人工智能培训

搜索

深度学习论文:将车辆间通信,车辆定位和数字地图集成到协同自适应巡航控制与目标检测损失(Integrating Inter-vehicular Communica

[复制链接]
wynrefer 发表于 2019-1-11 11:30:58 | 显示全部楼层 |阅读模式
wynrefer 2019-1-11 11:30:58 119 0 显示全部楼层
深度学习论文:将车辆间通信,车辆定位和数字地图集成到协同自适应巡航控制与目标检测损失(Integrating Inter-vehicular Communication, Vehicle Localization, and a  Digital Map for Cooperative Adaptive Cruise Control with Target Detection  Loss)自适应巡航控制系统(ACC)是一种先进的驾驶辅助系统(ADAS),可使车辆跟随所需的车辆间距离。协同自适应巡航控制(CACC)升级ACC,利用附加的车辆间无线通信来共享车辆状态,如加速到实现更短的差距跟随。 ACC和CACC都依赖于诸如雷达之类的范围传感器来获得用于保持控制的实际车辆间距离。由于有限的视角,范围传感器可能在弯曲的道路或陡峭的山坡上失去对目标,前方车辆的检测。不利的天气条件,目标选择失败或硬件问题也可能导致目标检测损失。在目标检测损失期间,车辆跟随系统通常回落到巡航控制(CC),其中跟随车辆保持恒定速度。在这项工作中,我们提出了在目标检测损失期间获得车辆间距离的替代方法,以继续跟踪车辆。所提出的算法集成了车辆间通信,精确的车辆定位以及具有车道中心信息的数字地图以近似车辆间距离。实验室中的机器人跟踪实验证明所提出的算法提供了期望的车辆间距离近似。虽然该算法旨在用于车辆跟随应用,但它也可以用于需要车辆的相对距离近似的其他场景。该工作还展示了我们的实验室内开发工作,即机械仿真连接和自动车辆的交通。
Adaptive Cruise Control (ACC) is an Advanced Driver Assistance System (ADAS)that enables vehicle following with desired inter-vehicular distances.Cooperative Adaptive Cruise Control (CACC) is upgraded ACC that utilizesadditional inter-vehicular wireless communication to share vehicle states suchas acceleration toenable shorter gap following.Both ACC and CACC rely onrange sensors such as radar to obtain the actual inter-vehicular distance forgap-keeping control.The range sensor may lose detection of the target, thepreceding vehicle, on curvy roads or steep hills due to limited angle of view.Unfavourable weather conditions, target selection failure, or hardware issuemay also result in target detection loss.During target detection loss, thevehicle following system usually falls back to Cruise Control (CC) wherein thefollower vehicle maintains a constant speed.In this work, we propose analternative way to obtain the inter-vehicular distance during target detectionloss to continue vehicle following.The proposed algorithm integratesinter-vehicular communication, accurate vehicle localization, and a digital mapwith lane center information to approximate the inter-vehicular distance.In-lab robot following experiments demonstrated that the proposed algorithmprovided desirable inter-vehicular distance approximation.Although thealgorithm is intended for vehicle following application, it can also be usedfor other scenarios that demand vehicles' relative distance approximation.Thework also showcases our in-lab development effort of robotic emulation oftraffic for connected and automated vehicles.深度学习论文:将车辆间通信,车辆定位和数字地图集成到协同自适应巡航控制与目标检测损失(Integrating Inter-vehicular Communication, Vehicle Localization, and a  Digital Map for Cooperative Adaptive Cruise Control with Target Detection  Loss) RzAzANmv9Da9Yn6n.jpg
URL地址:https://arxiv.org/abs/1901.02989     ----pdf下载地址:https://arxiv.org/pdf/1901.02989    ----深度学习论文:将车辆间通信,车辆定位和数字地图集成到协同自适应巡航控制与目标检测损失(Integrating Inter-vehicular Communication, Vehicle Localization, and a  Digital Map for Cooperative Adaptive Cruise Control with Target Detection  Loss)
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则 返回列表 发新帖

wynrefer当前离线
新手上路

查看:119 | 回复:0

快速回复 返回顶部 返回列表