vehicle-to-everything
PulseAugur coverage of vehicle-to-everything — every cluster mentioning vehicle-to-everything across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
Hyper-V2X 框架估计驾驶感知不确定性
研究人员开发了 Hyper-V2X，一个利用超网络估计自动驾驶合作语义分割中认知和偶然不确定性的新框架。该方法将贝叶斯超网络与 V2X 通信融合的多智能体特征相结合，以生成随机鸟瞰分割的权重分布。该方法与架构无关，并在 OPV2V 基准上进行了演示，以极低的计算开销提供了准确的不确定性估计，从而提高了整体感知可靠性。
-
新的V2V协议增强了密集空域中的无人机协调
研究人员开发了一种新的无人机系统（UAS）通信协议，以改善密集、低空空域中的战术协调和隔离。这种意图优先的车辆对车辆（V2V）系统将状态和意图信息与事件触发消息相结合，用于合作感知和应急规划。使用C-V2X模块进行的评估表明，该协议减少了信念分歧并增强了可观测性，尽管在高度密集或受损条件下的有效性会降低。
-
Camera-primed AI system VIBE improves mmWave beam management for vehicles
Researchers have developed a new system called VIsion-based BEamforming (VIBE) to improve real-time beam management for millimeter-wave (mmWave) vehicular connectivity. VIBE combines machine learning, model-based reason…
-
AFFormer enhances V2X cooperative perception with adaptive feature fusion
Researchers have developed AFFormer, a novel Transformer-based framework designed to improve the robustness of cooperative perception systems for autonomous vehicles under impaired communication conditions. This system …
-
Researchers develop noise-aware training for robust 3D object detection using V2X data
Researchers have developed a new method for integrating vehicle-to-everything (V2X) communication data into 3D object detection systems for autonomous driving. This approach aims to overcome the limitations of onboard s…
-
AI enhances transport security as IoT data traffic explosion looms
A new research paper explores the use of machine learning models for intrusion detection in intelligent transport systems. The study proposes a federated hybrid intrusion detection framework that utilizes random forests…