深圳：新一代人工智能系统正在开发中，旨在帮助机器人适应此前未曾遇到的情况。
SHENZHEN: A new generation of artificial intelligence systems is being developed to help robots adapt to situations they have not encountered before.
这项被称为“世界模型”的技术，旨在赋予机器对周围环境的理解能力，使其能够预判环境可能发生的变化，并决定如何应对。当今大多数机器人都是经过训练，在熟悉的环境中执行预设任务。
Known as “world models”, the technology aims to give machines an understanding of their surroundings, allowing them to anticipate how conditions could change and decide how to respond. Most robots today are trained to perform predefined tasks in familiar settings.
但现实世界瞬息万变，要为机器编程应对每一种可能的场景极其困难。
But the real world is constantly changing, making it difficult to programme a machine for every possible scenario.
基于人类行为训练机器人 ACE Robotics（智元机器人/具身智能公司，此处保留原名或译为“ACE机器人”）是越来越多开发该技术的中国企业之一。
TRAINING ROBOTS ON HUMAN BEHAVIOUR ACE Robotics is among a growing number of Chinese firms developing the technology.
其董事长王晓刚表示：“传统模型只能完成特定的预设简单任务。但如果你给机器人一个新任务，它就不知道如何完成。”
“Traditional models can only accomplish certain predefined and simple tasks. But if you give the robot a new task, it doesn't know how to accomplish it,” said its chairman Wang Xiaogang.
“有了世界模型，因为它能理解我们的世界是如何演变的，所以它能完成一些新任务。”世界模型不仅仅是学习在特定情况下采取哪种行动，而是旨在建立对环境的理解，预测环境可能如何变化，并利用这些信息决定下一步做什么。
“With the world model, because it can understand how our world has evolved, it can accomplish some new tasks.”Rather than simply learning which action to take in a given situation, world models aim to build an understanding of the environment, predicting how it could change and using that information to decide what to do next.
王晓刚表示，随着人工智能从数字世界走向在物理环境中运行的机器，这种能力将变得至关重要。
Wang said such capabilities would be important as AI moves beyond the digital world and into machines operating in physical environments.
他说：“大语言模型回答我们的问题、编写代码、编写智能体代码。所有这些都发生在数字世界。”
“Large language models answer our questions, do programming and code the agents. All that happened in the digital world,” he said.
“现在我们希望它走进我们的物理世界，帮助我们操作工具、提高生产力。”ACE Robotics最近在上海世界人工智能大会上发布了其“开物”世界模型的更新版本，目标应用领域包括酒店和零售业。但要让机器理解物理世界，需要海量数据。
“Now we are hoping that it comes to our physical world to help us operate tools and improve our productivity.”ACE Robotics recently launched an updated version of its Kairos world model at the World AI Conference in Shanghai, targeting applications including hospitality and retail. But teaching machines to understand the physical world requires vast amounts of data.
虽然大语言模型可以利用海量文本进行训练，但世界模型需要关于物理运动以及人与物体如何互动的数据。
While large language models can be trained on huge quantities of text, world models need data on physical movement and how people and objects interact.
王估计，最终可能需要大约 1000 万小时的数据量——这大约是他所在公司目前拥有数据量的 100 倍。为了收集更多数据，该公司正与各类企业、商店和工厂合作，记录人们日常执行的任务过程。参与者可以佩戴传感器，同时摄像头会记录他们的动作（例如手和手指的位置）。这些信息随后可以用来训练机器人如何完成类似的任务。
Wang estimated that about 10 million hours of data could eventually be needed – around 100 times the amount his company currently has. To gather more data, the company is partnering with businesses, shops and factories to record people carrying out everyday tasks. Participants can wear sensors while cameras record movements such as the positions of their hands and fingers. That information can then be used to teach robots how to perform similar tasks.
例如，在零售环境中，公司可以记录人们如何拿起商品并将其放入购物篮中，并从中提取有关人体动作和手部动作的信息。即使出现错误（比如人们在执行任务时掉落物品），这些错误数据也能成为有用的训练素材——系统不仅能从中学习到正确的操作方法，还能了解“失败”是什么样的。
In a retail setting, for example, the firm can record a person picking up products and placing them in a basket, then extract information about the person's body and hand movements. Mistakes can also provide useful training data. If a person drops an object while performing a task, the system can learn not only how the task should be completed, but also what failure looks like, Wang said.
然而，对于某些应用来说，机器需要学习的情况往往在现实生活中最难以遇到。这一点对于智能驾驶系统尤为关键，因为这些系统必须能够应对不可预测的道路使用者和突发障碍。中国科技巨头华为在其 Qiankun ADS 5 智能驾驶系统中采用了类似的方法：该系统将真实世界的驾驶数据与虚拟的“交通模拟环境”相结合，通过生成各种不同的交通场景来训练系统。
TRAINING FOR THE UNEXPECTED For some applications, however, the situations that machines need to learn from most may be the hardest to encounter in real life. That is particularly relevant for intelligent-driving systems, which must respond to unpredictable road users and unexpected obstacles. Chinese tech giant Huawei is applying a similar approach to its Qiankun ADS 5 intelligent-driving system. It combines real-world driving data with a virtual “world engine”, where different traffic scenarios can be generated to train the system. Data collected across different cities exposes the system to variations in road conditions and driving behaviour.
华为的技术被应用于 25 个以上的汽车品牌，因此该公司能够获取越来越多的驾驶数据。此外，模拟实验还能帮助开发者创建那些在现实中极难出现的复杂或异常场景，从而为系统提供更全面的训练数据。无论训练数据来自人类行为、车辆运行数据还是模拟结果，最终的目标都是打造出能够适应复杂、不可预测现实环境的 AI 系统。
More than 25 car brands use Huawei's intelligent-driving technology, giving it access to a growing pool of driving data. Simulations also allow developers to generate more difficult or unusual scenarios that may occur too rarely in the real world to provide enough training data. Whether the training data comes from humans, vehicles or simulations, the goal is to build AI systems that can adapt to an unpredictable physical world.