Robots that reconfigure
Image courtesy of the researchers
Image courtesy of the researchers
Image courtesy of the researchers
Image courtesy of the researchers
Like octopi squeezing through a tiny sea cave, metatruss robots can adapt to demanding environments by changing their shape. These robots are made of trusses composed of hundreds of beams and joints that rotate and twist, enabling astonishing volumetric transformations.
But as tasks become more complicated, so does the robot’s design. Adding actuating beams to the robot’s truss may help it perform more motions or tasks, but it also exponentially increases control complexity. And while designers can manually group actuators into control networks for greater simplicity, this process is both tedious and labor intensive.
Now, Berkeley-led researchers have developed an AI-driven framework to optimize and automate the design of complex truss robots, with an approach that enables designers to create robots with extraordinary capabilities while maximizing control efficiency.
“You can automatically design a robot able to meet all of your objectives — such as morphing into certain shapes, moving as fast as possible and grabbing a ball,” said Lining Yao, assistant professor of mechanical engineering.
The team, including researchers from Carnegie Mellon University and the Georgia Institute of Technology, developed several prototypes — including a quadruped robot, a shape-shifting helmet, a lobster-inspired walking robot and a tentacle-like actuator — and then tested their performance. Their findings not only showed that the AI-generated robots could achieve complex shape adaptations with minimal control units, but also identified the optimal number of control networks before performance gains begin to diminish.
Learn more: Mighty morphing robots; Optimization and control of actuator networks in variable geometry truss systems using genetic algorithms (Nature Communications)