2D and 3D Grasp Planners for the GET Asymmetrical Gripper

TL;DR

This paper presents two grasp planners, GET-2D-1.0 and GET-3D-1.0, for the GET asymmetrical gripper, demonstrating improved success rates and different computational efficiencies through physical experiments.

Contribution

Introduction of two novel grasp planning algorithms for the GET gripper, utilizing single-view RGB-D images and mesh-based methods with ray-tracing.

Findings

GET-2D-1.0 improves over baseline by over 40% in success metrics.

GET-3D-1.0 shows slight performance gains but is more computationally expensive.

GET-2D-1.0 is significantly faster, averaging 683 ms per plan.

Abstract

In this paper, we introduce GET-2D-1.0, a fast grasp planner for the GET asymmetrical gripper that operates from a single-view RGB-D image, using the Ferrari-Canny metric and a novel sampling strategy, and GET-3D-1.0, a mesh-based method using a 3D gripper model and ray-tracing. We evaluate both grasp planners against baselines with physical experiments, which suggest that GET-2D-1.0 can improve over a bounding box baseline by over 40% in lift success, shake survival, and force resistance. Experiments with GET-3D-1.0 suggest slight improvement compared to GET-2D-1.0 on lift success and shake survival, but are more computationally expensive, averaging 17 seconds of planning compared to 683 ms for GET-2D-1.0.