無(wú)標(biāo)題 1
在全自動(dòng)駕駛汽車(chē)完全替代駕駛員之前，電子科技仍然需要人在異常情況下做出決策。在正常駕駛條件下，自動(dòng)控制技術(shù)可以負(fù)責(zé)駕駛，但在需要做出復(fù)雜決策時(shí)仍需人力的介入。
奧迪最近公布了其自動(dòng)駕駛車(chē)輛項(xiàng)目的技術(shù)細(xì)節(jié)，作為該計(jì)劃的一部分，今年早些時(shí)候，一輛奧迪A7概念車(chē)完成了從舊金山到拉斯維加斯的行駛。這輛車(chē)在大部分路段中都采用自動(dòng)駕駛模式，但駕駛員必須保持警惕，這樣當(dāng)警報(bào)器提醒其重新掌握駕駛時(shí)，可以順利完成交接。
這輛概念車(chē)的車(chē)身中配置了一系列計(jì)算機(jī)，奧迪工程師打算在未來(lái)將它們縮減成一塊主板。該技術(shù)的核心是一系列攝像機(jī)、雷達(dá)和超聲波傳感器，并由一個(gè)名為zFASd的主板負(fù)責(zé)控制這些設(shè)備。該主板可以將各種傳感器的輸入數(shù)據(jù)結(jié)合起來(lái)，綜合構(gòu)建車(chē)輛對(duì)外部世界的感知。
“傳感器收集到的所有原始信號(hào)都會(huì)在一個(gè)傳感器融合箱內(nèi)匯聚，”奧迪架構(gòu)駕駛員輔助系統(tǒng)主管Matthias
Rudolph最近在Nvidia GPU技術(shù)論壇上如是說(shuō)?！巴ㄟ^(guò)這些輸入的數(shù)據(jù)，可以建立一個(gè)虛擬的環(huán)境?！?span lang="EN-US">
zFAS主板的基礎(chǔ)是由四個(gè)半導(dǎo)體元件構(gòu)的。Nvidia k1處理器可收集四個(gè)攝像機(jī)的數(shù)據(jù)，并可“在低速行駛過(guò)程中完成各種任務(wù)，”
Rudolph說(shuō)。Infineon Aurix處理器負(fù)責(zé)其他額外工作，Mobileye的
EyeQ3負(fù)責(zé)視覺(jué)處理，而Altera Cyclone FPGA（現(xiàn)場(chǎng)可編程門(mén)陣列）則負(fù)責(zé)進(jìn)行傳感器融合。
軟件架構(gòu)也是多層的，其中感知傳感器為第一層。在此之上是融合層，該層架構(gòu)可將傳感器數(shù)據(jù)與地圖、路標(biāo)和其從他來(lái)源獲得的信息結(jié)合起來(lái)。Rudolph指出，這種結(jié)合可以同時(shí)提升信息的質(zhì)量和分析的準(zhǔn)確性。
“雷達(dá)并不擅于確定車(chē)輛的寬度，” Rudolph表示?！暗珨z像機(jī)可以做到這一點(diǎn)。我們把二者結(jié)合起來(lái)，就得到關(guān)于車(chē)輛前方情況的信息了。”
有一項(xiàng)要求至關(guān)重要，那就是確保zFAS主板能夠預(yù)測(cè)潛在威脅，并進(jìn)行正確回應(yīng)，且不得出現(xiàn)誤報(bào)。如果車(chē)輛為了躲避并不構(gòu)成危險(xiǎn)的事物而停止或轉(zhuǎn)彎，那么駕駛員很有可能不再使用該系統(tǒng)。
“如果車(chē)輛在空無(wú)一物的地方突然剎車(chē)，會(huì)破壞司機(jī)對(duì)系統(tǒng)的信任，” Rudolph表示。“我們的系統(tǒng)沒(méi)有出現(xiàn)過(guò)誤報(bào)，這已經(jīng)在1萬(wàn)小時(shí)的駕駛測(cè)試中得到了證明，在該測(cè)試中車(chē)輛的平均速度為60kph
(37mph)，且需要經(jīng)過(guò)包括降雪和凍雨在內(nèi)的各種氣候的考驗(yàn)?！?span lang="EN-US">
奧迪將注意力放在移動(dòng)物體上，并根據(jù)車(chē)輛的駕駛路徑和速度分析它們的潛在影響。而所有靜止物體都被視為一個(gè)單一的目標(biāo)。
“我們對(duì)所有的靜止圖像一視同仁，” Rudolph表示?！安还苁且欢聣€是一輛停在路邊的車(chē)，我們都要確保不會(huì)撞上去?！?span lang="EN-US">
對(duì)所有自動(dòng)駕駛系統(tǒng)來(lái)說(shuō)，行人都是最大的挑戰(zhàn)之一。行人比車(chē)輛更難定位和識(shí)別，而且他們行為更加不可預(yù)見(jiàn)。奧迪的系統(tǒng)使用一個(gè)單目攝影機(jī)尋找行人。鑒于某些行人移動(dòng)方式的不規(guī)律性，奧迪決定不讓汽車(chē)因?yàn)樾腥说拇嬖诙Ｏ聛?lái)，除非行人的行為的確會(huì)構(gòu)成切實(shí)的威脅。
“在偵測(cè)行人時(shí)，我們會(huì)計(jì)算接觸時(shí)間，” Rudolph表示。“當(dāng)車(chē)子停下時(shí)，車(chē)和人之間的距離非常短。這就是我們想要做到的。這個(gè)距離幾公分就夠了，我們不想大老遠(yuǎn)地就把車(chē)停下來(lái)。”
盡管領(lǐng)航系統(tǒng)的目標(biāo)是避免碰到行人和其他絕大多數(shù)物體，但奧迪也意識(shí)，到碰撞是無(wú)法百分百預(yù)防的。
“如果一場(chǎng)事故實(shí)在不能避免，那我們就會(huì)引導(dǎo)車(chē)輛使用車(chē)身結(jié)構(gòu)部件來(lái)承受沖撞，以將人員傷害降至最低，”
Rudolph表示。
車(chē)輛的這種行為主要是在駕駛員未能及時(shí)接手駕駛的情況下發(fā)生的。奧迪使用LED報(bào)警系統(tǒng)告訴駕駛員交接的時(shí)間。他們可以通過(guò)急剎車(chē)或急轉(zhuǎn)彎避免碰撞。一臺(tái)車(chē)內(nèi)攝像頭時(shí)刻在觀察駕駛員，好讓系統(tǒng)知道是否需要將LED警報(bào)升級(jí)成聲響警報(bào)。
“在領(lǐng)航駕駛模式下，我們可能會(huì)需要駕駛員重新掌控駕駛，所以我們得知道駕駛員在做什么，”
Rudolph表示。
Audi details piloted driving technology
Before autonomous vehicles make drivers obsolete, electronic technologies will depend on people to make decisions when something unusual happens. During normal driving conditions, autonomous controls could pilot the vehicle, relying on humans when complex decisions are required.
Audi recently provided technical insight into its piloted vehicle project, in which an Audi A7 concept car drove from San Francisco to Las Vegas earlier this year. The vehicle drove itself most of the journey, though drivers had to remain alert to take over when alerts directed them to resume driving.
