Engineers build a robot that learns to understand itself, rather than the world around it
Jul 2022, phys.org
A Columbia Engineering team announced today they have created a robot that—for the first time—is able to learn a model of its entire body from scratch, without any human assistance. In a new study published by Science Robotics, the researchers demonstrate how their robot created a kinematic model of itself, and then used its self-model to plan motion, reach goals, and avoid obstacles in a variety of situations. It even automatically recognized and then compensated for damage to its body.The researchers placed a robotic arm inside a circle of five streaming video cameras. The robot watched itself through the cameras as it undulated freely.After about three hours, the robot stopped. Its internal deep neural network had finished learning the relationship between the robot's motor actions and the volume it occupied in its environment.
Yeah I'm creeped out.
via Columbia University School of Engineering and Applied Science: Boyuan Chen, Fully body visual self-modeling of robot morphologies, Science Robotics (2022). DOI: 10.1126/scirobotics.abn1944.
Image credit: AI Art - The Panopticon
DayDreamer: An algorithm to quickly teach robots new behaviors in the real world
Jul 2022, phys.org
Their approach, introduced in a paper pre-published on arXiv, is based on learning models of the world that allow robots to predict the outcomes of their movements and actions.The algorithm builds a world model based on its past "experiences" to teach robots new behaviors based on "imagined" interactions, reducing the need for extensive trial and error training in the real-world."We saw the robots adapt to changes in lighting conditions, such as shadows moving with the sun over the course of a day,"
via University of California, Berkeley: Philipp Wu et al, DayDreamer: world models for physical robot learning. arXiv:2206.14176v1 [cs.RO], arxiv.org/abs/2206.14176
Post Script:
"A promising direction would be to train the robots to explore their surroundings in the absence of a task through artificial curiosity, and then later adapt to solve tasks specified by users even faster," Hafner added.
Further Readings:
Ted Chiang's Digients (in Lifecycle of Software Objects)
