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
- 4 fundamental relationships between buildings and machines on April 17, 2019 at 9:20 am
Yet, Kurzweil also anticipates that within a century we will concede that machines have legal and civil rights. Will self-aware buildings become as privileged as their inhabitants? How will our ... […]
- Meet the nonprofit that’s already fighting for the rights of sentient robots on April 10, 2019 at 1:12 am
Movies like Blade Runner and other science fiction tend to depict robots as self-aware machines, capable of making their own decisions and able to express personality and emotion. Robots aren’t ... […]
- AI not similar to what’s portrayed in sci-fi, it's here to enhance our lives on April 6, 2019 at 9:46 pm
16 IST Many people think of artificial intelligence as self-aware computers, evil robots, and digital armageddon. But AI technology is often misunderstood, and the many benefits of machine ... […]
- Study suggests it's time to debate the morality of machines on April 5, 2019 at 11:22 pm
Let alone to systems that are designed to kill people?” While self-aware machines may still be the realm of science-fiction for now, defining these issues are what will shape our future. […]
- Artificial intelligence or advanced imitation? on April 4, 2019 at 1:54 am
Science fiction has often portrayed artificial intelligence (AI) as self-aware robots with anthropomorphic qualities ... AI in its current form is the simulation of human intelligence processes by ... […]
- On the way towards self-aware AI? on April 2, 2019 at 7:42 am
Alexa, Sophia, Watson: the ancient idea of a humanoid machine with superhuman powers has received fresh impetus by the progress achieved in AI research. Some actors offer the prospect of a ... […]
- The Best New Pinball Machines on the Floor of the Texas Pinball Festival on March 28, 2019 at 2:00 am
Deadpool is silly, snide and self-aware and the game captures him perfectly; it feels like Stern let the character design his own pinball machine even though we know he doesn't really exist (as far as ... […]
- Rise of the Machines and Descent of Man? Scientists Create Quasi-“Self-aware” Robot on February 4, 2019 at 6:47 am
From The Terminator to D.A.R.Y.L, science-fiction writers have presented memorable, though very different, visions of “self-aware” robots. But now it’s being reported that science itself has taken a ... […]
- A step closer to self-aware machines on January 30, 2019 at 11:07 am
New York, NY--January 30, 2019--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 ... […]
- Robot that can 'imagine itself' and became self-aware is built by scientists on January 30, 2019 at 11:07 am
A robot able to 'imagine' itself has been created in a step towards the self-aware robots envisioned in the Terminator movies. Skynet and other sci-fi machines are able to learn and decipher from ... […]
via Bing News