Discuz! Board

 找回密碼
 立即註冊
搜索
熱搜: 活動 交友 discuz
查看: 280|回復: 0
打印 上一主題 下一主題

「自動駕驶」訓練集優化之扩充数据量真的可以提高訓練精准度嗎?

[複製鏈接]

1116

主題

1116

帖子

3353

積分

管理員

Rank: 9Rank: 9Rank: 9

積分
3353
跳轉到指定樓層
樓主
發表於 2024-4-24 18:02:37 | 只看該作者 回帖獎勵 |倒序瀏覽 |閱讀模式
Advanced driver-assistance systems (ADAS) are nowadays not only a standard accessory in new cars, but also an important milestone on the road to autonomous dri新店汽車借款,ving.

高档駕驶辅助體系(ADAS)现在不但是新車的標配,也是主動駕驶門路上的一個首要里程碑。

Be it keeping the lane and distance to the vehicle in front or parking in tight spaces: The more the technical assistants are supposed to be able to do independently, the better the neural networks on which the systems are based have to be trained for this. Accordingly, the data sets used continue to grow.

不管是車道连結、與前車的間隔连結,仍是在狭窄空間泊車:辅助體系可以或许自力完成的事情越多,作為體系根本的神經收集就必需遭到更優良的練習。响應地,利用的数据集将延续扩充。

Yet, this raises a question: to what extent do the training data actually reflec能量梳,t the operational domains of the ADAS? This is often of secondary importance and rarely checked. In order to reduce the systems’ susceptibility to errors, only the quantity of data has been kept constantly increasing up to now. This results in unnecessarily complex, lengthy and thus also inefficient development processes.

但是,這激發了一個問题:練習的数据在多大水平上能真正反應ADAS體系在操作域的环境?這個問题凡是不被v臉面膜,人器重,而且也很少有人去查驗。為了削减體系對毛病的敏感度,到今朝為止,采纳的法子是不竭增长数据数目。這致使了不需要的繁杂、冗杂,是以也是低效的開辟進程。

ARRK Engineering has therefore developed an approach to analyze the models with regard to concrete operational domains and relevant scenarios, such as urban traffic or motorways. Data that is inaccurate or distorts reality can be corrected or removed and the ADAS can be trained in a targeted, reliable and at the same time resource-efficient manner.

是以,ARRK Engineering|埃尔科工程 開辟了一種法子来阐發有关详细操作域和相干場景的模子,如都會交通或高速公路。不许确或失真的数据可以被改正或删除,ADAS得以以一種有针對性的、靠得住的、同時也是節省資本的方法举行練習。

近况

Well-known OEMs are leading the way, mobility start-ups are following suit and consumers want it: more and more vehicles are being equipped with level 2 and level 3 driver-assistance systems.

知名汽車主機厂正在引领潮水,草創汽車公司踊跃跟進,消费者也巴望具有:愈来愈多的車辆正在配备L2级和L3级的駕驶辅助體系。

Thus, every day, numerous road users rely on lane keeping assists or autosteer (LKA/LCA), automated parking and adaptive cruise control (ACC). The general safety on the roads – and thus the safety of all ro支票借錢,ad users – therefore depends to a large extent on the proper functioning of these systems. To ensure this, their neuronal networks are trained with the help of huge data sets. The models are intended to represent all possible situations that the vehicle may encounter in everyday traffic and thus serve as a recognition and calculation basis for the autonomous reactions of the ADAS in the field.

是以,天天都有很多門路利用者依靠車道连結辅助@體%96wc9%系或主%4E2R6%動@轉向體系(LKA/LCA)、主動停車和自顺應巡航節制(ACC)。門路上的整體平安和所有門路利用者的平安在很大水平上取决于這些體系的正常運作。為此,他們的神經元收集必要借助大量数据集举行練習。這些練習模子旨在代表車辆在平常交通中可能碰到的所有环境,從而作為ADAS在现場做出自立反响的辨認與计较的根本。

Huge data sets: the vicious cycle of the mass

巨大的数据集:大范围的恶性轮回

The more complex the functionalities of different ADAS, the more specific data sets are required for their training. In order to cover all possible traffic situations, the data sets have been expanded more and more in recent years, focusing primarily on mass, i.e. the sheer number of recording hours or of annotated objects in different weather and lighting conditions.

