A Step Closer to Self-Aware Machines
Robots that are self-aware have been science fiction fodder for decades, and now we may finally be getting closer. Humans are unique in being able to imagine themselves—to picture themselves in future scenarios, such as walking along the beach on a warm sunny day. Humans can also learn by revisiting past experiences and reflecting on what went right or wrong. While humans and animals acquire and adapt their self-image over their lifetime, most robots still learn using human-provided simulators and models, or by laborious, time-consuming trial and error. Robots have not learned to simulate themselves the way humans do.
Columbia Engineering researchers have made a major advance in robotics by creating a robot that learns what it is, from scratch, with zero prior knowledge of physics, geometry, or motor dynamics. Initially the robot does not know if it is a spider, a snake, an arm—it has no clue what its shape is. After a brief period of “babbling,” and within about a day of intensive computing, their robot creates a self-simulation. The robot can then use that self-simulator internally to contemplate and adapt to different situations, handling new tasks as well as detecting and repairing damage in its own body. The work is published today in Science Robotics.
Video of Columbia Engineering robot that learns what it is, with zero prior knowledge of physics, geometry, or motor dynamics. Initially the robot has no clue what its shape is. After a brief period of “babbling,” and within about a day of intensive computing, the robot creates a self-simulation, which it can then use to contemplate and adapt to different situations, handling new tasks as well as detecting and repairing damage in its body.
To date, robots have operated by having a human explicitly model the robot. “But if we want robots to become independent, to adapt quickly to scenarios unforeseen by their creators, then it’s essential that they learn to simulate themselves,” says Hod Lipson, professor of mechanical engineering, and director of the Creative Machines lab, where the research was done.
For the study, Lipson and his PhD student Robert Kwiatkowski used a four-degree-of-freedom articulated robotic arm. Initially, the robot moved randomly and collected approximately one thousand trajectories, each comprising one hundred points. The robot then used deep learning, a modern machine learning technique, to create a self-model. The first self-models were quite inaccurate, and the robot did not know what it was, or how its joints were connected. But after less than 35 hours of training, the self-model became consistent with the physical robot to within about four centimeters. The self-model performed a pick-and-place task in a closed loop system that enabled the robot to recalibrate its original position between each step along the trajectory based entirely on the internal self-model. With the closed loop control, the robot was able to grasp objects at specific locations on the ground and deposit them into a receptacle with 100 percent success.
Even in an open-loop system, which involves performing a task based entirely on the internal self-model, without any external feedback, the robot was able to complete the pick-and-place task with a 44 percent success rate. “That’s like trying to pick up a glass of water with your eyes closed, a process difficult even for humans,” observed the study’s lead author Kwiatkowski, a PhD student in the computer science department who works in Lipson’s lab.
The self-modeling robot was also used for other tasks, such as writing text using a marker. To test whether the self-model could detect damage to itself, the researchers 3D-printed a deformed part to simulate damage and the robot was able to detect the change and re-train its self-model. The new self-model enabled the robot to resume its pick-and-place tasks with little loss of performance.
Lipson, who is also a member of the Data Science Institute, notes that self-imaging is key to enabling robots to move away from the confinements of so-called “narrow-AI” towards more general abilities. “This is perhaps what a newborn child does in its crib, as it learns what it is,” he says. “We conjecture that this advantage may have also been the evolutionary origin of self-awareness in humans. While our robot’s ability to imagine itself is still crude compared to humans, we believe that this ability is on the path to machine self-awareness.”
Lipson believes that robotics and AI may offer a fresh window into the age-old puzzle of consciousness. “Philosophers, psychologists, and cognitive scientists have been pondering the nature self-awareness for millennia, but have made relatively little progress,” he observes. “We still cloak our lack of understanding with subjective terms like ‘canvas of reality,’ but robots now force us to translate these vague notions into concrete algorithms and mechanisms.”
Lipson and Kwiatkowski are aware of the ethical implications. “Self-awareness will lead to more resilient and adaptive systems, but also implies some loss of control,” they warn. “It’s a powerful technology, but it should be handled with care.”
The researchers are now exploring whether robots can model not just their own bodies, but also their own minds, i.e. whether robots can think about thinking.
Learn more: A Step Closer to Self-Aware Machines
The Latest on: Self-aware machines
via Google News
The Latest on: Self-aware machines
- Vibration-Mitigating Algorithm Increases Speed of 3D Printingon May 10, 2021 at 5:00 pm
The average 3D printer is a hardworking machine. While the print head zips along the X ... We want a printer that is so smart and self-aware that it will self-optimize its behavior to get high quality ...
- ‘The Mitchells vs. the Machines’ May Already Be the Best Animated Movie of the Yearon May 5, 2021 at 6:30 pm
This Netflix acquisition about a dysfunctional suburban family battling the robot apocalypse is loud, funny, hyperactive, silly, deadpan — and surprisingly great ...
- The many applications of artificial intelligenceon May 5, 2021 at 5:00 pm
The study of AI believes that machines can be made self-aware with human-like AI, in which the computer program thinks and reasons at the level of a human being. On the other hand, there is also ...
- Machine Learning and Mandalas: Inside Suchi Reddy’s Latest Artworkon May 5, 2021 at 9:00 am
For the Smithsonian’s 175th anniversary exhibition, the architect and artist is assembling a 20-foot-high interactive sculpture—take an exclusive first look.
- Lantern Pharma Inc. (LTRN) CEO Panna Sharma on Q1 2021 Results - Earnings Call Transcripton May 3, 2021 at 10:49 pm
The collaboration focuses on leveraging the RADR AI platform, our machine learning methodology ... building that into pipelines that are more self-aware. There has been some non-significant.
- The Mitchells vs the Machines review: A funny and self-aware adventure in the mould of Into the Spider-Verseon April 29, 2021 at 8:24 pm
But The Mitchells vs the Machines, a family adventure from the producers of Spider-Man: Into the Spider-Verse, is far too sharp, funny, and self-aware to just wag its finger at audiences. Rick’s own ...
- The Mitchells vs The Machines review: The robot apocalypse has never been so funon April 28, 2021 at 5:03 am
It’s not long before The Mitchells face off with machines themselves – their ruler is revealed to be pal, a self-aware AI voiced by Olivia Colman. One of the most interesting things about The ...
- Collective Intelligence Is About To Disrupt Your Strategy: Are You Ready?on April 27, 2021 at 4:59 pm
The quest for Artificial General Intelligence (AGI) is making machines smarter by the day. Some wonder how this will shift the power equation within a supermind. Will self-aware machines displace ...
- Netflix’s The Mitchells vs. The Machines is a beautiful, witty delight that’s a godsend for locked-down familieson April 21, 2021 at 10:35 pm
The Machines is designed to entertain on a two-track system: Goofy and colourful and ridiculous and sweet enough for the under-12 set to enjoy, but also smart and witty and self-aware and ...
via Bing News