Mobileye高級(jí)駕駛輔助系統(tǒng)（ADAS）
Mobileye is the global leader in the development of vision technology for Advanced Driver Assistance Systems (ADAS) and autonomous driving.
We have over 1,700 employees continuing our two-decade tradition of developing state-of-the-art technologies in support of automotive safety and autonomous driving solutions.
Mobileye是高級(jí)駕駛輔助系統(tǒng)（ADAS）和自動(dòng)駕駛視覺(jué)技術(shù)開(kāi)發(fā)的全球領(lǐng)導(dǎo)者。
擁有1,700多名員工，延續(xù)了兩個(gè)十年的傳統(tǒng)，即開(kāi)發(fā)支持汽車(chē)安全和自動(dòng)駕駛解決方案的最新技術(shù)。
Mobileye是Tier 2汽車(chē)供應(yīng)商，與所有主要的Tier 1供應(yīng)商合作，涵蓋了絕大多數(shù)的汽車(chē)市場(chǎng)（擁有25個(gè)以上OEM的計(jì)劃）。這些OEM選擇Mobileye的原因在于其先進(jìn)的技術(shù)，創(chuàng)新的文化和敏捷性。直接的結(jié)果是，作為對(duì)安全性至關(guān)重要的汽車(chē)產(chǎn)品，進(jìn)行嚴(yán)格驗(yàn)證過(guò)程的一部分，技術(shù)的魯棒性和性能已在數(shù)百萬(wàn)英里的行駛里程中經(jīng)過(guò)了實(shí)戰(zhàn)測(cè)試。
Mobileye is a Tier 2 automotive supplier working with all major Tier 1 suppliers, covering the vast majority of the automotive market (programs with over 25 OEMs). These OEMs choose Mobileye, for its advanced technology, innovation culture, and agility. As a direct result, the robustness and performance of our technology have been battle-tested over millions of driving miles as part of the stringent validation processes of safety-critical automotive products.
From the beginning, Mobileye has developed hardware and software in-house. This has facilitated the strategic advantage of responsive and short development cycles of highly interdependent hardware, software and algorithmic stacks. This interdependence is key to producing high-performance and low power consumption products.
從一開(kāi)始，Mobileye就內(nèi)部開(kāi)發(fā)硬件和軟件。這促進(jìn)了高度相互依賴(lài)的硬件，軟件和算法堆棧的響應(yīng)時(shí)間短，開(kāi)發(fā)周期短的戰(zhàn)略?xún)?yōu)勢(shì) 。這種相互依賴(lài)關(guān)系是生產(chǎn)高性能和低功耗產(chǎn)品的關(guān)鍵。
Mobileye在的系統(tǒng)級(jí)芯片（SoC）- EyeQ ? 家族-提供處理能力，支持基于單個(gè)camera傳感器的ADAS功能全面的套件。第四代和第五代，EyeQ ? 將進(jìn)一步支持半和完全自主駕駛，具有帶寬/吞吐量流和處理的全套環(huán)繞camera，雷達(dá)和激光雷達(dá)。
Mobileye’s system-on-chip (SoC) – the EyeQ? family – provides the processing power to support a comprehensive suite of ADAS functions based on a single camera sensor. In its fourth and fifth generations, EyeQ? will further support semi and fully autonomous driving, having the bandwidth/throughput to stream and process the full set of surround cameras, radars and LiDARs.
ADAS
Advanced Driver Assistance Systems (ADAS) systems range on the spectrum of passive/active.
A passive system alerts the driver of a potentially dangerous situation so that the driver can take action to correct it. For example, Lane Departure Warning (LDW) alerts the driver of unintended/unindicated lane departure; Forward Collision Warning (FCW) indicates that under the current dynamics relative to the vehicle ahead, a collision is imminent. The driver then needs to brake in order to avoid the collision.
