A Human-Like Dual-Forklift Collaborative Mechanism for Container Handling

Abstract

At present, container handling facilities are huge in size, low in automation, and complicated to operate, which are not suitable for applications in the limited spaces. Inspired by humans’ flexible collaboration when carrying a heavy and large object, in this article we devise a novel dual-forklift collaborative mechanism to address this problem. Specifically, we design a turn lock and hydraulic lifting structure to enable a rigid connection between each forklift and the target container, deploy a four-wheel steering structure in each forklift for omnidirectional motion, and construct a novel vision system by leveraging both RGB camera and time-of-flight depth camera. Furthermore, to provide visual feedback to the controller such that the dual forklift can connect, lift, and handle the container successfully, we devise a coarse-to-fine container detection and corner junction location model. Experiments demonstrate that our model outperforms representative models in terms of both precision and efficiency. Besides, the designed dual-forklift system can accomplish the handling tasks at narrow spaces, confirming its practical value in industrial applications.