岛国奇葩货 机场行李输送带惊见“大鲔鱼” 这男子5年来天天喝自己的尿 治好了气喘 还减肥 留着胡须哺乳 美一变性人成功生子 灵魂又装错了身体 这位女纸变身成肌肉男模 不敢带“女友”回家 只因她是“男人” 贪食鲨鱼 吃了一口河豚 结果变成“最后的晚餐” 汪星人都汗颜 这只猫竟长达1.2米 还在生长中 印一村庄现“独眼羊”大大的眼睛 村民前来膜拜 这男子狂热“美人鱼”装扮 尽管被嘲笑 但还是坚持 “丑”与“美” 一个妹纸 两张脸 街头借钱大PK 你中枪了吗 岛国女最讨厌的男性穿著 艺术家利用梵高后人的基因 复制出梵高的耳朵 一罐结婚请柬 独特的婚礼邀请 利用Google Books 打造1906年老爷车 圆形国际象棋 玩三国战 蚂蚁玩“单手倒立” 原始的“电子书” 枪支弹药 搭建宗教建筑模型 最大的冰淇淋蛋糕 新的世界纪录 伟哥安全套 不仅仅是安全 世界上最长的手工雪茄 75年的等待 臭花终于开了 自行车运输精子 青蛙想跟金鱼OOXX 世界上最小的弩 战斗着 黄鼠狼“飞骑”啄木鸟 啄木鸟筷子 环保很重要 62年历史 世界上最小的书 长宽3.5毫米 仅可容纳40本书 世界上最小的图书馆 早产女婴判定为“死亡” 火化前几秒突然“呼吸” 是财神搞错了吗 这对夫妇3次中彩票大奖 印度店家推出“火烧槟榔” 好奇游客排队吞火球 水泡字体 可见的每个角度 超罕见的现象 新生宝宝被“完整羊膜囊”包裹 小浣熊头被卡下水道格栅 楚楚可怜 差点被饿死 身长达1米 体重3公斤 “非洲巨蛙”惊掉你的下巴 美摄影师意外拍摄到 一组非常感人的“熊抱抱” 一张酒店手册插画 又被200万网友“看污”了 奇趣发现 祝大家圣诞快乐! 它很美丽 你懂的 内衣要抗议 钉子的表情 树木编码 这是一本神马书? 完全透明的泡泡帐篷 水气球破裂瞬间 手蹼 大木夹子一个 墨西哥湾惊现“死鱼之海” 玩玩 侧身自行车 有形的钥匙环
Amazon hires Disney SVP Kyle Laughlin as director of Alexa Gadgets
Apple’s battery cases return for the iPhone XS and XR
The Future Of TV Is HTML
This Week On Bullish: Can The Bold Italic Come Back?
Microsoft Drops New Windows 10 Mobile Build, Promises Faster Release Cadence
Cisco Pops 2.5% After Reporting Better-Than-Expected FQ4 Revenue Of $12.84B
Yahoo Sags 4% After Alibaba's Q2 Earnings Disappointment
Microsoft Postpones Ship Date For Its 'Surface Hub' Wall Computer To January
You Can Now Run Windows 10 On Your Mac
Microsoft Drops Another Windows 10 Update
Zulily's Buyout Spike Leaves It Less Valuable Than When It Went Public
Microsoft Launches New Windows 10 Build, Vows To Keep Its Early Access Program Alive


漂流瓶终于彻底拜拜 微信7.0.4新版体验
微信漂流瓶被玩坏了 聊聊漂流瓶里那些事
微信关闭漂流瓶 它曾经满足了我们对世界的好奇
微信暂停漂流瓶功能:对色情内容零容忍
[视频]惠普Chromebook x360 14 G1评测:搭载Chrome OS的商务变形本
特斯拉:北京客户可三年免息融资购车并免费租赁车牌
借贷宝:停止催收百名裸条女大学生 未满23岁将不得借贷
京东白条多地频现盗刷 消费者遭催收公司“逼债”
借款野蛮催收行为将被规范 真是几家欢喜几家愁
为规范网贷催收 上海互金协会发行业倡议书
腾讯解释为什么微信没有夜间模式 真相你相信吗?
一张发行8年的微信唱片:只收录了4首歌曲


BMW and Mobileye to crowdsource real-time data for self-driving from 2018

当前位置: 艾金森 > 门户 > 海外资讯

点击量 26
编辑: 1   作者: Techcrunch   时间: 2018/11/14 8:30:15  

BMW and Mobileye are working together, with the automaker employing Mobileye's Road Experience Management (REM) software in its vehicles from 2018 onward. The tech, which Mobileye also recently announced would be coming to future Volkswagen cars, helps crowdsource real-time road data captures by the advanced driver assist hardware on vehicles, which will eventually help provide a key ingredient for fully autonomous driving.

The REM system developed by Mobileye can provide information like road hazards, traffic delays, weather information and even parking availability from individual vehicles, which it will pool in the cloud, and then make available to enter fleets, giving them a way to supplement pre-existing static HD maps with to-the-minute info from real-world driving. That kind of data will likely be crucial to autonomous vehicle systems, especially early on, as it's very challenging to build learning systems that can deal with all aspects of shifting road conditions on the fly.

Mobileye's goal is to source data from a range of different vehicle manufacturers, in order to more quickly and accurately build anonymized real-time mapping data that can serve to inform autonomous driving systems more generally, which should in theory lead to safer roads. The partnership with BMW will collect data that it then passes on to HERE, which will use the real-time info to provide instant updates to its HD Live Map, a cloud mapping service the company is making available for semi-autonomous and fully autonomous vehicles.

Basically, the more automakers Mobileye has on REM, the more useful and appealing to other automakers it becomes. Ultimately shared components between the disparate self-driving systems of various car manufacturers should help serve the overall efficacy and safety of the whole, since a system that can learn from larger and more comprehensive data sets is almost certainly bound to be better than one that has only a single piece of the puzzle.

BMW is already working with HERE, as long with Intel and Mobileye on delivering highly automated vehicles to the road for a target 2021 timeframe, so this should help pave the way for that, with ample data connected in advance from the next few years' worth of shipping vehicles.