How AI ‘world models’ are helping robots learn to adapt in the real world
The technology aims to give machines an understanding of their surroundings, allowing them to anticipate how conditions could change and decide how to respond.
ACE Robotics is among a growing number of Chinese tech firms developing world models. (Image: ACE Robotics)
New: You can now listen to articles.
This audio is generated by an AI tool.
Read a summary of this article on FAST.
Get bite-sized news via a new
cards interface. Give it a try.
Click here to return to FAST
Tap here to return to FAST
FAST
SHENZHEN: A new generation of artificial intelligence systems is being developed to help robots adapt to situations they have not encountered before.
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.
But the real world is constantly changing, making it difficult to programme a machine for every possible scenario.
TRAINING ROBOTS ON HUMAN BEHAVIOUR
ACE Robotics is among a growing number of Chinese firms developing the technology.
“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.
“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.
Wang said such capabilities would be important as AI moves beyond the digital world and into machines operating in physical environments.
“Large language models answer our questions, do programming and code the agents. All that happened in the digital world,” he said.
“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.
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.
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.
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.
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.
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.
Source: CNA/ca(oc)
Sign up for our newsletters
Get the CNA app
Stay updated with notifications for breaking news and our best stories
Get WhatsApp alerts
Join our channel for the top reads for the day on your preferred chat app
Get bite-sized news via a new
cards interface. Give it a try.
Click here to return to FAST
Tap here to return to FAST
FAST
