Because of their strength and speed, robotic arms are often permanently attached to floors or other structures for stability, limiting their reach. The objective of the research, carried out at the EPFL Algorithms and Learning Systems Laboratory (LASA), was to develop a bimodal robotic hand with expanded grasping capabilities, including occasional independence from the robotic arm to which it is attached.
Robot hands are typically designed with one goal in mind: holding things. To develop one that could do that and crawl on its own like the Addams Family Thing, the researchers generated and refined a basic design using a genetic algorithm (which relies on biological tricks like natural selection and evolution) and the MuJoCo Physics Simulator to test the practicality of the iterations.
The algorithm and simulations helped the researchers determine the optimal position and number of articulated fingers needed, which turned out to be five, in an arrangement similar to that of human hands. The robotic hand also uses a magnetic connector on the wrist, allowing it to attach and detach from an arm autonomously.
The fingers of the hand can bend in both directions, allowing you to use some of them to lift objects while the rest function as little legs. This design also expands the usefulness of the hand while attached to a robotic arm. You can lift multiple objects at once without rotating your arm to reposition unused fingers.
The hand is also considerably smaller than robots like Boston Dynamics' Spot, which can move freely using four legs. Spot has already been upgraded with his own robotic arm and gripper, but with an articulated hand that operates independently, he could be better equipped to explore or analyze areas that Spot can't get into.
