無(wú)人駕駛領(lǐng)域又要放大招了。一家名不見(jiàn)經(jīng)傳的初創(chuàng)公司正在研究一種新型的無(wú)人駕駛技術(shù),，據(jù)這家公司稱(chēng),，該技術(shù)能讓汽車(chē)?yán)谩俺ＷR(shí)”，在不可控的環(huán)境中像人類(lèi)一樣駕駛,。

在無(wú)人駕駛領(lǐng)域,，多數(shù)公司的研究重點(diǎn)是如何改進(jìn)傳感器、感知和控制技術(shù),。而iSee公司的CEO趙一彪表示,，他的公司開(kāi)發(fā)的機(jī)器人，將是業(yè)內(nèi)第一個(gè)能夠真正理解路面上發(fā)生了什么的機(jī)器人程序,。

大約一年前,，趙一彪與麻省理工學(xué)院的實(shí)驗(yàn)室伙伴克里斯·貝克和科技創(chuàng)業(yè)人黛比·于（音譯）一同創(chuàng)辦了這家公司。該公司也獲得了麻省理工學(xué)院的風(fēng)投機(jī)構(gòu)The Engine的資助,。

趙一彪上周在接受《財(cái)富》雜志的電話(huà)采訪(fǎng)時(shí)表示：“我們知道,，‘看到’不等于‘理解’。目前,，汽車(chē)已經(jīng)實(shí)現(xiàn)了‘看到’,，但它們并不能真的理解究竟發(fā)生了什么，別人在想什么，以及別人的意圖是什么,?！?/p>

而iSee公司則為汽車(chē)程序提供了一種特殊算法，使汽車(chē)可以在開(kāi)放環(huán)境中與人類(lèi)協(xié)作,。該系統(tǒng)有兩個(gè)主要組成部分：深度學(xué)習(xí)和常識(shí)引擎,。

系統(tǒng)的深度學(xué)習(xí)部分與Waymo和Uber的現(xiàn)有技術(shù)大同小異。所謂深度學(xué)習(xí),，是指如果你對(duì)某件事練習(xí)得足夠多,，你就能下意識(shí)地做到它。對(duì)于人類(lèi)來(lái)說(shuō),，正是快速的下意識(shí)思考,，才使你在駕駛時(shí)能夠同時(shí)完成多個(gè)操作。而對(duì)于無(wú)人駕駛技術(shù),，也正是這種深度學(xué)習(xí),，才使得汽車(chē)能始終保持在自己的車(chē)道里行駛。

然而當(dāng)你遇到特殊路況,，你就需要推理和有意識(shí)的思考了,。比如在高速公路上會(huì)車(chē)、變換車(chē)道或通過(guò)十字路口時(shí),，你都要預(yù)測(cè)其他車(chē)輛的活動(dòng),，有時(shí)甚至要跟其他司機(jī)“談判”，有時(shí)也得考慮其他可能性,，以求安全通過(guò),。

趙一彪表示：“作為一個(gè)人類(lèi)司機(jī)，我們會(huì)有意識(shí)地思考那些可能發(fā)生的情形,，這是因?yàn)槲覀兊念^腦中有一個(gè)‘常識(shí)引擎’,，因此，哪怕遇見(jiàn)一些從未見(jiàn)過(guò)的情形,，我們也同樣有能力去應(yīng)對(duì)它,。”

而無(wú)人駕駛汽車(chē)的常識(shí)引擎,，則同樣可以讓汽車(chē)基于常識(shí)和過(guò)往的經(jīng)驗(yàn)來(lái)應(yīng)對(duì)新情況,。

趙一彪介紹道，這個(gè)獨(dú)有的常識(shí)引擎能幫助汽車(chē)“真正理解現(xiàn)在發(fā)生了什么,，并且預(yù)測(cè)接下來(lái)兩秒鐘里,，他們可能會(huì)做什么?！边@樣一來(lái)，機(jī)器人就能“在需要與環(huán)境中的其他司機(jī)進(jìn)行交流甚至談判時(shí)，做出安全的,、策略性的決策,。”

趙一彪三人在大約一年前建立了這個(gè)算法,，并制作了一個(gè)模擬器,。然后他們想到，為什么不在一臺(tái)真正的汽車(chē)上做實(shí)驗(yàn)?zāi)?？黛比·于大方地借出了自己的一臺(tái)混動(dòng)SUV作為實(shí)驗(yàn)用車(chē),。

回憶起2017年冬天他們?cè)谲?chē)庫(kù)里工作的經(jīng)歷時(shí)，趙一彪笑道：“我們只花了兩周時(shí)間,，就讓那輛車(chē)實(shí)現(xiàn)了自動(dòng)駕駛,。這是一次非常有趣的經(jīng)歷?！?/p>

第一次實(shí)驗(yàn)成功后,，iSee的程序又經(jīng)過(guò)了多次修改完善。這個(gè)團(tuán)隊(duì)不僅利用模擬器進(jìn)行測(cè)試,，也在美國(guó)的多個(gè)州通過(guò)有人駕駛汽車(chē)實(shí)測(cè)了系統(tǒng)在真實(shí)路況中的表現(xiàn),。

這種技術(shù)使機(jī)器人得以流暢地與人類(lèi)協(xié)作。雖然該技術(shù)在無(wú)人駕駛領(lǐng)域之外也有應(yīng)用潛力,，不過(guò)趙一彪表示,，目前iSee將主要專(zhuān)注于無(wú)人駕駛領(lǐng)域。

