Counting Objects in a Robotic Hand

TL;DR

This paper introduces a contrastive learning-based classifier for accurately counting objects in a robotic hand, effectively handling occlusions, validated on simulated and real data with high accuracy.

Contribution

It presents a novel contrastive learning approach with a modified loss function for object counting in robotic grasping, addressing occlusion challenges.

Findings

Achieved above 96% accuracy in real setup for all object types.

Validated effectiveness across simulated and real environments.

Performed well with multiple object shapes like spheres, cylinders, and cubes.

Abstract

A robot performing multi-object grasping needs to sense the number of objects in the hand after grasping. The count plays an important role in determining the robot's next move and the outcome and efficiency of the whole pick-place process. This paper presents a data-driven contrastive learning-based counting classifier with a modified loss function as a simple and effective approach for object counting despite significant occlusion challenges caused by robotic fingers and objects. The model was validated against other models with three different common shapes (spheres, cylinders, and cubes) in simulation and in a real setup. The proposed contrastive learning-based counting approach achieved above 96\% accuracy for all three objects in the real setup.