Search papers, labs, and topics across Lattice.
This paper introduces GET-2D-1.0, a fast 2D grasp planner utilizing the Ferrari-Canny metric and a novel sampling strategy on RGB-D images, and GET-3D-1.0, a mesh-based 3D grasp planner using ray-tracing. Physical experiments demonstrate that GET-2D-1.0 significantly outperforms a bounding box baseline, improving lift success, shake survival, and force resistance by over 40%. While GET-3D-1.0 shows marginal improvements in lift success and shake survival compared to GET-2D-1.0, it comes at a significantly higher computational cost.
A 2D grasp planner can outperform a 3D one in real-world robotic manipulation tasks, while being 25x faster.
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.
