2023-08-28 09:45:29
It is easy for humans to use other parts of the body to help our fingers to grasp something. And we do it very often. For example, if we want to carry a large, heavy box up a flight of stairs, we extend our fingers, lift the box with both hands, then hold it on our forearms, and then rest it slightly against our chest.
However, for a robot such an operation is extremely difficult. For the robot, each point where the box can touch any point on its body’s fingers, arms, and torso represents a contact event that it must reason about. With billions of potential contact events, planning for this task quickly becomes unfeasible.
Now a team consisting of, among others, Tao Pang and HJ Terry Suh of the Massachusetts Institute of Technology (MIT) in the United States, has found a way to simplify this process.
These researchers have used an artificial intelligence-based technique to allow even a simple algorithm to quickly identify an effective manipulation plan for the robot when it wants to use more parts of its body to hold onto something.
Although it is still in the development phase, this method is already shaping up to be a breakthrough capable of marking a before and after in robotics. For example, it could allow factories to use smaller mobile robots that can manipulate objects with their entire arms or even their entire bodies, instead of having to rely on huge robotic arms that can only grasp objects with their fingertips. Such a change would help reduce energy consumption and costs.
MIT researchers have developed an artificial intelligence-based technique that enables a robot to devise complex ways to manipulate an object using more parts of its body than just its fingers or pincers. In the photo, a robot tries to rotate a cube 180 degrees. (Image: the research team. CC BY-NC-ND 3.0)
The new method of making extra use of a robot’s body could also be useful for robots sent on exploration missions to Mars or other stars, since they could adapt much better to the environment than robots with more classical control of their bodies. (Source: NCYT from Amazings)
#Artificial #intelligence #robots #manipulate #objects #parts #bodies