Temporally Consistent Object 6D Pose Estimation for Robot Control

Abstract

Single-view RGB object pose estimators have reached a level of precision and efficiency that makes them good candidates for vision-based robot control. However, off-the-shelf methods lack temporal consistency and robustness that are mandatory for a stable feedback control. In this work, we develop a factor graph approach to enforce temporal consistency of the object pose estimates. In particular, the proposed approach: (i) incorporates object motion models, (ii) explicitly estimates the object pose measurement uncertainty, and (iii) integrates the above two components in an online optimization-based estimator. We demonstrate that with appropriate outlier rejection and smoothing using the proposed factor graph approach, we can significantly improve the results on standardized pose estimation benchmarks. We experimentally validate the stability of the proposed approach for a feedback-based robot control task in which the object is tracked by the camera attached to a torque controlled manipulator.

Project page: https://data.ciirc.cvut.cz/public/projects/2024TemporalPose/

References in corpus (7)

• CubeSLAM: Monocular 3D Object SLAM
• Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
• MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
• Depth-Based Object Tracking Using a Robust Gaussian Filter
• SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
• Recent Advances in 3D Object and Hand Pose Estimation
• FoundPose: Unseen Object Pose Estimation with Foundation Features