Learning to Dexterously Pick or Separate Tangled-Prone Objects for Industrial Bin Picking

Abstract-- Industrial bin picking for tangled-prone objects requires the robot to either pick up untangled objects or perform separation manipulation when the bin contains no isolated objects. The robot must be able to flexibly perform appropriate actions based on the current observation. It is challenging due to high occlusion in the clutter, elusive entanglement phenomena, and the need for skilled manipulation planning. In this paper, we propose an autonomous, effective and general approach for picking up tangled-prone objects for industrial bin picking. First, we learn PickNet - a network that maps the visual observation to pixel-wise possibilities of picking isolated objects or separating tangled objects and infers the corresponding grasp. Then, we propose two effective separation strategies: Dropping the entangled objects into a buffer bin to reduce the degree of entanglement; Pulling to separate the entangled objects in the buffer bin planned by PullNet - a network that predicts position and direction for pulling from visual input. Other studies estimates the pose Bin picking is a valuable task in manufacturing to automate of object and evaluate the entanglement level for each object the assembly process. It deploys robots to pick [12], [13]. Such a paradigm relies on the full knowledge of necessary objects from disorganized bins, rather than relying the objects and may suffer from cumulative perception errors on human workers to arrange the objects or using a large due to heavy occlusion or self-occlusion of an individual number of part feeders. Existing studies have tackled some complex-shaped object. Other studies utilize force and torque challenges in bin picking such as planning grasps under rich sensors to classify if the robot grasps multiple objects [14].