“我們認(rèn)為,，無(wú)人駕駛是一個(gè)新興市場(chǎng),，所有人都在朝著這個(gè)目標(biāo)努力。而且現(xiàn)在市場(chǎng)已經(jīng)準(zhǔn)備好了,，客戶(hù)也已經(jīng)準(zhǔn)備好了,，缺的只是實(shí)現(xiàn)它的技術(shù)，所以我們的當(dāng)務(wù)之急,，是讓這個(gè)‘殺手級(jí)應(yīng)用’能夠管用,。未來(lái)我們也可以將它擴(kuò)展到其他應(yīng)用上?！?/p>

隨著常識(shí)引擎在技術(shù)上取得成功,，iSee公司也希望它能被廣泛接受——至少不要像行業(yè)領(lǐng)袖Waymo那樣遭到車(chē)主的嫌棄。據(jù)稱(chēng),，自從Waymo在亞利桑那州投入測(cè)試以來(lái),，已因其過(guò)于保守的駕駛風(fēng)格遭到了很多人類(lèi)司機(jī)的不滿(mǎn)。

對(duì)此趙一彪表示：“我認(rèn)為這正是這個(gè)領(lǐng)域的一個(gè)公開(kāi)挑戰(zhàn),。我覺(jué)得對(duì)于常識(shí)理解的核心部分,，現(xiàn)在連Waymo和Uber這些公司也沒(méi)有搞明白,，而我們正是專(zhuān)注于這一塊的，我認(rèn)為它將是讓無(wú)人駕駛系統(tǒng)真正適應(yīng)真實(shí)路況的一項(xiàng)關(guān)鍵技術(shù),?！?/p>

不過(guò)，這個(gè)目標(biāo)什么時(shí)候才能實(shí)現(xiàn)呢,？趙一彪表示：“它已經(jīng)發(fā)生了,，它不是未來(lái)，而是現(xiàn)在,?！保ㄘ?cái)富中文網(wǎng)）

譯者：樸成奎

A little-known name in the world of autonomous driving is paving the way for a new type of self-driving car—one that can use “common sense,” as the company calls it, to navigate an uncontrolled environment.

While most companies developing self-driving cars are focused on improving sensors, perception, and control, iSee CEO Yibiao Zhao says his company is the first to work on creating a robot that can really understand what’s going on.

Zhao founded iSee just about a year ago along with Chris Baker, his lab partner at the Massachusetts Institute of Technology, and Debbie Yu, who has a history with tech startups. The three are supported by MIT’s venture capital firm, The Engine, in Cambridge, Mass.

“We know that seeing is not equivalent to understanding,” Zhao told Fortune in a phone call last week. “Currently cars can see, but they cannot really understand what’s really going on and what other people are thinking, and what are the other people’s intentions.”

With iSee, the cars’ programming has a special algorithm allowing it to collaborate with humans in an open environment. The system has two components: deep learning and the common sense engine.

Deep learning is something other companies like Waymo and Uber have already established; it’s the notion that if you practice something enough, you’ll be able to do it unconsciously. In humans, it’s the fast, subconscious thinking that allows you to multitask while driving. In self-driving cars, it’s the type of learning that lets a car remain within a lane.

When you get to an obstacle, however, you’ll need reasoning, or conscious thinking. When you merge on the highway, change lanes, or come to an intersection, you need to predict the actions of other cars, negotiate with them, and consider different possibilities in order to make a safe decision.

As a human driver, “we’ll consciously think about those types of possible parallel futures,” says Zhao. “That is enabled by our common sense engine in our mind, and that gives us the ability to handle some new scenario that we never encountered before.”

In a self-driving car, the common sense engine allows it to navigate new situations based on a handful of past experiences and general knowledge.

This component, unique to iSee, helps the car to “truly understand what is going on, and to predict what they might do in the next two seconds,” says Zhao. This lets the robot “make safe and strategic decisions when they need to interact or even negotiate with the other drivers in the environment,” he says.

Once Zhao, Baker, and Yu had this algorithm established and passed through a simulator about a year ago, they figured “why not” try it on a real car, says Zhao. Yu generously agreed to let her car, a hybrid SUV, serve as guinea pig.

“We spent just two weeks, and we made the car driving,” says Zhao, laughing as he recalls how cold it was working in the garage in the winter of 2017. “It was a very fun experience.”

Since the success of that first experiment, iSee has gone through multiple variations of programming. The team tests their system with both a simulation engine and manned cars driving in multiple states.

This kind of technology, allowing robots to work fluidly with humans, has potential outside the industry of autonomous cars, but Zhao says iSee is focused on self-driving cars for now.

“We believe the self-driving car is the emerging market. Everyone is working so hard towards it, and the market is ready, the customer is ready,” he says. “What is lacking is this enabling technology, so we want to make this killer application work first. In the future, we can extend it to other applications.”

With the success of the common sense engine, iSee hopes to become widely accepted—without the controversies that have surrounded industry leaders like Waymo, which is reportedly hated by its human neighbors in Arizona due to the cars’ overly-conservative driving.

“I think that’s the open challenge in the field,” says Zhao. “There’s one single piece—that is this core part of the common sense understanding—and I think even Waymo and Uber, those companies, haven’t figured it out yet. We are laser focusing on that and I think that can be the enabling technology to make it really work well in a real-world scenario.”

How soon will that be? “It’s already happening,” says Zhao. “It’s not the future. It’s now.”