to-Infrastructure (V2I)...
Hoonhee Cho, Jae-Young Kang, Giwon Lee et al.· 0 citations
Cooperative perception (CP) is a pivotal technology for Autonomous Vehicles (AVs) to overcome the physical limitations of onboard sensors by sharing data via Vehicle-to-Vehicle (V2V) communication. However, the performance of CP is intrinsically coupled with vehicle control, as vehicle speed directly dictates the avail...
Zi-Xuan Kong, Lu-Han Wang, Hang Li et al.· 2026 14th International Conf...· 0 citations
Experiments on a large-scale real-world cooperative driving dataset demonstrate that V2X-WAM consistently improves planning accuracy and safety over representative end-to-end cooperative driving methods, while achieving stronger future-world prediction and substantially lower communication overhead.
Jun-Wei You, Wei-Zhe Tang, Can Wang et al.· arXiv.org· 1 citation
Vehicle-to-Everything (V2X) cooperative perception extends the perception horizon of autonomous vehicles by enabling information exchange between vehicles and roadside infrastructure. Its practical deployment is constrained by communication bandwidth, latency, and perception accuracy, since raw sensor data often exceed...
Олексій Ульянов, R. Shuvar, Vasyl Yaremovych Lyashkevych et al.· International Symposium ELMA...· 0 citations
ConVeX is introduced, an extensive multi-agent synthetic dataset for collaborative perception (CP) that reproduces different realistic driving scenarios (urban, rural, highway), road layouts, and weather and lighting conditions and ground-truth annotations for object detection.
M. Palena, D. Selvaraj, C. Chiasserini et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.