Multi-View Keypoints for Reliable 6D Object Pose Estimation
This addresses the problem of reliable object pose estimation in challenging robotics applications like bin-picking, representing a strong specific gain rather than a broad breakthrough.
The paper tackles 6D object pose estimation for low-feature and reflective objects in bin-picking by proposing a multi-view approach that combines heatmap and keypoint estimates into a 3D probability density map, achieving an average error of 0.5mm and 2 degrees and surpassing state-of-the-art detection rates.
6D Object pose estimation is a fundamental component in robotics enabling efficient interaction with the environment. It is particularly challenging in bin-picking applications, where many objects are low-feature and reflective, and self-occlusion between objects of the same type is common. We propose a novel multi-view approach leveraging known camera transformations from an eye-in-hand setup to combine heatmap and keypoint estimates into a probability density map over 3D space. The result is a robust approach that is scalable in the number of views. It relies on a confidence score composed of keypoint probabilities and point-cloud alignment error, which allows reliable rejection of false positives. We demonstrate an average pose estimation error of approximately 0.5mm and 2 degrees across a variety of difficult low-feature and reflective objects in the ROBI dataset, while also surpassing the state-of-art correct detection rate, measured using the 10% object diameter threshold on ADD error.