Search

In robotic assembly of flexible flat cables (FFCs), a unique challenge is the inherent difficulty in manipulating such flexible objects compared to their rigid counterparts and the precise estimation of the cable pose. This work proposes a framework that combines object pose estimation using computer-aided design (CAD) models and multiview fusion to perform precise FFC assembly. Our key insight is that a multiview fusion combined with pretrained 6-D pose estimation models offers a more flexible and precise object pose estimation. In a series of experiments involving FFC insertion tasks requiring assembly tolerances down to 0.1 mm, our approach achieves an insertion success rate of 399 out of 400 total attempts. Furthermore, the assembly tasks include the releasing and securing of FFCs from cable connectors, where the system is successful in 200 out of 200 trials. We have also demonstrated the generalization capability of the methodology by successfully completing insertion tasks for common electronic cables like DisplayPort and USB-A, achieving 199 successes in 200 trials. The results not only validate the feasibility of the proposed approach, but also demonstrate its robustness for real-world industrial applications.

Soft robotic devices have gained popularity for their ability perform intricate grasping and dexterous manipulation tasks, providing an alternative to traditional rigid robotic end-effectors. These devices are known for their simplicity, lightweight design, and cost-effectiveness. In recent developments, kirigami-inspired structures have been employed to fabricate affordable and disposable soft robotic grippers and hands. These grippers exhibit a complex post-contact reconfiguration process, adapting to the shape and size of objects they grasp. In this paper, we explore this new class of soft robotic grippers by proposing new designs and investigating their post-contact reconfiguration behaviour in a series of experiments covering grasping experiments and grasping force exertion measurement experiments. Moreover, we leverage their post-contact reconfiguration and further investigate their use in single-grasp object classification. Two classes of kirigami grippers are investigated, extension-based and compression-based. While the former was previously studied in the literature, the later is a novel class of kirigami grippers. We evaluate them and present a performance comparison between the two classes. The results demonstrate the outstanding and varied capabilities of the grippers, ranging from autonomous gripper mounting and disposal, to being able to pick-and-place delicate food items, raw egg yolks, human hair, and even liquids. Furthermore, the single-grasp object classification system exhibits a high accuracy in discriminating objects of various shapes, food items and transparent objects. These research outcomes demonstrate the kirigami-based robotic grippers’ potential in offering robust and intelligent grasping and manipulation solutions.