Robust AI-Driven Target-Object-Free Hybrid Vision/Force Control of Industrial Robotic Systems
提出一种基于AI的混合视觉/力控制方法，利用预训练深度神经网络提取图像特征，无需目标物体即可实现工业机器人的精确跟踪和力控制，实验证明其在抛光打磨任务中优于传统方法。
This article introduces a robust AI-driven hybrid vision/force control (HVFC) method for industrial robots. The proposed HVFC method exploits Superpoint, a pretrained deep convolutional neural network (DCNN), as the AI agent to extract interest points for image-based visual servoing (IBVS), making it a target-object-free method. This tackles the limited workspace issue of eye-in-hand robots interacting with a workpiece due to the short distance between the camera and the workpiece, including a target object or landmarks. A learning-by-demonstration (LBD) method is also developed to generate the desired interest points associated with the desired path on the workpiece for interaction. To handle the issue of a high and variable number of interest points for use in IBVS, a set of six independent image features is extracted from the detected interest points, resulting in an invertible image interaction matrix, leading to global stability and a robust control process. To perform HVFC, a hierarchical orthogonal sliding manifold is defined, allowing force control in the normal direction and IBVS in the rest. Further, a filtered terminal integral sliding-mode controller is developed to stabilize the manifold, resulting in high tracking accuracy and robust performance against uncertainties and measurement noises. The experimental results of polishing and sanding the surfaces of a flat plastic board, a wooden airplane propeller, and a metal pegboard demonstrate the feasibility and superiority of the proposed HVFC-LBD method over conventional counterparts in terms of workspace expansion, robustness, and tracking accuracy.