Consider having to carry a sizable, weighty box up a set of stairs. You may spread your fingers and lift the box with both hands, then support it against your chest by balancing it on top of your forearms while utilizing your entire body to move the box.
Robots typically struggle with whole-body manipulation, a skill that humans typically excel at. The robot must consider every possible point on the carrier’s fingers, arms, and chest where the box could touch as a contact event. Planning for this work quickly becomes impossible due to the enormous number of possible contact events.
With the development of contact-rich manipulation planning, MIT researchers have now discovered a technique to streamline this procedure. They employ the smoothing AI technique, which condenses several contact events into a smaller number of choices, to make it possible for even a straightforward algorithm to quickly determine an efficient manipulation strategy for the robot.
This approach, while still in its infancy, may eventually allow industries to use smaller, mobile robots that can control objects with their complete arms or bodies rather than big robotic arms that can only grasp with their fingers. This might save prices and lower energy use. Additionally, since they could swiftly adjust to their surroundings using only an onboard computer, this method could be helpful for robots sent on exploration missions to Mars or other solar system worlds.
According to H.J. Terry Suh, a graduate student in electrical engineering and computer science (EECS) and co-lead author of a paper on this method, “rather than thinking about this as a black-box system, if we can leverage the structure of these kinds of robotic systems using models, there is an opportunity to accelerate the whole procedure of trying to make these decisions and come up with contact-rich plans.”
EECS graduate student Lujie Yang, roboticist Tao Pang PhD ’23, senior author Russ Tedrake, the Toyota Professor of EECS, Aeronautics and Astronautics, and Mechanical Engineering, and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL), are the other authors on the paper with Suh. This week, the study is published in IEEE Transactions on Robotics.
