Prescribed Performance Control of Deformable Object Manipulation in Spatial Latent Space
🤖 AI Summary
Addressing the control challenges posed by high-dimensional state spaces and complex nonlinear dynamics in 3D deformable object manipulation, this paper proposes a model-free shape control framework. Methodologically, it employs deep learning to extract geometry-preserving keypoint representations from point clouds, yielding low-dimensional spatial features; integrates these into a visual servoing architecture; models dynamic responses via a deformation Jacobian matrix; and designs a prescribed-performance controller incorporating a barrier Lyapunov function to explicitly enforce state constraints and guarantee convergence rate during keypoint motion. Theoretical analysis proves global asymptotic stability of the closed-loop system. Experiments demonstrate high-precision shape reproduction and strong robustness under large deformations and multi-contact scenarios, significantly enhancing the practicality and reliability of autonomous deformable object manipulation.
Application Category
📝 Abstract
Manipulating three-dimensional (3D) deformable objects presents significant challenges for robotic systems due to their infinite-dimensional state space and complex deformable dynamics. This paper proposes a novel model-free approach for shape control with constraints imposed on key points. Unlike existing methods that rely on feature dimensionality reduction, the proposed controller leverages the coordinates of key points as the feature vector, which are extracted from the deformable object's point cloud using deep learning methods. This approach not only reduces the dimensionality of the feature space but also retains the spatial information of the object. By extracting key points, the manipulation of deformable objects is simplified into a visual servoing problem, where the shape dynamics are described using a deformation Jacobian matrix. To enhance control accuracy, a prescribed performance control method is developed by integrating barrier Lyapunov functions (BLF) to enforce constraints on the key points. The stability of the closed-loop system is rigorously analyzed and verified using the Lyapunov method. Experimental results further demonstrate the effectiveness and robustness of the proposed method.
Problem
Research questions and friction points this paper is trying to address.
Controls robotic manipulation of 3D deformable objects
Simplifies complex deformable dynamics using key points
Enhances control accuracy with prescribed performance constraints
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses key point coordinates as feature vector
Simplifies manipulation via visual servoing problem
Integrates barrier Lyapunov functions for control accuracy
🔎 Similar Papers
No similar papers found.
