6D Robotic Assembly Based on RGB-only Object Pose Estimation
This addresses the problem of precise robotic assembly for industrial or manufacturing applications, offering an off-the-shelf RGB-only solution, though it appears incremental in its approach.
The paper tackles the challenge of vision-based robotic assembly requiring high precision by proposing an integrated 6D robotic system that uses RGB-only object pose estimation to assemble blocks with tight tolerances, demonstrating effectiveness through quantitative and qualitative results.
Vision-based robotic assembly is a crucial yet challenging task as the interaction with multiple objects requires high levels of precision. In this paper, we propose an integrated 6D robotic system to perceive, grasp, manipulate and assemble blocks with tight tolerances. Aiming to provide an off-the-shelf RGB-only solution, our system is built upon a monocular 6D object pose estimation network trained solely with synthetic images leveraging physically-based rendering. Subsequently, pose-guided 6D transformation along with collision-free assembly is proposed to construct any designed structure with arbitrary initial poses. Our novel 3-axis calibration operation further enhances the precision and robustness by disentangling 6D pose estimation and robotic assembly. Both quantitative and qualitative results demonstrate the effectiveness of our proposed 6D robotic assembly system.