The concept car has a range of computers in the trunk. Audi engineers plan to reduce them to a single board over time. The mainstays of the piloted vehicle technologies are an array of cameras, radar, and ultrasonic sensors that are controlled by what’s called the zFAS board. It combines sensor inputs to give the car its view of the world.
“All raw signals from the sensors is collected in a sensor fusion box,” Matthias Rudolph, Head of Architecture Driver Assistance Systems at Audi AG said during the recent Nvidia GPU Technology Conference. “From that input, a virtual environment is created.”
Four semiconductors are the basis of the zFAS board. An Nvidia k1 processor collects data from four cameras and “does everything while driving at low speeds,” Rudolph said. An Infineon Aurix processor handles additional chores. Mobileye’s EyeQ3 performs vision processing, while an Altera Cyclone FPGA (field programmable gate array) performs sensor fusion.
The software architecture is layered, with the perception sensor programs forming the first layer. Above that, there’s a fusion layer that blends data from the sensors with information from maps, road graphs, and other sources. Rudolph noted that combining inputs provides better information and increases confidence in the analysis.
“Radar is not good at determining the width of a car,” Rudolph said. “A camera does that well. If we fuse data from each of them we get good information on what’s ahead.”
Ensuring that the zFAS boards detect potential threats and respond to them correctly without false alerts is critical. If vehicles stop or swerve to avoid something that isn’t a true danger, drivers are likely to stop using the system.
“If the car brakes and nothing’s there, it will destroy the confidence of the driver,” Rudolph said. “We have had no false positives; that’s been proven with over 10,000 hours of driving at an average speed of 60 kph (37 mph) in situations including snow and freezing rain.”
Audi looks at moving objects to analyze their potential impact given the vehicle’s driving path and speed. All stationary items are viewed with a single goal.
“We look at static images as the same,” Rudolph said. “It doesn’t matter if it’s a wall or a parked car, we don’t want to hit it.”
Pedestrians are a major challenge for all types of autonomous systems. They’re harder to spot and categorize than vehicles, and they have more degrees of freedom. The system uses a single monocular camera to search for pedestrians. Given the erratic behavior of some walkers, Audi doesn’t stop for pedestrians unless they’re truly in harm’s way.
“When we detect pedestrians, we compute the time to contact,” Rudolph said. “We’re close when the vehicle stops. We want to be close, just a few centimeters away. We do not want to stop far away.”
Though the piloted system aims to avoid pedestrians and most everything else, Audi realizes that collisions can’t always be prevented.
“If we can’t avoid an accident, we steer to use the structure of the car to minimize the chance of injury,” Rudolph said.
Such an action would occur mainly when the human driver didn’t take over in time to avoid a collision. Audi uses an LED alert system to tell drivers when they need to take charge. They can do that by hitting the brakes or making a sharp steering wheel movement. An internal-looking camera watches drivers so the system knows whether the LED alert needs to be augmented with an audible warning.
“In the piloted driving mode, we may need to get the driver back, so we need to know what he’s doing,” Rudolph said.
奧迪打算將領(lǐng)航汽車(chē)中笨重的電子系統(tǒng)縮減成一塊單一主板。