A team at Columbia Engineering has developed a robot that, for the first time, can learn a model of its whole body from scratch without any human help. Their robot built a kinematic model of itself in a recent paper published in Science Robotics and utilized that model to plan movements, accomplish objectives, and avoid obstacles in a range of scenarios. Even damage to its body was automatically detected and corrected.
“We were really curious to see how the robot imagined itself,” said Hod Lipson, professor of mechanical engineering and director of Columbia’s Creative Machines Lab, where the work was done. “But you can’t just peek into a neural network, it’s a black box.” After the researchers struggled with various visualization techniques, the self-image gradually emerged. “It was a sort of gently flickering cloud that appeared to engulf the robot’s three-dimensional body,” said Lipson. “As the robot moved, the flickering cloud gently followed it.” The robot’s self-model was accurate to about 1% of its workspace.
The ability of robots to model themselves without being guided by engineers is massively significant for many reasons: It saves labor and enables the robot to keep up with its own wear-and-tear, and even detect and compensate for damage. This ability is highly valuable as autonomous systems are required to be more self-reliant.
“We humans clearly have a notion of self,” explained the study’s first author Boyuan Chen, who led the work and is now an assistant professor at Duke University. “Close your eyes and try to imagine how your own body would move if you were to take some action, such as stretch your arms forward or take a step backward. Somewhere inside our brain, we have a notion of self, a self-model that informs us what volume of our immediate surroundings we occupy, and how that volume changes as we move.”
“Self-modeling is a primitive form of self-awareness,” Lipson explained. “If a robot, animal, or human, has an accurate self-model, it can function better in the world, it can make better decisions, and it has an evolutionary advantage.”
The researchers are aware of the limits, risks, and controversies about making machines more autonomous through self-awareness. Lipson is quick to admit that the kind of self-awareness demonstrated in this study is, as he noted, “trivial compared to that of humans, but you have to start somewhere. We have to go slowly and carefully, so we can reap the benefits while minimizing the risks.”
