Learning Strategies for Erecting Horizontal Objects via Half-Grasping to Aid Subsequent Tasks

In robotic assembly environments, the difficulty of subsequent tasks depends on how and where the target object is grasped, such as in peg-in-hole or bolting/screwing scenarios. Therefore, adjusting the pose of the target object is often necessary before achieving the desired configuration. Conventional wisdom dictates a grasping position distant from the center of mass of an object, resulting in the rotational displacement near the grasp point, as a failure. However, in this study, we redefine such scenarios as "half-grasping" and intentionally leverage them to execute the task of erecting horizontally lying objects. In this research, we introduce the concept of uprighting objects using half-grasping. We implemented this approach in the virtual environment using NVIDIA Isaac Sim and trained manipulation strategies through deep reinforcement learning. Using the trained policy, an object erection task was performed in a virtual environment, achieving a success rate of over 98.2% thus confirming the feasibility of the proposal.