Grasping in Uncertain Environments: A Case Study For Industrial Robotic Recycling

TL;DR

This work tackles robust robotic grasping in uncertain industrial environments, using WEEE disassembly as a case study where vision can be unreliable. It introduces three inexpensive grippers and tactile-based force strategies, integrated into a hybrid Cartesian force-velocity control framework and a recycling-line task planner that operates with limited or no continuous vision feedback. The key contributions include selecting cost-effective grippers, embedding grasping skills into the recycling workflow, and developing force-based strategies that leverage tactile sensing to overcome pose and shape uncertainty, demonstrated across four WEEE devices in lab and plant settings. The results show substantially improved grasping robustness and success when vision is uncertain, highlighting practical benefits for productivity, safety, and adaptability in automated recycling lines, with broader applicability to other industrial domains.

Abstract

Autonomous robotic grasping of uncertain objects in uncertain environments is an impactful open challenge for the industries of the future. One such industry is the recycling of Waste Electrical and Electronic Equipment (WEEE) materials, in which electric devices are disassembled and readied for the recovery of raw materials. Since devices may contain hazardous materials and their disassembly involves heavy manual labor, robotic disassembly is a promising venue. However, since devices may be damaged, dirty and unidentified, robotic disassembly is challenging since object models are unavailable or cannot be relied upon. This case study explores grasping strategies for industrial robotic disassembly of WEEE devices with uncertain vision data. We propose three grippers and appropriate tactile strategies for force-based manipulation that improves grasping robustness. For each proposed gripper, we develop corresponding strategies that can perform effectively in different grasping tasks and leverage the grippers design and unique strengths. Through experiments conducted in lab and factory settings for four different WEEE devices, we demonstrate how object uncertainty may be overcome by tactile sensing and compliant techniques, significantly increasing grasping success rates.

Figures (9)

• Figure 1: Industrial 6-DoF robot arm in industrial environment with FT sensor and gripper attached through tool changer. A PCT is currently clamped.
• Figure 2: The selected grippers with tool changer side B attached.
• Figure 3: Embedding of the robotic grasping skills in the overall disassembly procedure. Our focus is on the top box containing the robotic grasping skills, which can be called by the task planner and delivers a result back to it. There is no feedback loop between the vision and robotic units in this system.
• Figure 4: Common structure of all grasping skills. First, the system performs an automated tool change routine if needed. Afterwards, the robot moves to a safe position. The grasping algorithm determines a safe pre-pose and sends the robot to this pose. Then, the tool dependent grasping strategy is performed. If the grasping skill fails, the robot sends a failed message to the task planner and returns to the safe pose to await the next call. Otherwise, the robot delivers the object to a specified release pose, before returning to a safe position.
• Figure 5: Tactile finger gripper with the EL light bulb pressing against it, the resulting pressure distribution on the sensor array and the calculated CoP.