如今,越來(lái)越多的公司開始前仆后繼地涌入自動(dòng)駕駛汽車領(lǐng)域,渴望能在這個(gè)生機(jī)勃勃的市場(chǎng)中分一杯羹。Mentor Graphics公司的嵌入式系統(tǒng)部門也不例外,這家公司推出了一款自動(dòng)駕駛模組,可直接利用傳感器的原始數(shù)據(jù),做出駕駛決策。
Mentor公司的這個(gè)最新平臺(tái)能夠捕捉并融合來(lái)自雷達(dá)、激光雷達(dá)、視覺(jué)傳感器等系統(tǒng)的原始數(shù)據(jù)輸入,而后判斷車輛是否需要做出轉(zhuǎn)彎、制動(dòng)等動(dòng)作。在底特律舉行的SAE 2017 全球汽車年會(huì)(WCX17)上,Mentor公司的DRS360模組正式發(fā)布。該模組的主要應(yīng)用場(chǎng)景為SAE Level 5自動(dòng)駕駛汽車,但也可用于支持ADAS。
DRS360模組的硬件組成包括賽靈(Xilinx)的現(xiàn)場(chǎng)可編程門陣列(FPGA),及一些基于X86或ARM架構(gòu)的微控制器。軟件則主要基于公司行業(yè)領(lǐng)先的汽車Linux平臺(tái),需運(yùn)行Linux軟件。
與許多安全系統(tǒng)不同,Mentor的DRS360模組可直接使用傳感器的原始數(shù)據(jù)。一般來(lái)說(shuō),絕大部分公司都會(huì)為傳感器配置微控制器,在數(shù)據(jù)進(jìn)入汽車系統(tǒng)之前對(duì)其進(jìn)行一些基礎(chǔ)的處理,從而降低傳感器對(duì)帶寬需求,并減輕中央處理模組的工作負(fù)擔(dān)。
Mentor公司的工程師認(rèn)為,考慮到像以太網(wǎng)等網(wǎng)絡(luò)可以滿足絕大多數(shù)高分辨率傳感器的帶寬要求,因此直接使用原始數(shù)據(jù)是個(gè)更加高效的選擇。摒棄在傳感器內(nèi)安裝運(yùn)算模組的設(shè)計(jì),可以同時(shí)節(jié)約時(shí)間和成本,對(duì)于滿載各種傳感器的自動(dòng)駕駛汽車來(lái)說(shuō)更是如此。
“在自適應(yīng)巡航控制系統(tǒng)中,車輛雷達(dá)配置了一個(gè)處理器。該處理器會(huì)先對(duì)數(shù)據(jù)進(jìn)行篩選,而后將重要部分傳入車輛系統(tǒng),并供后者判斷車輛是否需要采取剎車等行動(dòng)。”Mentor Graphics公司嵌入式系統(tǒng)部門總經(jīng)理Glenn Perry表示,“在傳感器中增加處理器的設(shè)計(jì)會(huì)帶來(lái)延遲,需要使用的材料種類自然也更多。考慮到SAELevel 5自動(dòng)駕駛汽車所裝載的大量激光雷達(dá)、雷達(dá)及攝像頭,這種作法會(huì)給汽車廠商帶來(lái)沉重的成本壓力,并造成巨大的計(jì)算負(fù)擔(dān),因此可能行不通。”
DRS360模組的功率不到100 W。在最近進(jìn)行的測(cè)試中,我們發(fā)現(xiàn),當(dāng)設(shè)備采用的傳感器越多,這款模組的性能優(yōu)化效果就越明顯。技術(shù)人員在運(yùn)行“行人、自行車、汽車”目標(biāo)分類算法時(shí)使用了一個(gè)單獨(dú)傳感器,而后又增加了更多傳感器輸入。當(dāng)一組傳感器的輸入相互融合后,系統(tǒng)分析數(shù)據(jù)所需的計(jì)算能力降低了。
“當(dāng)采用一個(gè)傳感器時(shí),我們的CPU負(fù)載在85%左右,完成目標(biāo)分類大約需要600ms,置信度為65%。”Perry說(shuō),“當(dāng)我們?cè)黾永走_(dá)和激光雷達(dá)的數(shù)量時(shí),系統(tǒng)的置信水平有所提高,而CPU負(fù)載卻下降至55%,分類時(shí)間僅為1ms。”
Perry指出,“我們很驚訝地看到,當(dāng)CPU需要處理的數(shù)據(jù)更多時(shí),其數(shù)據(jù)傳輸量反而下降了,這是違反常理的。”
事實(shí)上,性能并非各家廠商決定是否購(gòu)買Mentor模組的唯一理由,一級(jí)供應(yīng)商及各廠商集團(tuán)所處的商業(yè)環(huán)境也將發(fā)揮關(guān)鍵作用。
與當(dāng)今流行的分布式處理器架構(gòu)相比,Mentor的模組采用了一款強(qiáng)大的中央處理器。很多自動(dòng)駕駛架構(gòu)也采用了中央控制器,而這均非常依賴預(yù)處理數(shù)據(jù)輸入。Mentor公司ADAS部總監(jiān)AminKashi認(rèn)為,公司的購(gòu)買決定主要是從商業(yè)方面考慮,而非技術(shù)。
“從組織結(jié)構(gòu)和供應(yīng)鏈方面考慮,目前行業(yè)似乎對(duì)‘整合’的概念有所抵觸。”Kashi表示,“也就是說(shuō),市場(chǎng)上有一些信息娛樂(lè)設(shè)備在與車內(nèi)相關(guān)系統(tǒng)的整合時(shí),根本沒(méi)有考慮太多結(jié)構(gòu)的問(wèn)題,特別是一些中國(guó)廠商尤其如此。”
開放性也是DRS360的另一個(gè)商業(yè)加分點(diǎn)。一些供應(yīng)商僅能向客戶提供黑盒解決方案,因此客戶很難改變其中的硬件或軟件。Mentor則允許廠商根據(jù)需要,自行調(diào)整模組的算法和硬件設(shè)計(jì)。
Perry表示,“很多廠商均視ADAS為各家公司拉開差距的地方,但如果他們都只能拿到同一個(gè)黑盒解決方案,就很難真正拉開差距。而我們提供的開放平臺(tái)則允許他們根據(jù)公司需要,進(jìn)行一些定制處理,真正讓他們的產(chǎn)品脫穎而出。”
The race to gain a foothold in the emerging autonomous vehicle market continues to attract more players. Mentor Graphics Embedded Systems Division is joining the game, introducing a system that captures raw sensor data and makes driving decisions.
Mentor’s new platform captures and fuses raw data from radar, lidar, vision and other sensors, then decides whether to turn, brake or take other actions. The DRS360, unveiled at the SAE WCX17 in Detroit, is aimed primarily at SAE Level 5 autonomous vehicles, though it can also be used for advanced driver assistance systems (ADAS).
