Counting Objects in a Robotic Hand
This addresses a specific challenge in robotics for multi-object grasping, though it is incremental as it applies a modified contrastive learning method to an existing bottleneck.
The paper tackled the problem of counting objects in a robotic hand after grasping to improve pick-place efficiency, achieving over 96% accuracy for spheres, cylinders, and cubes in real-world tests.
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.