Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ICGNet: A Unified Approach for Instance-Centric Grasping

About

Accurate grasping is the key to several robotic tasks including assembly and household robotics. Executing a successful grasp in a cluttered environment requires multiple levels of scene understanding: First, the robot needs to analyze the geometric properties of individual objects to find feasible grasps. These grasps need to be compliant with the local object geometry. Second, for each proposed grasp, the robot needs to reason about the interactions with other objects in the scene. Finally, the robot must compute a collision-free grasp trajectory while taking into account the geometry of the target object. Most grasp detection algorithms directly predict grasp poses in a monolithic fashion, which does not capture the composability of the environment. In this paper, we introduce an end-to-end architecture for object-centric grasping. The method uses pointcloud data from a single arbitrary viewing direction as an input and generates an instance-centric representation for each partially observed object in the scene. This representation is further used for object reconstruction and grasp detection in cluttered table-top scenes. We show the effectiveness of the proposed method by extensively evaluating it against state-of-the-art methods on synthetic datasets, indicating superior performance for grasping and reconstruction. Additionally, we demonstrate real-world applicability by decluttering scenes with varying numbers of objects.

Ren\'e Zurbr\"ugg, Yifan Liu, Francis Engelmann, Suryansh Kumar, Marco Hutter, Vaishakh Patil, Fisher Yu• 2024

Related benchmarks

TaskDatasetResultRank
Clutter removalPile scenes single-view, fixed camera, gamma noise
GSR57.3
16
Clutter removalPacked scenes single-view, fixed camera, gamma noise
GSR60.3
16
Clutter removalPacked single-view, random camera pose, Gaussian noise
GSR97.7
10
Clutter removalPile single-view, random camera pose, Gaussian noise
GSR92
10
Clutter removalPile Real-world
GSR (%)71.1
7
Clutter removalReal-world Packed
GSR72.2
7
Clutter removalReal-world Adv
GSR69.9
7
Showing 7 of 7 rows

Other info

Follow for update