Searcharxiv⌕ Search

arXiv subjects

Peng Zhou

Publications and source records attributed to Peng Zhou.

At least 109 records · Page 6Linked to original sources
arXiv2024

Interactive Perception for Deformable Object Manipulation

Interactive perception enables robots to manipulate the environment and objects to bring them into states that benefit the perception process. Deformable objects pose challenges to this due to significant manipulation difficulty and occlusion in vision-based perception. In this work, we address such a problem with a setup involving both an active camera and an object manipulator. Our approach is based on a sequential decision-making framework and explicitly considers the motion regularity and structure in coupling the camera and manipulator. We contribute a method for constructing and computing a subspace, called Dynamic Active Vision Space (DAVS), for effectively utilizing the regularity in motion exploration. The effectiveness of the framework and approach are validated in both a simulation and a real dual-arm robot setup. Our results confirm the necessity of an active camera and coordinative motion in interactive perception for deformable objects.

cs.RO↗
arXiv2024

Quiver Hecke algebras from Floer homology in Couloumb branches

Homology theories categorifying quantum group link invariants are known to be governed by the representation theory of quiver Hecke algebras, also called KLRW algebras. Here we show that certain cylindrical KLRW algebras, relevant in particular for cylindrical generalizations of link homology theories, can be realized by Lagrangian Floer homology in multiplicative Coulomb branches. This confirms a homological mirror symmetry prediction of the first author.

math.SG↗
arXiv2024

Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network

Style transfer aims to render an image with the artistic features of a style image, while maintaining the original structure. Various methods have been put forward for this task, but some challenges still exist. For instance, it is difficult for CNN-based methods to handle global information and long-range dependencies between input images, for which transformer-based methods have been proposed. Although transformers can better model the relationship between content and style images, they require high-cost hardware and time-consuming inference. To address these issues, we design a novel transformer model that includes only the encoder, thus significantly reducing the computational cost. In addition, we also find that existing style transfer methods may lead to images under-stylied or missing content. In order to achieve better stylization, we design a content feature extractor and a style feature extractor, based on which pure content and style images can be fed to the transformer. Finally, we propose a novel network termed Puff-Net, i.e., pure content and style feature fusion network. Through qualitative and quantitative experiments, we demonstrate the advantages of our model compared to state-of-the-art ones in the literature.

cs.CV↗
arXiv2024

Homological mirror symmetry for complete intersections in algebraic tori

We prove one direction of homological mirror symmetry for complete intersections in algebraic tori, in all dimensions. The mirror geometry is not a space but a LG model, i.e. a pair given by a space and a regular function. We show that the Fukaya category of the complete intersection is equivalent to the category of matrix factorizations of the LG pair. Our approach yields new results also in the hypersurface setting, which was treated earlier by Gammage and Shende. Our argument depends on breaking down the complete intersection into smaller more manageable pieces, i.e. finite covers of products of higher dimensional pairs-of-pants, thus implementing a program first suggested by Seidel.

math.SG↗
arXiv2024

Memristive switching in the surface of a charge-density-wave topological semimetal

Owing to the outstanding properties provided by nontrivial band topology, topological phases of matter are considered as a promising platform towards low-dissipation electronics, efficient spin-charge conversion, and topological quantum computation. Achieving ferroelectricity in topological materials enables the non-volatile control of the quantum states, which could greatly facilitate topological electronic research. However, ferroelectricity is generally incompatible with systems featuring metallicity due to the screening effect of free carriers. In this study, we report the observation of memristive switching based on the ferroelectric surface state of a topological semimetal (TaSe4)2I. We find that the surface state of (TaSe4)2I presents out-of-plane ferroelectric polarization due to surface reconstruction. With the combination of ferroelectric surface and charge-density-wave-gapped bulk states, an electric switchable barrier height can be achieved in (TaSe4)2I-metal contact. By employing a multi-terminal grounding design, we manage to construct a prototype ferroelectric memristor based on (TaSe4)2I with on/off ratio up to 10^3, endurance over 10^3 cycles, and good retention characteristics. The origin of the ferroelectric surface state is further investigated by first-principles calculations, which reveals an interplay between ferroelectricity and band topology. The emergence of ferroelectricity in (TaSe4)2I not only demonstrates it as a rare but essential case of ferroelectric topological materials, but also opens new routes towards the implementation of topological materials in functional electronic devices.

cond-mat.mtrl-sci↗
arXiv2024

Learning to Rank Patches for Unbiased Image Redundancy Reduction

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods rely on supervisory signals. They may compel models to preserve content that aligns with labeled categories and discard content belonging to unlabeled categories. This categorical inductive bias makes these methods less effective in real-world scenarios. To address this issue, we propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches (LTRP). We observe that image reconstruction of masked image modeling models is sensitive to the removal of visible patches when the masking ratio is high (e.g., 90\%). Building upon it, we implement LTRP via two steps: inferring the semantic density score of each patch by quantifying variation between reconstructions with and without this patch, and learning to rank the patches with the pseudo score. The entire process is self-supervised, thus getting out of the dilemma of categorical inductive bias. We design extensive experiments on different datasets and tasks. The results demonstrate that LTRP outperforms both supervised and other self-supervised methods due to the fair assessment of image content.

