Imagine you want to carry a large, heavy box up a flight of stairs. You could spread your fingers and lift the box with both hands, then hold it on your forearms and balance it against your chest, using your whole body to move the box.

Humans are usually good at whole-body manipulation, but robots struggle with such tasks. For a robot, any place where the crate might touch any point on the wearer's fingers, arms or torso represents a contact event that it must think about. With billions of potential touches, planning for this task quickly becomes intractable.

Researchers at MIT have now found a way to simplify this process, known as contact-rich manipulation planning. They use an AI technique called smoothing, which combines many contact events into a smaller number of decisions. This allows even a simple algorithm to quickly determine an effective manipulation plan for the robot.

Smaller, mobile robots possible in the future

This method is still in its infancy, but it could enable factories to use smaller, mobile robots that can manipulate objects with their whole arms or bodies, rather than large robotic arms that can only grip with their fingertips. This could help reduce energy consumption and lower costs.

In addition, this technique could be useful for robots sent on exploration missions to Mars or other solar system bodies, as they could quickly adapt to the environment using only an on-board computer.