提出自适应视觉伺服控制，让机械臂在视野外也能稳定精准定位。
Innovative Adaptive Imaged Based Visual Servoing Control of 6 DoFs Industrial Robot Manipulators
- 采用前馈-反馈结构与Youla参数化设计，实现动态自适应控制。
- 视野外点特征时仍保持快速稳定运动，进入视野后精度不降。
- 适合工业机械臂场景，无需复杂建模，易部署于多种系统。
基于图像的视觉伺服（IBVS）方法在姿态对齐中已广泛应用，但多数研究聚焦于3D点特征可见情况下的控制方案。本文提出一种创新的前馈-反馈自适应控制结构，结合Youla参数化方法。设计特征估计算法，在点特征位于视场外时确保运动控制的稳定与快速；当3D点特征进入视场后，IBVS反馈回路维持末端姿态精度。同时，在反馈回路中开发自适应控制器，实现全工况下的系统稳定性。通过自适应算法在线线性化并解耦非线性相机与机器人模型，控制器基于当前线性化点的模型实时计算。所提方案具备强鲁棒性且易于在不同工业机器人系统中实现。通过多种仿真场景验证了控制器的有效性与鲁棒性能。
原文摘要 · Abstract (English)
Image-based visual servoing (IBVS) methods have been well developed and used in many applications, especially in pose (position and orientation) alignment. However, most research papers focused on developing control solutions when 3D point features can be detected inside the field of view. This work proposes an innovative feedforward-feedback adaptive control algorithm structure with the Youla Parameterization method. A designed feature estimation loop ensures stable and fast motion control when point features are outside the field of view. As 3D point features move inside the field of view, the IBVS feedback loop preserves the precision of the pose at the end of the control period. Also, an adaptive controller is developed in the feedback loop to stabilize the system in the entire range of operations. The nonlinear camera and robot manipulator model is linearized and decoupled online by an adaptive algorithm. The adaptive controller is then computed based on the linearized model evaluated at current linearized point. The proposed solution is robust and easy to implement in different industrial robotic systems. Various scenarios are used in simulations to validate the effectiveness and robust performance of the proposed controller.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。