A principle of minimum translation search approach for object pose refinement
| Autor: | Rasoul Mojtahedzadeh, Achim J. Lilienthal |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Solid modeling
Translation (geometry) minimum translation search Containers Set (abstract data type) Search algorithm geometrically consistent objects configuration Search problems inaccurate noisy poses Computer vision cluttered environments Pose Pose estimation object pose refinement Mathematics Computer Sciences business.industry detected poses minimum translation search approach Uncertainty depth-limited search Shape Information and Computer Science object pose estimation approaches PROMTS Object (computer science) Rigid body robot vision interpenetration-free configuration Datavetenskap (datalogi) A-star search pose estimation accuracy Three-dimensional displays Artificial intelligence business Algorithm rigid body assumption shipping containers overlapping objects |
| Zdroj: | IROS |
| DOI: | 10.1109/iros.2015.7353776 |
| Popis: | The state-of-the-art object pose estimation approaches represent the set of detected poses together with corresponding uncertainty. The inaccurate noisy poses may result in a configuration of overlapping objects especially in cluttered environments. Under a rigid body assumption the inter-penetrations between pairs of objects are geometrically inconsistent. In this paper, we propose the principle of minimum translation search, PROMTS, to find an inter-penetration-free configuration of the initially detected objects. The target application is to automate the task of unloading shipping containers, where a geometrically consistent configuration of objects is required for high level reasoning and manipulation. We find that the proposed approach to resolve geometrical inconsistencies improves the overall pose estimation accuracy. We examine the utility of two selected search methods: A-star and Depth-Limited search. The performance of the search algorithms are tested on data sets generated in simulation and from real-world scenarios. The results show overall improvement of the estimated poses and suggest that depth-limited search presents the best overall performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|