Precision-Focused Reinforcement Learning Model for Robotic Object Pushing
This work improves robotic assistance in everyday tasks by enhancing precision in non-prehensile manipulation, though it appears incremental as it builds on existing state-of-the-art methods.
The paper tackles the problem of robotic object pushing by addressing challenges from diverse object properties, which often cause overshooting and require corrective movements. It introduces a memory-based vision-proprioception RL model that achieves more precise pushing with fewer corrective movements.
Non-prehensile manipulation, such as pushing objects to a desired target position, is an important skill for robots to assist humans in everyday situations. However, the task is challenging due to the large variety of objects with different and sometimes unknown physical properties, such as shape, size, mass, and friction. This can lead to the object overshooting its target position, requiring fast corrective movements of the robot around the object, especially in cases where objects need to be precisely pushed. In this paper, we improve the state-of-the-art by introducing a new memory-based vision-proprioception RL model to push objects more precisely to target positions using fewer corrective movements.