AI-powered robot mimics ANY action after watching a person do it just once, paving the way for machines to learn new skills in the same way as humans
- Scientists have developed a clawed machine that can learn several tasks
- It masters new skills by watching a video of a human performing the action once
- This allows the android to master new skills faster than other robots
- It could lead to machines that learn complex tasks purely through observation
A new breed of AI-powered robots could soon mimic almost any action after watching a human do them just once.
Scientists have developed a clawed machine that can learn new tasks, such as dropping a ball into a bowl or picking up a cup, simply by viewing a person perform them first.
Researchers said the trick allows the android to master new skills much faster than other robots, and could one day lead to machines capable of learning complex tasks purely through observation – much like humans and animals do.
Scroll down for video
A new breed of AI-powered robots could soon mimic almost any action after watching a human do them just once. This animation shows a person completing a simple task (left) that is then copied by a new robot developed by scientists in California (right)
Project lead scientist scientist Tianhe Yu wrote in a blog post: ‘Learning a new skill by observing another individual, the ability to imitate, is a key part of intelligence in human and animals.
‘Such a capability would make it dramatically easier for us to communicate new goals to robots – we could simply show robots what we want them to do.’
Developed by engineers at the University of California at Berkeley, the robot quickly learns new actions by watching a person do it on video.
- Thousands of Spotify customers demand REFUNDS after they are… Galaxy believed to be devoid of dark matter could FINALLY… Nasa confirms launch date for its 430,000mph Parker Solar… WhatsApp says it is ‘horrified’ over deadly India lynchings…
Share this article
Clips of the android show it picking up fruit and putting it into a bowl, as well as carefully moving around an obstacle following the same path demonstrated by a scientist.
Most machines, such as the robots in car factories, are programmed to complete tasks via computer code – a rigid and often time-consuming process.
More recently, androids have been developed that can learn by watching another robot complete the action, though they typically need to mimic the task thousands of times before perfecting it.
Scientists have developed a clawed machine that can learn several tasks – such as dropping a ball into a bowl or moving a plastic plant pot – by first viewing a person perform it
In the new paper, the UC team outline the technique which allowed them to teach a robot actions with just one demonstration – vastly speeding up the learning process.
They combined two different learning algorithms into a single super-AI.
One of these – a meta-learning algorithm – helps a robot to learn by incorporating the movements used in prior tasks rather than master each skill from scratch.
The other, an imitation algorithm, allows the machine to pick up a new skill by watching something else perform it.
The robot can learn to manipulate an object it has never seen before by watching a single video – a breakthrough that could accelerate machine learning. Pictured is the android learning to place a pot into a bowl
Experts combined two algorithms into a single super-AI. One of these – a meta-learning algorithm (left) – helps a robot to learn by incorporating the movements used in prior tasks. The other (right) allows the machine to pick up a new skill by imitation
Combining the two allowed scientists to build an AI that draws on both prior experience as well as mimicry to build new skills in a process the researchers call model-agnostic meta-learning (Maml).
This means it can learn to manipulate an object it has never seen before by watching a single video – a breakthrough that could accelerate machine learning.
Researchers wrote: ‘Our method enables a PR2 robot to effectively learn to push many different objects that are unseen during meta-training toward target positions.’
The robot can also ‘pick up many objects and place them onto target containers by watching a human manipulates each object’, they said.
HOW DOES ARTIFICIAL INTELLIGENCE LEARN?
AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn.
ANNs can be trained to recognise patterns in information – including speech, text data, or visual images – and are the basis for a large number of the developments in AI over recent years.
Conventional AI uses input to ‘teach’ an algorithm about a particular subject by feeding it massive amounts of information.
AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn. ANNs can be trained to recognise patterns in information – including speech, text data, or visual images
Practical applications include Google’s language translation services, Facebook’s facial recognition software and Snapchat’s image altering live filters.
The process of inputting this data can be extremely time consuming, and is limited to one type of knowledge.
A new breed of ANNs called Adversarial Neural Networks pits the wits of two AI bots against each other, which allows them to learn from each other.
This approach is designed to speed up the process of learning, as well as refining the output created by AI systems.
In future, the team said they plan to expand the range of tasks that the robot can learn from humans.
The eventual goal is to develop machines that can ‘quickly develop strategies for new situations’, they said.
The study was posted to the pre-publish journal Arxiv and has not yet undergone peer review.
Source: Read Full Article