A machine-learning model worked out how to keep this robot stable on three legs while it uses one leg to open doors
Philip Arm, Mayank Mittal, Hendrik Kolvenbach, and Marco Hutter/Robotic Systems Lab
A robot dog can use a leg to open doors, press buttons and pick up rucksacks while balancing on its other three legs.
Four-legged robots like Spot, the star of Boston Dynamics’ viral videos, normally need an arm attached to their body to open doors or pick up objects, but this can add significant weight and make it harder for the robot to squeeze through narrow spaces.
Philip Arm at ETH Zurich in Switzerland and his colleagues used a machine-learning model to teach an off-the-shelf robotic dog to use one of its legs to perform tasks while standing still or moving with the other three legs.
“We cannot do everything with the legs that we could do with an arm – right now, a hand is way more dexterous. But the point is really to make this work for applications where you maybe have mass constraints, or we don’t want to have that additional complexity, like for space exploration where every kilogram of such a robot counts,” says Arm.
To train the dog – an ANYmal robot made by ANYbotics – Arm 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.
Arm 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, Arm hopes that future improvements will allow the dog to autonomously manipulate objects with its leg.
Topics:
