arXiv subjects

Yujun Zhu

Publications and source records attributed to Yujun Zhu.

At least 19 recordsLinked to original sources

arXiv2026

ViTacPhys: Physical Property-Aware Grasping from Human Visual-Tactile Demonstrations

Recent vision-based action models have demonstrated strong capabilities in complex manipulation, but they rarely leverage explicit object physical properties to adapt their policies. We introduce ViTacPhys, a visual-tactile framework and data acquisition system that estimates object mass and friction-coefficient classes, together with continuous stiffness, from human manipulation demonstrations. Trained on data from 60 rigid and deformable objects, ViTacPhys combines temporal visual-tactile modeling, cross-attention multimodal fusion, and a semantic prior derived from a vision-language model. On seen objects, it achieves 97.2% mass classification accuracy, 98.8% friction-coefficient classification accuracy, and a stiffness mean absolute percentage error (MAPE) of 5.51%. On held-out objects from known categories, it achieves 87.5% mass accuracy, 97.5% friction-coefficient accuracy, and a stiffness MAPE of 9.08%. We transfer ViTacPhys from the human domain to the robot domain using limited robot teleoperation data, robot-style video augmentation, and human demonstrations with matched actions, and deploy it as an online module for adaptive grasping. The resulting physical-property-conditioned policy achieves total grasping success rates of 95.0% on in-distribution objects and 83.4% on out-of-distribution objects. For out-of-distribution objects successfully grasped by both methods, its force profiles are more consistent with human teleoperation than those produced by ACT. These results demonstrate the feasibility of explicitly estimating and conditioning on object physical properties for real-world adaptive grasping.

cs.RO↗

arXiv2026

Symbolic dynamics for certain non-invertible $C^{1+β}$ maps

Let $f$ be a non-invertible $C^{1+β}(β>0)$ map with zero Lyapunov exponents and singularities on a closed Riemannian manifold $M$. We consider the symbolic dynamics of $f$. Combining the techniques in recent works of Sarig, Ovadia and Araujo-Lima-Poletti, we construct a countable Markov partition for the invariant set consisting of summable points of the inverse limit space of $(M, f)$ and show that there exists a finite-to-one symbolic extension for $f$ on the corresponding subset of $M$.

math.DS↗

arXiv2026

An efficient solver based on low-rank approximation and Neumann matrix series for unsteady diffusion-type partial differential equations with random coefficients

In this paper, we develop an efficient numerical solver for unsteady diffusion-type partial differential equations with random coefficients. A major computational challenge in such problems lies in repeatedly handling large-scale linear systems arising from spatial and temporal discretizations under uncertainty. To address this issue, we propose a novel generalized low-rank matrix approximation to represent the stochastic stiffness matrices, and approximate their inverses using the Neumann matrix series expansion. This approach transforms high-dimensional matrix inversion into a sequence of low-dimensional matrix multiplications. Therefore, the solver significantly reduces the computational cost and storage requirements while maintaining high numerical accuracy. The error analysis of the proposed solver is also provided. Finally, we apply the method to two classic uncertainty quantification problems: unsteady stochastic diffusion equations and the associated distributed optimal control problems. Numerical results demonstrate the feasibility and effectiveness of the proposed solver.

math.NA↗

arXiv2025

Topological pressure and equilibrium state for certain correspondences

In \cite{Miller-Akin1999}, Miller and Akin investigated the invariant measures for correspondences, which are also known as upper semi-continuous set-valued maps. Recently, the variational principle and thermodynamic formalism for forward expansive correspondences were studied by Li, Li and Zhang \cite{Xiaoran Li-Zhiqiang Li-Yiwei Zhang2023}. In this paper, the invariant measures and the associated transition probability kernels are explicitly expressed for certain correspondences satisfying the assumptions in \cite{Xiaoran Li-Zhiqiang Li-Yiwei Zhang2023} via the equilibrium states of some particular potentials. Let $T$ be a correspondence on a closed connected Riemannian manifold generated by finite $C^{2}$-expanding endomorphisms. When the generators of $T$ have no coincidence point, a locally Hölder continuous potential $ϕ$ of two variables is defined via the Jacobians of the generators. The pressure of $ϕ$ and its equilibrium state $(μ, \mathcal{Q})$ are obtained, where $μ$ is a $T$-invariant measure which is absolutely continuous with respect to the volume and $\mathcal{Q}$ is the associated transition probability kernel satisfying $μ\mathcal{Q}=μ$. For the correspondence $T$ on the torus whose generators have coincidence points, the variational topological pressures for measurable potentials are introduced and the corresponding equilibrium states are considered. Moreover, the uniqueness of the equilibrium states of correspondences is considered via the natural extensions.