高級(jí)駕駛員輔助系統(tǒng)（ADAS）系統(tǒng)的作用范圍是被動(dòng)/主動(dòng)。
被動(dòng)系統(tǒng)會(huì)警告駕駛員潛在的危險(xiǎn)情況，以便駕駛員可以采取措施進(jìn)行糾正。例如，車(chē)道偏離警告（LDW）會(huì)警告駕駛員意外/意外的車(chē)道偏離；前向碰撞警告（FCW）表示在相對(duì)于前方車(chē)輛的當(dāng)前動(dòng)態(tài)情況下，即將發(fā)生碰撞。然后，駕駛員需要?jiǎng)x車(chē)以避免碰撞。
相反，主動(dòng)安全系統(tǒng)會(huì)采取行動(dòng)。自動(dòng)緊急制動(dòng)（AEB）可以識(shí)別即將發(fā)生的碰撞和剎車(chē)，而無(wú)需任何駕駛員干預(yù)。主動(dòng)功能的其它示例，包括自適應(yīng)巡航控制（ACC），車(chē)道保持輔助（LKA），車(chē)道居中（LC）和交通擁堵輔助（TJA）。
In contrast, active safety systems take action. Automatic Emergency Braking (AEB) identifies the imminent collision and brakes without any driver intervention. Other examples of active functions are Adaptive Cruise Control (ACC), Lane Keeping Assist (LKA), Lane Centering (LC), and Traffic Jam Assist (TJA).
ACC automatically adjusts the host vehicle speed from its pre-set value (as in standard cruise control) in case of a slower vehicle in its path. LKA and LC automatically steer the vehicle to stay within the lane boundaries. TJA is a combination of both ACC and LC under traffic jam conditions. It is these automated features which comprise the building blocks of semi/fully autonomous driving.
Mobileye supports a comprehensive suite of ADAS functions – AEB, LDW, FCW, LKA, LC, TJA, Traffic Sign Recognition (TSR), and Intelligent High-beam Control (IHC) – using a single camera mounted on the windshield, processed by a single EyeQ? chip.
如果行駛中的車(chē)輛速度較慢，ACC會(huì)根據(jù)其預(yù)設(shè)值，自動(dòng)調(diào)整本車(chē)速度（如標(biāo)準(zhǔn)巡航控制）。LKA和LC會(huì)自動(dòng)引導(dǎo)車(chē)輛停留在車(chē)道邊界內(nèi)。在交通擁堵情況下，TJA是ACC和LC的組合。 這些自動(dòng)化功能構(gòu)成了半自動(dòng)駕駛/全自動(dòng)駕駛的基礎(chǔ)。
Mobileye支持安裝在擋風(fēng)玻璃上的單個(gè)攝像頭，由ABS，LDW，FCW，LKA，LC，TJA，交通標(biāo)志識(shí)別（TSR）和智能遠(yuǎn)光燈控制（IHC）等全面的ADAS功能套件支持。單EyeQ ? 芯片。
除了通過(guò)與汽車(chē)原始設(shè)備制造商集成來(lái)交付這些ADAS產(chǎn)品之外，Mobileye還提供售后預(yù)警系統(tǒng)，可以將其改裝到任何現(xiàn)有車(chē)輛上。Mobileye售后產(chǎn)品在一個(gè)捆綁包中提供了許多救生警告，從而保護(hù)駕駛員免受分心和疲勞的危險(xiǎn)。
In addition to the delivery of these ADAS products through integration with automotive OEMs, Mobileye offers an aftermarket warning-only system that can be retrofitted onto any existing vehicle. The Mobileye aftermarket product offers numerous life-saving warnings in a single bundle, protecting the driver against the dangers of distraction and fatigue.
Computer Vision
From the outset, Mobileye’s philosophy has been that if a human can drive a car based on vision alone – so can a computer. Meaning, cameras are critical to allow an automated system to reach human-level perception/actuation: there is an abundant amount of information (explicit and implicit) that only camera sensors with full 360 degree coverage can extract, making it the backbone of any automotive sensing suite.
It is this early recognition – nearly two decades ago – of the camera sensor superiority and investment in its development, that led Mobileye to become the global leader in computer vision for automotive.
