Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands

Wen, Bowen; Mitash, Chaitanya; Soorian, Sruthi; Kimmel, Andrew; Sintov, Avishai; Bekris, Kostas E.

doi:10.48550/arxiv.2003.03518

Cited by 1 publication

(1 citation statement)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, the objective is to generate complete meshes and often involves additional setup and post-processing steps. The complete models are then used to perform pose estimation [18], [19], [20], [21] over the online sensor data and transfer the manipulation actions that are defined over the model to the scene. Given the effort in modeling every object instance, some approaches operate at the category-level where objects are represented in a normalized object frame [22] or via a canonical model [23].…”

Section: Related Workmentioning

confidence: 99%

Task-driven Perception and Manipulation for Constrained Placement of Unknown Objects

Mitash¹,

Shome²,

Wen³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Recent progress in robotic manipulation has dealt with the case of previously unknown objects in the context of relatively simple tasks, such as bin-picking. Existing methods for more constrained problems, however, such as deliberate placement in a tight region, depend more critically on shape information to achieve safe execution. This work deals with pickand-constrained placement of objects without access to geometric models. The objective is to pick an object and place it safely inside a desired goal region without any collisions, while minimizing the time and the sensing operations required to complete the task. An algorithmic framework is proposed for this purpose, which performs manipulation planning simultaneously over a conservative and an optimistic estimate of the object's volume. The conservative estimate ensures that the manipulation is safe while the optimistic estimate guides the sensor-based manipulation process when no solution can be found for the conservative estimate. To maintain these estimates and dynamically update them during manipulation, objects are represented by a simple volumetric representation, which stores sets of occupied and unseen voxels. The effectiveness of the proposed approach is demonstrated by developing a robotic system that picks a previously unseen object from a table-top and places it in a constrained space. The system comprises of a dual-arm manipulator with heterogeneous endeffectors and leverages hand-offs as a re-grasping strategy. Realworld experiments show that straightforward pick-sense-andplace alternatives frequently fail to solve pick-and-constrained placement problems. The proposed pipeline, however, achieves more than 95% success rate and faster execution times as evaluated over multiple physical experiments.

show abstract