評論
打印
Similar techniques are used to train self-driving cars to operate in traffic.
自動駕駛汽車在進行上路訓練時也會應用類似技術。
Cars thus learn how to obey lane markings, avoid other vehicles, hit the brakes at a red light and so on.
汽車會學習如何遵守車道標志、避開其他車輛、在紅燈時剎車等。
But they do not understand many things a human driver takes for granted—that other cars on the road have engines and four wheels, or that they obey traffic regulations (usually) and the laws of physics (always).
但他們理解不了許多人類司機認為理所當然的事情，比如為什么路上的汽車有引擎和四個輪子，或者為什么這些車(通常)遵守交通規則、(總是)遵循物理定律。
And they do not understand object permanence.
它們無法理解“物體恒存性”。
In a recent paper in Artificial Intelligence, Mehul Bhatt of Orebro University, in Sweden, who is also the founder of a firm called CoDesign Lab which is developing his ideas commercially, describes a different approach.
近期，瑞典厄勒布魯大學的梅于爾·巴特在《人工智能》雜志上發表了一篇論文，描述了一種獨特的方法。梅于爾·巴特也是一家名為CoDesign Lab的公司的創始人，該公司正著手將他的想法商業化。
He and his colleagues took some existing AI programs which are used by self-driving cars and bolted onto them a piece of software called a symbolic-reasoning engine.
他和他的同事采用了現有的自動駕駛汽車使用的部分人工智能程序，同時將一個叫做“符號推理引擎”的軟件嵌入其中。
Instead of approaching the world probabilistically, as machine learning does, this software was programmed to apply basic physical concepts to the output of the programs that process signals from an autonomous vehicle's sensors.
該軟件不像機器學習那樣以概率的方式認知世界，而是將基本的物理概念應用到處理自動駕駛汽車傳感器信號的程序輸出中。
This modified output was then fed to the software which drives the vehicle.
然后將修改后的輸出輸入驅動車輛的軟件當中。
The concepts involved included the ideas that discrete objects continue to exist over time, that they have spatial relationships with one another— such as "in-front-of" and "behind"—and that they can be fully or partly visible, or completely hidden by another object.
所涉及的概念有：互相獨立的物體會一直存在，它們之間有空間關系，比如“在前面”、“在后面”，它們可以完全可見、部分可見、或者完全被另一個物體擋住。
And it worked. In tests, if one car momentarily blocked the sight of another, the reasoning-enhanced software could keep track of the blocked car, predict where and when it would reappear, and take steps to avoid it if necessary.
它是有用的。在測試中，如果一輛車暫時擋住了另一輛車的視線，該推理增強軟件可以追蹤被擋住的車，預測它將在何時何地再次出現，并在必要時采取措施避開它。
The improvement was not huge. On standard tests Dr Bhatt's system scored about 5% better than existing software.
不過進步并不大。在標準測試中，巴特博士的系統評分比現有的軟件僅高出約5%。
But it proved the principle. And it also yielded something else.
但它證明了原理，還產出了其他東西。
For, unlike a machine-learning algorithm, a reasoning engine can tell you the reason why it did what it did.
因為，推理引擎和機器學習算法不同，它可以告訴你為什么這么做。
譯文由可可原創，僅供學習交流使用，未經許可請勿轉載。
