In the ever-evolving world of robotics, researchers are constantly seeking innovative ways to enhance the capabilities of these machines. One that has captured the attention of scientists is the potential of using legs instead of arms for certain tasks. Four-legged robots normally need an arm attached to their body to open doors or pick up objects, but this can add additional weight and make it harder for the robot to squeeze through narrow spaces.
Philip Smith in Switzerland and his colleagues used a machine-learning model to teach a ready-made robotic dog to use one of its legs to perform tasks while standing still or moving with the other three legs. The robot dog can use a leg to open doors, press buttons and pick up backpacks while balancing on its other three legs.
"We cannot do everything with the legs that we could do with an arm — right now, a hand is far more skillful. But the point is really to make this work for applications where we maybe have mass limits, or we don't want to have that additional complexity, like for space exploration where every kilogram of such a robot counts," says Smith.
To train the robot dog, Smith and his team gave the machine-learning model the objective of finding a specific point in space with one of the robot's legs. The model then worked out by itself how to control the remaining three legs and balance the robot while standing or walking. Smith and his team could then control the robot remotely to carry out movements like picking up a backpack and putting it in a box, or collecting rocks. While the robot can currently only do these tasks while operated by a person, Smith hopes that future improvements will allow the dog to autonomously handle objects with its leg.