從一開(kāi)始，Mobileye的哲學(xué)就是， 如果人類(lèi)可以?xún)H憑視覺(jué)駕駛汽車(chē)，那么計(jì)算機(jī)也可以。 這意味著，相機(jī)對(duì)于使自動(dòng)化系統(tǒng)達(dá)到人類(lèi)水平的感知/致動(dòng)至關(guān)重要：只有大量的傳感器信息（顯式和隱式）才可以提取具有完整360度覆蓋范圍的相機(jī)傳感器，從而使其成為任何汽車(chē)的骨干感應(yīng)套件。
正是在將近二十年前的早期認(rèn)可中，攝像機(jī)傳感器的優(yōu)越性和對(duì)其開(kāi)發(fā)的投資使Mobileye成為了汽車(chē)計(jì)算機(jī)視覺(jué)領(lǐng)域的全球領(lǐng)導(dǎo)者。
Mobileye開(kāi)發(fā)camera功能的方法，始終是首先生產(chǎn)經(jīng)過(guò)優(yōu)化并經(jīng)過(guò)驗(yàn)證的，可滿(mǎn)足所有功能需求的最佳，獨(dú)立的僅相機(jī)產(chǎn)品。作為展示，演示車(chē)僅從耶路撒冷自動(dòng)駕駛到特拉維夫，而后僅依靠攝像頭傳感器，而批量生產(chǎn)的自動(dòng)駕駛車(chē)融合了附加的傳感器，以提供基于多種模式（主要是雷達(dá)和LiDAR）的強(qiáng)大，冗余的解決方案。
Mobileye’s approach to the development of camera capabilities has always been to first produce optimal, self-contained camera-only products, demonstrated and validated to serve all functional needs. As a showcase, our demonstration vehicle drives autonomously from Jerusalem to Tel Aviv and back relying on camera sensors alone, while series-production autonomous vehicles fuse-in additional sensors for delivering a robust, redundant solution based on multiple modalities (mainly radar and LiDAR).
From ADAS to Autonomous
The road from ADAS to full autonomy depends on mastering three technological pillars:
? Sensing: robust and comprehensive human-level perception of the vehicle’s environment, and all actionable cues within it.
? Mapping: as a means of path awareness and foresight, providing redundancy to the camera’s real-time path sensing.
? Driving Policy: the decision-making layer which, given the Environmental Model – assesses threats, plans maneuvers, and negotiates the multi-agent game of traffic.
Only the combination of these three pillars will make fully autonomous driving a reality.
從ADAS到完全自主的道路取決于掌握三個(gè)技術(shù)支柱：
? 感應(yīng)：對(duì)車(chē)輛環(huán)境及其內(nèi)部所有可行線(xiàn)索的全面，全面的人類(lèi)感知。
? 映射：作為路徑感知和預(yù)見(jiàn)的一種手段，為camera的實(shí)時(shí)路徑感應(yīng)提供冗余。
? 駕駛策略：決策層根據(jù)環(huán)境模型–評(píng)估威脅，計(jì)劃演習(xí)并協(xié)商交通的多主體博弈。
只有將這三個(gè)支柱結(jié)合起來(lái)，才能實(shí)現(xiàn)完全自動(dòng)駕駛。
The Sensing Challenge
Perception of a comprehensive Environmental Model breaks down into four main challenges:
? Freespace: determining the drivable area and its delimiters
? Driving Paths: the geometry of the routes within the drivable area
? Moving Objects: all road users within the drivable area or path
? Scene Semantics: the vast vocabulary of visual cues (explicit and implicit) such as traffic lights and their color, traffic signs, turn indicators, pedestrian gaze direction, on-road markings, etc.
傳感挑戰(zhàn)
全面環(huán)境模型的認(rèn)知可分為四個(gè)主要挑戰(zhàn)：
? 自由空間：確定可驅(qū)動(dòng)區(qū)域及其定界符
? 行駛路線(xiàn)：可駕駛區(qū)域內(nèi)路線(xiàn)的幾何形狀
? 移動(dòng)物體：可駕駛區(qū)域或路徑內(nèi)的所有道路使用者
? 場(chǎng)景語(yǔ)義：大量的視覺(jué)線(xiàn)索（顯性和隱式），例如交通信號(hào)燈及其顏色，交通標(biāo)志，轉(zhuǎn)向指示器，行人注視方向，道路標(biāo)記等。
The Mapping Challenge
The need for a map to enable fully autonomous driving stems from the fact that functional safety standards require back-up sensors – “redundancy” – for all elements of the chain – from sensing to actuation. Within sensing, this applies to all four elements mentioned above.
While other sensors such as radar and LiDAR may provide redundancy for object detection – the camera is the only real-time sensor for driving path geometry and other static scene semantics (such as traffic signs, on-road markings, etc.). Therefore, for path sensing and foresight purposes, only a highly accurate map can serve as the source of redundancy.
In order for the map to be a reliable source of redundancy, it must be updated with an ultra-high refresh rate to secure its low Time to Reflect Reality (TTRR) qualities.
