Geometry-Based Grasping of Vine Tomatoes

TL;DR

A geometry-based grasping method for vine tomatoes that allows for grasping tomato trusses without requiring delicate contact sensors or complex mechanistic models and under minimal risk of damaging the tomatoes.

Abstract

We propose a geometry-based grasping method for vine tomatoes. It relies on a computer-vision pipeline to identify the required geometric features of the tomatoes and of the truss stem. The grasping method then uses a geometric model of the robotic hand and the truss to determine a suitable grasping location on the stem. This approach allows for grasping tomato trusses without requiring delicate contact sensors or complex mechanistic models and under minimal risk of damaging the tomatoes. Lab experiments were conducted to validate the proposed methods, using an RGB-D camera and a low-cost robotic manipulator. The success rate was 83% to 92%, depending on the type of truss.

Figures (12)

• Figure 1: A human hand applies caging to a tomato truss. In this way, one can grasp the truss without applying force to the tomatoes varava2016caging.
• Figure 2: The vine tomato terminology: the stem consists of the peduncle, pedicels and calyxes combined.
• Figure 3: A cropped image overlaid with the class contours (for the sake of visualization only).
• Figure 4: Result of the tomato detection step. The identified tomatoes are shown as the dashed circles, and the estimated truss center of mass is marked by the crossed circle.
• Figure 5: The peduncle detection process. Edges are marked by the dark green lines, junctions by the purple dots, and tails by the red dots.