math.DS↗

arXiv2025

On equilibrium states for certain partially hyperbolic endomorphisms with one-dimensional center

In this paper, the equilibrium states for a non-degenerate $ C^2 $ partially hyperbolic endomorphism $f$ on a closed Riemannian manifold $M$ with one-dimensional center bundle are investigated. Applying the criterion of Climenhaga-Thompson (\cite{CT21}) and the method of Mongez-Pacifico (\cite{Mongez}), we use the techniques of inverse limit to obtain the uniqueness and robustness of equilibrium states for $f$ and any Hölder continuous potential satisfying certain conditions about the unstable pressure and stable pressure.

math.DS↗

arXiv2025

Reinforcement Learning for Robotic Safe Control with Force Sensing

For the task with complicated manipulation in unstructured environments, traditional hand-coded methods are ineffective, while reinforcement learning can provide more general and useful policy. Although the reinforcement learning is able to obtain impressive results, its stability and reliability is hard to guarantee, which would cause the potential safety threats. Besides, the transfer from simulation to real world also will lead in unpredictable situations. To enhance the safety and reliability of robots, we introduce the force and haptic perception into reinforcement learning. Force and tactual sensation play key roles in robotic dynamic control and human-robot interaction. We demonstrate that the force-based reinforcement learning method can be more adaptive to environment, especially in sim-to-real transfer. Experimental results show in object pushing task, our strategy is safer and more efficient in both simulation and real world, thus it holds prospects for a wide variety of robotic applications.

cs.RO↗

arXiv2025

A low-rank solver for the Stokes-Darcy model with random hydraulic conductivity and Beavers-Joseph condition

This paper proposes, analyzes, and demonstrates an efficient low-rank solver for the stochastic Stokes-Darcy interface model with a random hydraulic conductivity both in the porous media domain and on the interface. We consider three interface conditions with randomness, including the Beavers-Joseph interface condition with the random hydraulic conductivity, on the interface between the free flow and the porous media flow. Our solver employs a novel generalized low-rank approximation of the large-scale stiffness matrices, which can significantly cut down the computational costs and memory requirements associated with matrix inversion without losing accuracy. Therefore, by adopting a suitable data compression ratio, the low-rank solver can maintain a high numerical precision with relatively low computational and space complexities. We also propose a strategy to determine the best choice of data compression ratios. Furthermore, we carry out the error analysis of the generalized low-rank matrix approximation algorithm and the low-rank solver. Finally, numerical experiments are conducted to validate the proposed algorithms and the theoretical conclusions.

math.NA↗

arXiv2025

WigglyEyes: Inferring Eye Movements from Keypress Data

We present a model for inferring where users look during interaction based on keypress data only. Given a key log, it outputs a scanpath that tells, moment-by-moment, how the user had moved eyes while entering those keys. The model can be used as a proxy for human data in cases where collecting real eye tracking data is expensive or impossible. Our technical insight is an inference architecture that considers the individual characteristics of the user, inferred as a low-dimensional parameter vector. We present a novel loss function for synchronizing inferred eye movements with the keypresses. Evaluations on touchscreen typing demonstrate accurate gaze inference.

cs.HC↗

arXiv2025

Splitting Method for Stochastic Navier-Stokes Equations

This paper investigates the two-dimensional stochastic steady-state Navier-Stokes(NS) equations with additive random noise. We introduce an innovative splitting method that decomposes the stochastic NS equations into a deterministic NS component and a stochastic equation. We rigorously analyze the proposed splitting method from the perspectives of equivalence, stability, existence and uniqueness of the solution. We also propose a modified splitting scheme, which simplified the stochastic equation by omitting its nonlinear terms. A detailed analysis of the solution properties for this modified approach is provided. Additionally, we discuss the statistical errors with both the original splitting format and the modified scheme. Our theoretical and numerical studies demonstrate that the equivalent splitting scheme exhibits significantly enhanced stability compared to the original stochastic NS equations, enabling more effective handling of nonlinear characteristics. Several numerical experiments were performed to compare the statistical errors of the splitting method and the modified splitting method. Notably, the deterministic NS equation in the splitting method does not require repeated solving, and the stochastic equation in the modified scheme is free of nonlinear terms. These features make the modified splitting method particularly advantageous for large-scale computations, as it significantly improves computational efficiency without compromising accuracy.

math.NA↗

arXiv2025

Clustering-based Low Rank Approximation Method

We propose a clustering-based generalized low rank approximation method, which takes advantage of appealing features from both the generalized low rank approximation of matrices (GLRAM) and cluster analysis. It exploits a more general form of clustering generators and similarity metrics so that it is more suitable for matrix-structured data relative to conventional partitioning methods. In our approach, we first pre-classify the initial matrix collection into several small subset clusters and then sequentially compress the matrices within the clusters. This strategy enhances the numerical precision of the low-rank approximation. In essence, we combine the ideas of GLRAM and clustering into a hybrid algorithm for dimensionality reduction. The proposed algorithm can be viewed as the generalization of both techniques. Theoretical analysis and numerical experiments are established to validate the feasibility and effectiveness of the proposed algorithm.

math.OC↗

arXiv2025

Simulating Errors in Touchscreen Typing

Empirical evidence shows that typing on touchscreen devices is prone to errors and that correcting them poses a major detriment to users' performance. Design of text entry systems that better serve users, across their broad capability range, necessitates understanding the cognitive mechanisms that underpin these errors. However, prior models of typing cover only motor slips. The paper reports on extending the scope of computational modeling of typing to cover the cognitive mechanisms behind the three main types of error: slips (inaccurate execution), lapses (forgetting), and mistakes (incorrect knowledge). Given a phrase, a keyboard, and user parameters, Typoist simulates eye and finger movements while making human-like insertion, omission, substitution, and transposition errors. Its main technical contribution is the formulation of a supervisory control problem wherein the controller allocates cognitive resources to detect and fix errors generated by the various mechanisms. The model generates predictions of typing performance that can inform design, for better text entry systems.

cs.HC↗

arXiv2024

SitPose: Real-Time Detection of Sitting Posture and Sedentary Behavior Using Ensemble Learning With Depth Sensor

Poor sitting posture can lead to various work-related musculoskeletal disorders (WMSDs). Office employees spend approximately 81.8% of their working time seated, and sedentary behavior can result in chronic diseases such as cervical spondylosis and cardiovascular diseases. To address these health concerns, we present SitPose, a sitting posture and sedentary detection system utilizing the latest Kinect depth camera. The system tracks 3D coordinates of bone joint points in real-time and calculates the angle values of related joints. We established a dataset containing six different sitting postures and one standing posture, totaling 33,409 data points, by recruiting 36 participants. We applied several state-of-the-art machine learning algorithms to the dataset and compared their performance in recognizing the sitting poses. Our results show that the ensemble learning model based on the soft voting mechanism achieves the highest F1 score of 98.1%. Finally, we deployed the SitPose system based on this ensemble model to encourage better sitting posture and to reduce sedentary habits.

cs.CV↗

arXiv2024

Real-Time Fall Detection Using Smartphone Accelerometers and WiFi Channel State Information

In recent years, as the population ages, falls have increasingly posed a significant threat to the health of the elderly. We propose a real-time fall detection system that integrates the inertial measurement unit (IMU) of a smartphone with optimized Wi-Fi channel state information (CSI) for secondary validation. Initially, the IMU distinguishes falls from routine daily activities with minimal computational demand. Subsequently, the CSI is employed for further assessment, which includes evaluating the individual's post-fall mobility. This methodology not only achieves high accuracy but also reduces energy consumption in the smartphone platform. An Android application developed specifically for the purpose issues an emergency alert if the user experiences a fall and is unable to move. Experimental results indicate that the CSI model, based on convolutional neural networks (CNN), achieves a detection accuracy of 99%, \revised{surpassing comparable IMU-only models, and demonstrating significant resilience in distinguishing between falls and non-fall activities.

cs.LG↗

arXiv2024

CLEAR: Channel Learning and Enhanced Adaptive Reconstruction for Semantic Communication in Complex Time-Varying Environments

To address the challenges of robust data transmission over complex time-varying channels, this paper introduces channel learning and enhanced adaptive reconstruction (CLEAR) strategy for semantic communications. CLEAR integrates deep joint source-channel coding (DeepJSCC) with an adaptive diffusion denoising model (ADDM) to form a unique framework. It leverages a trainable encoder-decoder architecture to encode data into complex semantic codes, which are then transmitted and reconstructed while minimizing distortion, ensuring high semantic fidelity. By addressing multipath effects, frequency-selective fading, phase noise, and Doppler shifts, CLEAR achieves high semantic fidelity and reliable transmission across diverse signal-to-noise ratios (SNRs) and channel conditions. Extensive experiments demonstrate that CLEAR achieves a 2.3 dB gain on peak signal-to-noise ratio (PSNR) over the existing state-of-the-art method, DeepJSCC-V. Furthermore, the results verify that CLEAR is robust against varying channel conditions, particularly in scenarios characterized by high Doppler shifts and strong phase noise.