制圖挑戰(zhàn)
需要地圖以實(shí)現(xiàn)全自動(dòng)駕駛的原因是，功能安全標(biāo)準(zhǔn)要求從感測(cè)到執(zhí)行到后備鏈的所有元素，需要備用傳感器-“冗余”。在感測(cè)中，適用于上述所有四個(gè)元素。
盡管其它傳感器（例如雷達(dá)和LiDAR）可能會(huì)為對(duì)象檢測(cè)提供冗余，但攝像頭是唯一用于行駛路徑幾何形狀和其它靜態(tài)場(chǎng)景語(yǔ)義（例如交通標(biāo)志，道路標(biāo)記等）的實(shí)時(shí)傳感器。出于路徑檢測(cè)和預(yù)見(jiàn)目的，只有高度精確的映射才能用作冗余的來(lái)源。
為了使地圖成為可靠的冗余源，必須使用超高的刷新率對(duì)其進(jìn)行更新，確保其較低的反映現(xiàn)實(shí)時(shí)間（TTRR）質(zhì)量。
為了應(yīng)對(duì)這一挑戰(zhàn)，Mobileye為利用集群的力量鋪平了道路：利用基于攝像頭的ADAS系統(tǒng)的泛濫，以近乎實(shí)時(shí)的方式建立和維護(hù)準(zhǔn)確的環(huán)境圖。
Mobileye的道路體驗(yàn)管理（REM TM）是完全自治的端到端映射和本地化引擎。 解決方案由三層組成：收集代理（任何配備攝像頭的車(chē)輛），地圖聚合服務(wù)器（云）和使用地圖的代理（自動(dòng)車(chē)輛）。
To address this challenge, Mobileye is paving the way for harnessing the power of the crowd: exploiting the proliferation of camera-based ADAS systems to build and maintain in near-real-time an accurate map of the environment.
Mobileye’s Road Experience Management (REMTM) is an end-to-end mapping and localization engine for full autonomy. The solution is comprised of three layers: harvesting agents (any camera-equipped vehicle), map aggregating server (cloud), and map-consuming agents (autonomous vehicle).
The harvesting agents collect and transmit data about the driving path’s geometry and stationary landmarks around it. Mobileye’s real-time geometrical and semantic analysis, implemented in the harvesting agent, allows it to compress the map-relevant information – facilitating very small communication bandwidth (less than 10KB/km on average).
The relevant data is packed into small capsules called Road Segment Data (RSD) and sent to the cloud. The cloud server aggregates and reconciles the continuous stream of RSDs – a process resulting in a highly accurate and low TTRR map, called “Roadbook.”
收取代理收集并傳輸有關(guān)行駛路徑的幾何形狀和周?chē)潭窐?biāo)的數(shù)據(jù)。 在收取代理中實(shí)施的Mobileye實(shí)時(shí)幾何和語(yǔ)義分析使它能夠壓縮與地圖有關(guān)的信息-促進(jìn)非常小的通信帶寬（平均小于10KB / km）。
相關(guān)數(shù)據(jù)被打包到稱(chēng)為路段數(shù)據(jù)（RSD）的小型capsules膠囊中，并發(fā)送到云中。云服務(wù)器聚合并協(xié)調(diào)連續(xù)的RSD流-此過(guò)程產(chǎn)生了高度準(zhǔn)確且低TTRR的地圖，稱(chēng)為“ Roadbook”。
映射鏈中的最后一個(gè)鏈接是本地化：為了使自動(dòng)駕駛汽車(chē)可以使用任何地圖，該車(chē)輛必須能夠在其中定位自己。在地圖使用代理（自動(dòng)駕駛汽車(chē)）中運(yùn)行的Mobileye軟件，通過(guò)實(shí)時(shí)檢測(cè)存儲(chǔ)在其中的所有地標(biāo)，自動(dòng)在“Roadbook道路手冊(cè)”中對(duì)車(chē)輛進(jìn)行定位。
此外， REM TM提供了跨行業(yè)信息共享的技術(shù)和商業(yè)渠道。 REM TM旨在使不同的OEM可以參與此AD關(guān)鍵資產(chǎn)（Roadbook）的建設(shè)，同時(shí)為其RSD貢獻(xiàn)獲得適當(dāng)和成比例的補(bǔ)償。
The last link in the mapping chain is localization: in order for any map to be used by an autonomous vehicle, the vehicle must be able to localize itself within it. Mobileye software running within the map-consuming agent (the autonomous vehicle) automatically localizes the vehicle within the Roadbook by real-time detection of all landmarks stored in it.
Further, REMTM provides the technical and commercial conduit for cross-industry information sharing. REMTM is designed to allow different OEMs to take part in the construction of this AD-critical asset (Roadbook) while receiving adequate and proportionate compensation for their RSD contributions.
