Embracing Contact: Pushing Multiple Objects with Robot's Forearm
This work addresses manipulation efficiency for robotics, though it appears incremental as it extends existing nonprehensile methods to a new robot body part.
The paper tackles the problem of robot manipulation efficiency by proposing to use the robot's forearm to push multiple objects simultaneously instead of relying solely on end-effector grasping. In a simulated sorting task, this approach combined with pick-and-place operations reduced task completion time by 28% compared to individual object handling.
Grasping is the dominant approach for robot manipulation, but only a single object can be grasped at a time. Nonprehensile manipulation offers richer set of interactions, however state-of-the-art is limited to using the end-effector only. We propose using a robot link (forearm) to push multiple objects at once. In a simulated task where the robot's task is to sort two kinds of objects into their respective goal regions, we show that a greedy strategy that uses a combination of forearm pushes and pick and place operations reduces task completion time by %28 compared to picking and placing each object individually.