Only Pick Once: Algorithms for Efficiently Picking an Exact Number of Multiple Identical Objects

Zihe Ye, Ricardo Frumento, Yu Sun

Abstract: Picking up multiple objects at once is a grasping skill that makes a human worker efficient in many domains. This work tackles the problem of getting a requested number of identical objects in a shallow bin by only pick once (OPO) using a simple parallel gripper. The proposed system contains several graph-based algorithms that convert the layout of objects into a graph, cluster vertices in the graph, rank and select candidate clusters based on their topology. Our algorithm also has a multi-object picking predictor based on a convolutional neural network for estimating how many objects would be picked up with a given gripper location and orientation. This paper presents four evaluation metrics and three protocols to evaluate the proposed system. The results show that our proposed system has very high success rates for two and three objects when only picking once. Utilizing our approach can significantly outperform single object picking two to three times in terms of efficiency. The results also show our algorithm can be applied to one unseen shape (hexagon) and unseen sizes cube and cylinder during training without fine-tuning to achieve decent accuracy. Note to Practitioners—This paper is motivated by the current bottleneck in robotics picking which restricts the mass deployment of robots in tasks that are similar to batch-picking in logistics. The state of the art (SOTA) picking algorithm is fast but only focuses on picking one object at a time, which inspires us to look into picking multiple objects at once to increase the efficiency. We design a custom-sized parallel-jaw gripper based on the object sizes’ need, and we train a deep-learning model for each designed gripper to predict the number of objects that a grasp pose can retrieve. Our simulation and real-life evaluations have very good results in picking 2 to 3 objects at once in a random setting. Our future work will consider more complex scenarios and rearrangements that can break some hard settings.