cs.CV↗
arXiv2024

Revolutionizing Packaging: A Robotic Bagging Pipeline with Constraint-aware Structure-of-Interest Planning

Bagging operations, common in packaging and assisted living applications, are challenging due to a bag's complex deformable properties. To address this, we develop a robotic system for automated bagging tasks using an adaptive structure-of-interest (SOI) manipulation approach. Our method relies on real-time visual feedback to dynamically adjust manipulation without requiring prior knowledge of bag materials or dynamics. We present a robust pipeline featuring state estimation for SOIs using Gaussian Mixture Models (GMM), SOI generation via optimization-based bagging techniques, SOI motion planning with Constrained Bidirectional Rapidly-exploring Random Trees (CBiRRT), and dual-arm manipulation coordinated by Model Predictive Control (MPC). Experiments demonstrate the system's ability to achieve precise, stable bagging of various objects using adaptive coordination of the manipulators. The proposed framework advances the capability of dual-arm robots to perform more sophisticated automation of common tasks involving interactions with deformable objects.

cs.RO↗
arXiv2024

MV2MAE: Multi-View Video Masked Autoencoders

Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from synchronized multi-view videos. We use a cross-view reconstruction task to inject geometry information in the model. Our approach is based on the masked autoencoder (MAE) framework. In addition to the same-view decoder, we introduce a separate cross-view decoder which leverages cross-attention mechanism to reconstruct a target viewpoint video using a video from source viewpoint, to help representations robust to viewpoint changes. For videos, static regions can be reconstructed trivially which hinders learning meaningful representations. To tackle this, we introduce a motion-weighted reconstruction loss which improves temporal modeling. We report state-of-the-art results on the NTU-60, NTU-120 and ETRI datasets, as well as in the transfer learning setting on NUCLA, PKU-MMD-II and ROCOG-v2 datasets, demonstrating the robustness of our approach. Code will be made available.

cs.CV↗
arXiv2023

RWKV: Reinventing RNNs for the Transformer Era

Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit linear scaling in memory and computational requirements but struggle to match the same performance as Transformers due to limitations in parallelization and scalability. We propose a novel model architecture, Receptance Weighted Key Value (RWKV), that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. Our approach leverages a linear attention mechanism and allows us to formulate the model as either a Transformer or an RNN, thus parallelizing computations during training and maintains constant computational and memory complexity during inference. We scale our models as large as 14 billion parameters, by far the largest dense RNN ever trained, and find RWKV performs on par with similarly sized Transformers, suggesting future work can leverage this architecture to create more efficient models. This work presents a significant step towards reconciling trade-offs between computational efficiency and model performance in sequence processing tasks.

cs.CL↗
arXiv2023

Global Strong Solutions to the incompressible Magnetohydrodynamic Equations with Density-Dependent Viscosity and Vacuum in 3D Exterior Domains

The nonhomogeneous incompressible Magnetohydrodynamic Equations with density-dependent viscosity is studied in three-dimensional (3D) exterior domains with slip boundary conditions. The key is the constraint of an additional initial value condition $B_0\in L^p (1\leqslant p<12/7)$, which increase decay-in-time rates of the solutions, thus we obtain the global existence of strong solutions provided the gradient of the initial velocity and initial magnetic field is suitably small. In particular, the initial density is allowed to contain vacuum states and large oscillations. Moreover, the large-time behavior of the solution is also shown.

math.AP↗
arXiv2023

Enhancing Deformable Object Manipulation By Using Interactive Perception and Assistive Tools

In the field of robotic manipulation, the proficiency of deformable object manipulation lags behind human capabilities due to the inherent characteristics of deformable objects. These objects have infinite degrees of freedom, resulting in non-trivial perception and state estimation, and complex dynamics, complicating the prediction of future configurations. Although recent research has focused on deformable object manipulation, most approaches rely on static vision and simple manipulation techniques, limiting the performance level. This paper proposes two solutions to enhance the performance: interactive perception and the use of assistive tools. The first solution posits that optimal perspectives exist during deformable object manipulation, facilitating easier state estimation. By exploring the action-perception regularity, interactive perception facilitates better manipulation and perception. The second solution advocates for the use of assistive tools, a hallmark of human intelligence, to improve manipulation performance. For instance, a folding board can aid in garment folding tasks by reducing object deformation and managing complex dynamics. Hence, this research aims to address the deformable object manipulation problem by incorporating interactive perception and assistive tools to augment manipulation performance.

