The number of images taken from different view-points plays an important role in the accuracy of object detection in cluttered scenarios. Considering Electric Vehicles battery pack disassembly task, which is a highly dense clutter, a framework is proposed to approximate the number of viewpoints to acquire the accuracy of 3.82 mm in screw detection. The paper explores two methods of image acquisition i) taking multiple 3D images, and ii) taking one 3D image and multiple 2D images and combines it with two methods of image processing i) marking the exact visible center of the screw for calculation, and ii) using a bounding box to mark the screw and calculating the center by intersecting diagonals. The results show that using eight viewpoints with a reliable 3D camera delivers the optimal results.

Automation in Electric Vehicle (EV) Li-Ion Battery (LIB) pack disassembly is getting a lot of attraction with increased number of EVs being manufactured. Highly cluttered components placed in complex configurations present a unique challenge for object detection models. To get maximum coverage of the components in the EV battery pack, images from multiple viewpoints are considered and merged using Multiple-View Super Resolution (MVSR). The proposed method provides 7% higher accuracy in the screw detection task than the statistical methods previously derived [[1]].

The automation of recycling processes for electric vehicle lithium-ion battery packs is crucial for the advancement of green energy transportation. Testing disassembly strategies on real equipment is time consuming, expensive, and poses significant safety risks. This paper presents a novel simulation-based framework that leverages the integration of a high-fidelity virtual environment with a Robot Operating System (ROS) to visualize and accurately calculate the time required for complex robotic disassembly operations. The calculated operation times are then used as input for genetic algorithm optimization to improve process efficiency. The results demonstrate that automation significantly improves the total speed of the disassembly process compared to manual methods. By utilizing this novel simulation and optimization approach, a 25% improvement in performance was achieved for the pack-to-module disassembly stage. This method provides a safe and cost-effective approach for process design, contributing directly to the development of a circular economy and supporting the transition towards sustainable transportation.