Driving Policy
Where sensing detects the present, driving policy plans for the future. Human drivers plan ahead by negotiating with other road users mainly using motion cues – the “desires” of giving-way and taking-way are communicated to other vehicles and pedestrians through steering, braking and acceleration. These “negotiations” take place all the time and are fairly complicated – which is one of the main reasons human drivers take many driving lessons and need an extended period of training until we master the art of driving. Moreover, the “norms” of negotiation vary from region to region as the code of driving in Massachusetts, for example, is quite different from that of California, even though the rules are identical.
駕駛策略
傳感可以檢測(cè)到當(dāng)前情況，并為未來(lái)制定政策計(jì)劃。駕駛員主要通過(guò)使用運(yùn)動(dòng)線(xiàn)索與其它道路使用者進(jìn)行協(xié)商，從而制定了提前調(diào)度，即通過(guò)轉(zhuǎn)向，制動(dòng)和加速，將“讓步”和“讓步”的“愿望”傳達(dá)給其它車(chē)輛和行人。這些“協(xié)商”一直在發(fā)生，而且相當(dāng)復(fù)雜，這是人類(lèi)駕駛員上許多駕駛課程并需要長(zhǎng)期訓(xùn)練，直到掌握駕駛技術(shù)的主要原因之一。此外，協(xié)商的“規(guī)范”因地區(qū)而異，例如，馬薩諸塞州的駕車(chē)守則與加利福尼亞州的駕車(chē)守則大不相同，
使機(jī)器人系統(tǒng)控制汽車(chē)的挑戰(zhàn)在于，在可預(yù)見(jiàn)的未來(lái)，“其它”道路使用者很可能是人為驅(qū)動(dòng)的。為了不妨礙交通，機(jī)器人汽車(chē)應(yīng)表現(xiàn)出與人協(xié)商的技巧，同時(shí)時(shí)間保證功能安全。 換句話(huà)說(shuō)，希望自動(dòng)駕駛汽車(chē)安全駕駛，但要符合該地區(qū)的駕駛規(guī)范。Mobileye認(rèn)為，對(duì)于手工制定的基于規(guī)則的決策而言，駕駛環(huán)境過(guò)于復(fù)雜。取而代之的是，采用機(jī)器學(xué)習(xí)來(lái)通過(guò)暴露于數(shù)據(jù)來(lái)“學(xué)習(xí)”決策過(guò)程。
The challenge behind making a robotic system control a car is that for the foreseeable future the “other” road users are likely to be human-driven, therefore in order not to obstruct traffic, the robotic car should display human negotiation skills but at the same time guarantee functional safety. In other words, we would like the robotic car to drive safely, yet conform to the driving norms of the region. Mobileye believes that the driving environment is too complex for hand-crafted rule-based decision making. Instead we adopt the use of machine learning to “l(fā)earn” the decision making process through exposure to data.
Mobileye’s approach to this challenge is to employ what is called reinforcement learning algorithms trained through deep networks. This requires training the vehicle system through increasingly complex simulations by rewarding good behavior and punishing bad behavior. Our proprietary reinforcement learning algorithms add human-like driving skills to the vehicle system, in addition to the super-human sight and reaction times that our sensing and computing platforms provide. It also allows the system to negotiate with other human-driven vehicles in complex situations. Knowing how to do this well is one of the most critical enablers for safe autonomous driving.
Mobileye應(yīng)對(duì)這一挑戰(zhàn)的方法，采用通過(guò)深度網(wǎng)絡(luò)訓(xùn)練的所謂的強(qiáng)化學(xué)習(xí)算法。需要通過(guò)獎(jiǎng)勵(lì)良好行為和懲罰不良行為，通過(guò)日益復(fù)雜的模擬來(lái)訓(xùn)練車(chē)輛系統(tǒng)。除了感知和計(jì)算平臺(tái)提供的超人視覺(jué)和反應(yīng)時(shí)間外，專(zhuān)有的強(qiáng)化學(xué)習(xí)算法還為車(chē)輛系統(tǒng)增加了類(lèi)似人的駕駛技能。允許系統(tǒng)在復(fù)雜情況下與其它人為駕駛的車(chē)輛進(jìn)行協(xié)商。理解如何做到這一點(diǎn)是安全自動(dòng)駕駛的最關(guān)鍵因素之一。

總結(jié)

以上是生活随笔為你收集整理的Mobileye高级驾驶辅助系统（ADAS）的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。