stories on progressThis self-learning AI software lets robots do tasks autonomously.
June 1, 2021
image | above
Pictured is the BRETT robot used in lab experiments at the Univ. of California. This robot responds to smart AI software that enables the robot to complete physical tasks by trial + error.
It’s called autonomous learning — meaning BRETT can approach a new environment, with objects he’s never seen, and figure-out by himself how to touch, move, assemble, stack, open, close, and operate all kinds of things he detects in the space. Even if he’s never encountered them before. The AI software program gives him the ability to learn without being pre-programmed on each task ahead of time.
— contents —
~ story
~ quotes
~ featurette
~ reading
story |
Univ. of California researchers have developed new computer AI software that enables robots to learn physical skills — called motor tasks — by trial + error. The robot uses a step-by-step process similar to the way humans learn.
The lab made a demo of their technique — called re-inforcement learning. In the test: the robot completes a variety of physical tasks — without any pre-programmed details about its surroundings.
Some of the robot’s successful test tasks:
- putting a clothes hanger on a pole
- stacking wood donuts on a pole
- assembling a toy airplane
- screwing the cap on a water bottle
- inserting a shaped peg into its matching hole
Robots learn motor tasks autonomously with AI.
The research is part of the People + Robots Initiative — at the Univ. of California’s Center for Information Technology Research in the Interest of Society — CITRIS. The center develops info-tech solutions for world-wide benefit. They advance AI, robotics, and automation.
1. |
quote | by Pieter Abbeel PhD
What we’re showing in this project is a new approach to enable a robot to learn. The key is that when a robot is faced with something new, we won’t have to re-program it. The same AI software enables the robot to learn all the different tasks we gave it.
name: Pieter Abbeel PhD
about: A robotics engineer, teacher, and a lead researcher on the project.
the Kurzweil Library
:: card catalog | visit
::
view | full profile
bio: robotics engineer
bio: teacher
field:
at | the Univ. of California
web: profile
2. |
quote | by Trevor Darrell PhD
Most robotic applications happen in controlled environments — where physical objects are in predictable positions in the surroundings. The challenge of putting robots into real-life settings — like homes, offices, or transported to new or unknown facilities — is that those environments are constantly changing. The robot must be able to sense + adapt to its surroundings.
name: Trevor Darrell PhD
about:bio: robotics engineer
bio: teacher | the Univ. of California
web: profile
image | left
Pictured is the BRETT robot. He’s programmed with AI software to use tools + complete motor tasks. He lives in an experimental lab at the Univ. of California.
You can see the robot’s gripper hand pulling a wood nail out of a wood beam with the back-end of a hammer.
He does this by himself — carefully adjusting the arc, angle, direction, pressure, motion, and force he applies to the hammer. Just like a human would.
He finally accomplishes his task across many trial + error attempts. So he’s also learning the same way humans do.
The research team, located at the university’s famous Berkeley campus, nick-named the robot BRETT for:
B | Berkeley
R | Robot for the
E | Elimination of
T | Tedious
T | Tasks
Better than old approaches.
Previous techniques to help a robot make its way through a 3D environment required:
- pre-programming it to handle the vast range of possible scenario
- creating simulated environments that the robot operates inside
Instead, the researchers used the computer software technique called deep-learning AI — enabling the robot to make sense of all the data it receives, from all its sensors.
AI deep-learning software programs create layers of pattern recognition — that handle raw sensory data coming from the robot’s 3D environment. From sound, echo, touch, pressure, temperature, motion, position, and camera vision. With AI the robot can track patterns in the ongoing info-stream it’s getting — from its many sensors.
DOTLINE
3. |
quote | by Sergey Levine PhD
Humans are not born with a repertoire of behaviors that can be deployed like a Swiss army knife. And we don’t need to be pre-programmed to do activities. People learn new skills over time — from experience + by watching other humans.
This learning process is so deeply rooted in our biology, that we can’t even communicate to somebody precisely how to do any physical task. We can only give guidance as they learn it on their own.
name: Sergey Levine PhD
about
bio: robotics engineer
bio: teacher | the Univ. of California
web: profile
— featurette —
An AI feedback loop powers the software.
For the experiments, the team used the Personal Robot 2 — called PR2 — product from Clearpath Robotics. And nick-named it the Berkeley Robot for the Elimination of Tedious Tasks — BRETT.
They presented BRETT with a series of motor tasks — examples: placing blocks into matching openings, and stacking Lego blocks. The software program controlling BRETT’s learning supplies a score, based-on how well the robot is doing its task.
- BRETT takes-in its ‘scene’ with its cameras
- that means its surroundings
- it includes the position of its own arms + hands
- the program supplies a real-time score as feedback
- the score is based-on the robot’s movements
- movements that help the robot achieve the task score higher
- movements that don’t help the robot with the task score lower
- then the score goes back to the program
- so the robot can learn which movements are best for the task
This training process lets the robot learn on its own. As BRETT moves its joints + manipulates physical objects — the AI software program calculates good values for 92,000 factors in its environment that it needs to assess.
A jump in self-learning robotics advances.
When BRETT is given the coordinates for the beginning + end of a task, the robot can master most tasks in 10 minutes. When the robot is not given the location for the objects in the scene — and needs to learn vision + control together — the learning process takes 3 hours.
— quote —
The field of robotics will see big improvements — as our ability to process huge amounts of data improves. With more data, you can start learning more complex things. It’s a long way before robots can learn to clean a house, do the dishes, and sort laundry.
But our promising results show these kinds of AI software programs can enable robots to learn complex tasks by themselves, without being pre-programmed. In 5 — 10 years we’ll see major advances in robot learning capability.
— Pieter Abbeel PhD
name: Pieter Abbeel PhD
bio: robotics engineer
bio: teacher | the Univ. of California
web: profile
watching
1. |
school: the Univ. of California
featurette title: BRETT the robot learns to put things together on his own
watch | featurette
— summary —
Univ. of California at Berkeley researchers developed software that enables robots to learn motor tasks through trial + error. This is similar to the way humans learn — marking a major milestone in the computer software field of artificial intelligence. In their experiments, the robot used AI deep-learning — a software programming technique — to complete tasks without pre-programmed details about its surroundings.
presented by
school: the Univ. of California
web: home ~ channel
motto: Let there be light.
program: People + Robots
web: home ~ background ~ channel
tag line: —
2. |
broadcast: Bloomberg
featurette title: See smart robots learn to play like human children
watch | featurette
— summary —
BRETT is a robot that can think. Researchers at the Univ. of California at Berkeley have programmed BRETT to learn on its own — through trial + error — how to accomplish tasks. Such as screwing a cap on a bottle, putting Lego blocks together, and solving a simple puzzle. It’s all made possible by a type of AI computer program called deep-learning that’s revolutionizing robotics.
presented by
broadcast: Bloomberg
web: home ~ channel
tag line: All the most important market news. All in one place.
webpages
Clearpath Robotics | home ~ channel
tag line: Boldly go where no robot has gone before.
— about —
We build the world’s best robot development platforms. Developing autonomous robots has never been easier. Our goal is to automate the planet’s dullest, dirtiest, and deadliest jobs. We’re the leader in research robotics — blazing the trail for robots in industry.
— notes —
UC = the University of California
univ. = university
AI = artificial intelligence
IT = information technology
info-tech = information technology
CITRIS = Center for Information Technology Research in the Interest of Society
BRETT = Berkeley Robot for the Elimination of Tedious Tasks