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
- The Rise of the Ironic Boat and Toteon August 3, 2022 at 6:45 am
When you see an L.L.Bean's Boat and Tote in the wild—carried in line at the grocery store, perched on a beach towel—there's a certain expectation for what's embroidered on the side. "Unhinged" in ...
- Problems with Assessing Consciousness in the 21st Centuryon August 2, 2022 at 8:00 am
The meaning of consciousness has been debated since at least the 17 th century, when John Locke described consciousness as “the perception of what passes in a man’s own mind” … The debate surrounding ...
- 5 innovative campaigns that raise awareness regarding Human Traffickingon July 30, 2022 at 8:48 am
Today is the International Day against human trafficking. In India, an average of 1827 women are trafficked every hour.
- VEMI Lab researchers earn federal prize, invite to White House for software that makes self-driving cars more accessibleon July 27, 2022 at 8:01 am
The VEMI lab at the University of Maine earned third place in a national competition and an invitation to the White House for developing an inclusive ...
- Beyond machines: Technology is just a mediumon July 26, 2022 at 1:04 pm
There is phenomenal energy to bring about a massive disruption by young entrepreneurs and emerging leaders, solving problems for farmers with technical ingenuities in a world driven by the ...
- Future Tech: What is Machine Vision?on July 23, 2022 at 1:08 am
Machine learning (ML), artificial intelligence (AI), and robotic process automation (RPA) are all terms we frequently hear when discussing the value of advanced automation. Machine vision, however, is ...
- We Are in the Ex Machina Era | Opinionon July 20, 2022 at 5:09 pm
From a viral post on Medium to a primetime appearance with Fox News' Tucker Carlson, software engineer Blake Lemoine has asserted that an AI called LaMDA is roughly self-aware, like humans and ...
- Should Robots Be Self-aware?on July 18, 2022 at 10:40 pm
Despite the risks of giving machines more autonomy, one researcher asserts that the amount of self-awareness this particular robot has is “trivial compared to humans, and yet we have to beware ...
- Autonomous Robot Creates a Likeness of Itselfon July 14, 2022 at 10:45 am
A robot that can model itself has important benefits, but the technology behind the self-awareness gives rise to concerns, too. A Columbia Engineering team has created a robot that is able to ...
- A robot learns to imagine itselfon July 12, 2022 at 5:00 pm
The researchers are aware of the limits, risks, and controversies surrounding granting machines greater autonomy through self-awareness. Lipson is quick to admit that the kind of self-awareness ...
via Bing News