cs.RO↗
arXiv2023

A General Neural Causal Model for Interactive Recommendation

Survivor bias in observational data leads the optimization of recommender systems towards local optima. Currently most solutions re-mines existing human-system collaboration patterns to maximize longer-term satisfaction by reinforcement learning. However, from the causal perspective, mitigating survivor effects requires answering a counterfactual problem, which is generally unidentifiable and inestimable. In this work, we propose a neural causal model to achieve counterfactual inference. Specifically, we first build a learnable structural causal model based on its available graphical representations which qualitatively characterizes the preference transitions. Mitigation of the survivor bias is achieved though counterfactual consistency. To identify the consistency, we use the Gumbel-max function as structural constrains. To estimate the consistency, we apply reinforcement optimizations, and use Gumbel-Softmax as a trade-off to get a differentiable function. Both theoretical and empirical studies demonstrate the effectiveness of our solution.

cs.LG↗
arXiv2023

Integrating Visual Foundation Models for Enhanced Robot Manipulation and Motion Planning: A Layered Approach

This paper presents a novel layered framework that integrates visual foundation models to improve robot manipulation tasks and motion planning. The framework consists of five layers: Perception, Cognition, Planning, Execution, and Learning. Using visual foundation models, we enhance the robot's perception of its environment, enabling more efficient task understanding and accurate motion planning. This approach allows for real-time adjustments and continual learning, leading to significant improvements in task execution. Experimental results demonstrate the effectiveness of the proposed framework in various robot manipulation tasks and motion planning scenarios, highlighting its potential for practical deployment in dynamic environments.

cs.RO↗
arXiv2023

Fair Causal Feature Selection

Fair feature selection for classification decision tasks has recently garnered significant attention from researchers. However, existing fair feature selection algorithms fall short of providing a full explanation of the causal relationship between features and sensitive attributes, potentially impacting the accuracy of fair feature identification. To address this issue, we propose a Fair Causal Feature Selection algorithm, called FairCFS. Specifically, FairCFS constructs a localized causal graph that identifies the Markov blankets of class and sensitive variables, to block the transmission of sensitive information for selecting fair causal features. Extensive experiments on seven public real-world datasets validate that FairCFS has comparable accuracy compared to eight state-of-the-art feature selection algorithms, while presenting more superior fairness.

cs.LG↗
arXiv2023

Adaptive Shape Servoing of Elastic Rods using Parameterized Regression Features and Auto-Tuning Motion Controls

The robotic manipulation of deformable linear objects has shown great potential in a wide range of real-world applications. However, it presents many challenges due to the objects' complex nonlinearity and high-dimensional configuration. In this paper, we propose a new shape servoing framework to automatically manipulate elastic rods through visual feedback. Our new method uses parameterized regression features to compute a compact (low-dimensional) feature vector that quantifies the object's shape, thus, enabling to establish an explicit shape servo-loop. To automatically deform the rod into a desired shape, the proposed adaptive controller iteratively estimates the differential transformation between the robot's motion and the relative shape changes; This valuable capability allows to effectively manipulate objects with unknown mechanical models. An auto-tuning algorithm is introduced to adjust the robot's shaping motions in real-time based on optimal performance criteria. To validate the proposed framework, a detailed experimental study with vision-guided robotic manipulators is presented.

cs.RO↗
arXiv2023

FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly

While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation. In response, we introduce FocalDreamer, a framework that merges base shape with editable parts according to text prompts for fine-grained editing within desired regions. Specifically, equipped with geometry union and dual-path rendering, FocalDreamer assembles independent 3D parts into a complete object, tailored for convenient instance reuse and part-wise control. We propose geometric focal loss and style consistency regularization, which encourage focal fusion and congruent overall appearance. Furthermore, FocalDreamer generates high-fidelity geometry and PBR textures which are compatible with widely-used graphics engines. Extensive experiments have highlighted the superior editing capabilities of FocalDreamer in both quantitative and qualitative evaluations.

cs.CV↗
arXiv2023

Neuromorphic Hebbian learning with magnetic tunnel junction synapses

Neuromorphic computing aims to mimic both the function and structure of biological neural networks to provide artificial intelligence with extreme efficiency. Conventional approaches store synaptic weights in non-volatile memory devices with analog resistance states, permitting in-memory computation of neural network operations while avoiding the costs associated with transferring synaptic weights from a memory array. However, the use of analog resistance states for storing weights in neuromorphic systems is impeded by stochastic writing, weights drifting over time through stochastic processes, and limited endurance that reduces the precision of synapse weights. Here we propose and experimentally demonstrate neuromorphic networks that provide high-accuracy inference thanks to the binary resistance states of magnetic tunnel junctions (MTJs), while leveraging the analog nature of their stochastic spin-transfer torque (STT) switching for unsupervised Hebbian learning. We performed the first experimental demonstration of a neuromorphic network directly implemented with MTJ synapses, for both inference and spike-timing-dependent plasticity learning. We also demonstrated through simulation that the proposed system for unsupervised Hebbian learning with stochastic STT-MTJ synapses can achieve competitive accuracies for MNIST handwritten digit recognition. By appropriately applying neuromorphic principles through hardware-aware design, the proposed STT-MTJ neuromorphic learning networks provide a pathway toward artificial intelligence hardware that learns autonomously with extreme efficiency.

cs.NE↗