arXiv subjects

Yuqiang Wu

Publications and source records attributed to Yuqiang Wu.

4 recordsLinked to original sources

arXiv2025

SPI-BoTER: Error Compensation for Industrial Robots via Sparse Attention Masking and Hybrid Loss with Spatial-Physical Information

The widespread application of industrial robots in fields such as cutting and welding has imposed increasingly stringent requirements on the trajectory accuracy of end-effectors. However, current error compensation methods face several critical challenges, including overly simplified mechanism modeling, a lack of physical consistency in data-driven approaches, and substantial data requirements. These issues make it difficult to achieve both high accuracy and strong generalization simultaneously. To address these challenges, this paper proposes a Spatial-Physical Informed Attention Residual Network (SPI-BoTER). This method integrates the kinematic equations of the robotic manipulator with a Transformer architecture enhanced by sparse self-attention masks. A parameter-adaptive hybrid loss function incorporating spatial and physical information is employed to iteratively optimize the network during training, enabling high-precision error compensation under small-sample conditions. Additionally, inverse joint angle compensation is performed using a gradient descent-based optimization method. Experimental results on a small-sample dataset from a UR5 robotic arm (724 samples, with a train:test:validation split of 8:1:1) demonstrate the superior performance of the proposed method. It achieves a 3D absolute positioning error of 0.2515 mm with a standard deviation of 0.15 mm, representing a 35.16\% reduction in error compared to conventional deep neural network (DNN) methods. Furthermore, the inverse angle compensation algorithm converges to an accuracy of 0.01 mm within an average of 147 iterations. This study presents a solution that combines physical interpretability with data adaptability for high-precision control of industrial robots, offering promising potential for the reliable execution of precision tasks in intelligent manufacturing.

cs.RO↗

arXiv2022

Error Processing of Sparse Identification of Nonlinear Dynamical Systems via $L_\infty$ Approximation

This paper deals with the error processing problem of sparse identification of nonlinear dynamical systems(SINDy) through introducing the $L_\infty$ approximation to take place of the former $L_2$ approximation. The motivation is that the $L_\infty$ approximation could better describe the error phenomenon in the SINDy, which consists of the derivative approximation error and the measurement noise. Then, an iterative thresholding algorithm is proposed to solve the reformulated problem. 3 scenarios of possible errors are considered in the experiment. The results show that the $L_\infty$ approximation performs better or at least equal than the $L_2$ approximation in face of different error cases. Hence, it is reasonable to consider the $L_\infty$ approximation in the applications of the SINDy.

eess.SY↗

arXiv2022

Learning Cooperative Dynamic Manipulation Skills from Human Demonstration Videos

This article proposes a method for learning and robotic replication of dynamic collaborative tasks from offline videos. The objective is to extend the concept of learning from demonstration (LfD) to dynamic scenarios, benefiting from widely available or easily producible offline videos. To achieve this goal, we decode important dynamic information, such as the Configuration Dependent Stiffness (CDS), which reveals the contribution of arm pose to the arm endpoint stiffness, from a three-dimensional human skeleton model. Next, through encoding of the CDS via Gaussian Mixture Model (GMM) and decoding via Gaussian Mixture Regression (GMR), the robot's Cartesian impedance profile is estimated and replicated. We demonstrate the proposed method in a collaborative sawing task with leader-follower structure, considering environmental constraints and dynamic uncertainties. The experimental setup includes two Panda robots, which replicate the leader-follower roles and the impedance profiles extracted from a two-persons sawing video.

cs.RO↗

arXiv2020

Reconstruction of Delay Differential Equation via Learning Parameterized Dictionary

This paper presents a variant of sparse representation modeling method, which has a promising performance of reconstruction of delay differential equation from sampling data. In the new method, a parameterized dictionary of candidate functions is constructed against the traditional expanded dictionary. The parameterized dictionary uses a function with variables to represent a series of functions. It accordingly has the ability to express functions in the continuous function space so that the dimension of the dictionary can be exponentially decreased. This is particularly important when an exhaustion of candidate functions is needed to construct appropriate dictionary. The reconstruction of delay differential equation is such the case that each possible delay item should be considered as the basis to construct the dictionary and this naturally induces the curse of dimensionality. Correspondingly, the parameterized dictionary uses a variable to model the delay item so the curse disappears. Based on the parameterized dictionary, the reconstruction problem is then rewritten and treated as a mixed-integer nonlinear programming with both binary and continuous variables. To the best of our knowledge, such optimization problem is hard to solve with the traditional mathematical methods while the emerging evolutionary computation provides competitive solutions. Hence, the evolutionary computation technique is considered and a typical algorithm named particle swarm optimization is adopted in this paper. Experiments are carried out in 5 test systems including 3 well-known chaotic delay differential equations such as Mackey-Glass system. The experiment result shows the effectiveness of the new method to reconstruct delay differential equation.

eess.SP↗