分歧的ADAS的功效越繁杂,其練習所需的数据集就越详细。為了涵盖所有可能的交通环境,比年来,数据集被愈来愈多地扩充,重要集中在数目上,比方在分歧的气候和照明前提下,记實的小時数或注释工具的数目。

However, this inevitably increases the proportion of data that is inaccurate or simply unsuitable for a particular operational domain. To ensure that the newly developed ADAS continue to function reliably, their quality deficit has in turn been compensated for with quantity – a vicious cycle. This has already led to very long development times with many iteration loops, in which the training of the neural networks alone takes several weeks.

但是,這不成防止地增长了不许确或底子不合适特定操作域的数据比例。為了确保新開辟的ADAS延续靠得住地運行,以数目袒護質量缺點——這是一個恶性轮回。這致使了很是长的開辟時候和很多迭代轮回,此中仅神經收集的練習就必要几周時候。

技能解决方案

To escape this dile妹妹a, the automotive industry needs to shift the focus away from quantity and towards quality of data sets. Therefore, the machine learning specialists at ARRK Engineering have developed an approach to validate the processes with regard to an operational domain and to correct them if necessary. In this way, development can be made more efficient and, more importantly, the functional safety of the ADAS can be increased – an essential prerequisite for its future further development into higher levels of autonomous driving.

為了解脱這類窘境,汽車行業必要将重點從数据集的数目轉移到質量上。是以,ARRK Engineering|埃尔科工程 的呆板進修專家已開辟出一種法子,以驗證與操作范畴有关的流程,并在需要時對其举行批改。經由過程這類方法,可以提高開辟效力,更首要的是,可以提高ADAS的功效性平安,這是将来進一步成长為更高程度的主動駕驶的需要条件。

The above content was created by Václav Diviš, Senior Expert Machine Learning at ARRK Engineering, and presented at the SafetyAI 2023 conference. In the next issue, we'll continue to share the case studies from the report and provide a way to download the full report, so stay tuned!

以上内容由ARRK Engineering|埃尔科工程 的呆板進修高档專家Václav Diviš創作并在AAAI人工智能大會 SafetyAI 2023分论坛宣读,下期咱們将继续分享该陈述中的案例鑽研,并供给完备陈述的下载方法,敬辟穀茯苓糕,请等待!

Senior Expert Machine Learning  :Václav Diviš

如您也對

ADAS范畴感樂趣

接待存眷VX:ARRK 德國埃尔科

领會更多具體信息

ARRK Engineering GmbH 原名 P+Z Engineering GmbH,建立于1967年,总部位于德國慕尼黑,在英國、罗马尼亚、日本、中國和马来西亚均設有分公司或辦公室,是汽車及航空航天等行業内浩繁國際一线品牌的持久互助火伴,為客户供给高真個工程開辟咨询辦事與独家自研產物。

ARRK China|埃尔科中國 是德國 ARRK Engineering GmbH 在中國設立的全資子公司,志為中國汽車范畴供给世界一流的工程技能辦事。
回復

使用道具 舉報

您需要登錄後才可以回帖 登錄 | 立即註冊

本版積分規則

Archiver|手機版|小黑屋|新北市學車交流論壇  

跨境電商, 加盟創業, 國際旅遊鞋工廠, 廢棄物處理公司, 品牌設計,

GMT+8, 2024-12-18 09:51 , Processed in 0.080530 second(s), 6 queries , File On.

Powered by Discuz! X3.3

© 2001-2017 Comsenz Inc.

快速回復 返回頂部 返回列表