Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter

TL;DR

This paper introduces a Multi-View Picking (MVP) controller that actively selects camera viewpoints in real time to improve grasp detection in cluttered environments, significantly increasing success rates over static methods.

Contribution

The paper presents a novel active perception approach that dynamically chooses informative viewpoints based on grasp pose estimates, outperforming static multi-view and single-view methods.

Findings

Achieved 80% grasp success rate in cluttered object trials.

Outperformed static multi-view and single-view grasp detectors.

Demonstrated increased accuracy and efficiency in viewpoint selection.

Abstract

Camera viewpoint selection is an important aspect of visual grasp detection, especially in clutter where many occlusions are present. Where other approaches use a static camera position or fixed data collection routines, our Multi-View Picking (MVP) controller uses an active perception approach to choose informative viewpoints based directly on a distribution of grasp pose estimates in real time, reducing uncertainty in the grasp poses caused by clutter and occlusions. In trials of grasping 20 objects from clutter, our MVP controller achieves 80% grasp success, outperforming a single-viewpoint grasp detector by 12%. We also show that our approach is both more accurate and more efficient than approaches which consider multiple fixed viewpoints.