cs.NI↗

arXiv2024

FlexScatter: Predictive Scheduling and Adaptive Rateless Coding for Wi-Fi Backscatter Communications in Dynamic Traffic Conditions

The potential of Wi-Fi backscatter communications systems is immense, yet challenges such as signal instability and energy constraints impose performance limits. This paper introduces FlexScatter, a Wi-Fi backscatter system using a designed scheduling strategy based on excitation prediction and rateless coding to enhance system performance. Initially, a Wi-Fi traffic prediction model is constructed by analyzing the variability of the excitation source. Then, an adaptive transmission scheduling algorithm is proposed to address the low energy consumption demands of backscatter tags, adjusting the transmission strategy according to predictive analytics and taming channel conditions. Furthermore, leveraging the benefits of low-density parity-check (LDPC) and fountain codes, a novel coding and decoding algorithm is developed, which is tailored for dynamic channel conditions. Experimental validation shows that FlexScatter reduces bit error rates (BER) by up to 30%, improves energy efficiency by 7%, and increases overall system utility by 11%, compared to conventional methods. FlexScatter's ability to balance energy consumption and communication efficiency makes it a robust solution for future IoT applications that rely on unpredictable Wi-Fi traffic.

cs.NI↗

arXiv2023

Low rank approximation method for perturbed linear systems with applications to elliptic type stochastic PDEs

In this paper, we propose a low rank approximation method for efficiently solving stochastic partial differential equations. Specifically, our method utilizes a novel low rank approximation of the stiffness matrices, which can significantly reduce the computational load and storage requirements associated with matrix inversion without losing accuracy. To demonstrate the versatility and applicability of our method, we apply it to address two crucial uncertainty quantification problems: stochastic elliptic equations and optimal control problems governed by stochastic elliptic PDE constraints. Based on varying dimension reduction ratios, our algorithm exhibits the capability to yield a high precision numerical solution for stochastic partial differential equations, or provides a rough representation of the exact solutions as a pre-processing phase. Meanwhile, our algorithm for solving stochastic optimal control problems allows a diverse range of gradient-based unconstrained optimization methods, rendering it particularly appealing for computationally intensive large-scale problems. Numerical experiments are conducted and the results provide strong validation of the feasibility and effectiveness of our algorithm.

math.NA↗

arXiv2021

Subsystems with shadowing property for $\mathbb{Z}^{k}$-actions

In this paper, subsystems with shadowing property for $\mathbb{Z}^{k}$-actions are investigated. Let $α$ be a continuous $\mathbb{Z}^{k}$-action on a compact metric space $X$. We introduce the notions of pseudo orbit and shadowing property for $α$ along subsets, particularly subspaces, of $\mathbb{R}^{k}$. Combining with another important property "expansiveness" for subsystems of $α$ which was introduced and systematically investigated by Boyle and Lind, we show that if $α$ has the shadowing property and is expansive along a subspace $V$ of $\mathbb{R}^{k}$, then so does for $α$ along any subspace $W$ of $\mathbb{R}^{k}$ containing $V$. Let $α$ be a smooth $\mathbb{Z}^{k}$-action on a closed Riemannian manifold $M$, $μ$ an ergodic probability measure and $Γ$ the Oseledec set. We show that, under a basic assumption on the Lyapunov spectrum, $α$ has the shadowing property and is expansive on $Γ$ along any subspace $V$ of $\mathbb{R}^{k}$ containing a regular vector; furthermore, $α$ has the quasi-shadowing property on $Γ$ along any 1-dimensional subspace $V$ of $\mathbb{R}^{k}$ containing a first-type singular vector. As an application, we also consider the 1-dimensional subsystems (i.e., flows) with shadowing property for the $\mathbb{R}^{k}$-action on the suspension manifold induced by $α$.

math.DS↗

arXiv2020

NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control

Traditionally, reinforcement learning methods predict the next action based on the current state. However, in many situations, directly applying actions to control systems or robots is dangerous and may lead to unexpected behaviors because action is rather low-level. In this paper, we propose a novel hierarchical reinforcement learning framework without explicit action. Our meta policy tries to manipulate the next optimal state and actual action is produced by the inverse dynamics model. To stabilize the training process, we integrate adversarial learning and information bottleneck into our framework. Under our framework, widely available state-only demonstrations can be exploited effectively for imitation learning. Also, prior knowledge and constraints can be applied to meta policy. We test our algorithm in simulation tasks and its combination with imitation learning. The experimental results show the reliability and robustness of our algorithms.

cs.RO↗