The hardware includes Xilinx FPGAs Mentor and either X86- or ARM-based microcontrollers. It runs Linux software, building upon the company’s claims of leadership in automotive Linux.
Unlike many safety systems, Mentor is using raw sensor data. Many companies add microcontrollers to sensors, doing elementary processing before data goes onto the network. That reduces bandwidth requirements and lightens the workload for the central processing modules.
Mentor engineers contend that it’s more efficient to stream raw data, since networks like Ethernet can meet even the demands of many high-resolution sensors. Eliminating intelligence within sensors can save both time and money, especially in sensor-laden autonomous vehicles.
“In adaptive cruise control, the radar has a processor that filters out data; the important data is then sent to a system that decides whether it needs to brake,” explained Glenn Perry, General Manager of the Mentor Graphics Embedded Systems Division. “Adding a processor in the sensor induces latency and adds to the bill of materials. When you have all the lidar, radar, cameras needed for Level 5, I’m not sure this works. It will be expensive and consume an extraordinary amount of compute power.”
The Mentor module, which has a power budget of under 100W, actually improved performance in a recent test in which more sensors were added. Technicians used a single sensor when they ran object classification algorithm with a pedestrian, bicycle and vehicle, then added more sensor inputs. When input from complementary sensors was combined, it took less compute power to analyze the data.
“With one sensor, we were at an 85% CPU load with a classification time of about 600 milliseconds and a confidence rating of 65%,” Perry said. “When we added radar and lidar, the confidence level rose, the CPU load went down to 55% and the classification time was one millisecond.
"We were surprised how much the CPU load dropped; it was counterintuitive to stream in more Gbits of data and see a decline,” ne noted.
Performance won’t be the only factor that determines whether companies buy into Mentor’s concept. Business issues driven by Tier 1s as well as OEM groups will play a key role.
Mentor’s architecture utilizes a powerful centralized computer, in contrast to today’s distributed-intelligence architectures. Many autonomous architectures also employ a centralized controller that relies heavily on pre-processed inputs. Amin Kashi, Mentor’s ADAS Director, contends that this is driven by business rationales, not technical efficiency
“There’s been a resistance to consolidation, more due to organizational structures and supply chain issues,” Kashi said. “That said, there’s been some consolidation in infotainment and in-vehicle infotainment systems, especially by the Chinese, who don’t care much about structures.”
Openness is another plus on the business side. Some suppliers offer only a black box, so it’s difficult to alter hardware or software. Mentor will let OEMs tweak algorithms and hardware designs.
“OEMs feel ADAS is an area of differentiation, but if they can only get a black box, it’s difficult to differentiate. With an open platform, they can make alterations to differentiate their offerings,” Perry said.
Author: Terry Costlow
Source: SAE Automotive Engineering Magazine