arXiv subjects

Yu Xiang

Publications and source records attributed to Yu Xiang.

At least 127 records · Page 7Linked to original sources

arXiv2021

Learning Composable Behavior Embeddings for Long-horizon Visual Navigation

Learning high-level navigation behaviors has important implications: it enables robots to build compact visual memory for repeating demonstrations and to build sparse topological maps for planning in novel environments. Existing approaches only learn discrete, short-horizon behaviors. These standalone behaviors usually assume a discrete action space with simple robot dynamics, thus they cannot capture the intricacy and complexity of real-world trajectories. To this end, we propose Composable Behavior Embedding (CBE), a continuous behavior representation for long-horizon visual navigation. CBE is learned in an end-to-end fashion; it effectively captures path geometry and is robust to unseen obstacles. We show that CBE can be used to performing memory-efficient path following and topological mapping, saving more than an order of magnitude of memory than behavior-less approaches.

cs.RO↗

arXiv2021

A Vehicles Control Model to Alleviate Traffic Instability

While bringing convenience to people, the growing number of vehicles on road already cause inevitable traffic congestion. Some traffic congestion happen with observable reasons, but others occur without apparent reasons or bottlenecks, which referred to as phantom jams, are caused by traditional vehicle following model. In order to alleviate the traffic instability caused by phantom jam, several models have been proposed with the development of intelligent transportation system (ITS). these have been proved to be able to suppress traffic instability in the ideal situation. But in road scenarios, uncertainties of vehicle state measurements and time delay caused by on-board sensors, inter-vehicle communications and control system of vehicles will affect the performance of the existing models severely, and cannot be ignored. In this paper, a novel predictable bilateral control model-PBCM, which consists of best estimation and state prediction is proposed to determine accurate acceleration values of the host vehicle in traffic flow to alleviate traffic instability. Theoretical analysis and simulation results show that our model could reduce the influence of the measurement errors and the delay caused by communication and control system effectively, control the state of the vehicles in traffic flow accurately, thus achieve the goal of restrain the instability of traffic flow.

eess.SY↗

arXiv2021

Deterministic distribution of multipartite entanglement and steering in a quantum network by separable states

As two valuable quantum resources, Einstein-Podolsky-Rosen entanglement and steering play important roles in quantum-enhanced communication protocols. Distributing such quantum resources among multiple remote users in a network is a crucial precondition underlying various quantum tasks. We experimentally demonstrate the deterministic distribution of two- and three-mode Gaussian entanglement and steering by transmitting separable states in a network consisting of a quantum server and multiple users. In our experiment, entangled states are not prepared solely by the quantum server, but are created among independent users during the distribution process. More specifically, the quantum server prepares separable squeezed states and applies classical displacements on them before spreading out, and users simply perform local beam-splitter operations and homodyne measurements after they receive separable states. We show that the distributed Gaussian entanglement and steerability are robust against channel loss. Furthermore, one-way Gaussian steering is achieved among users that is useful for further directional or highly asymmetric quantum information processing.

quant-ph↗

arXiv2020

Aerodynamic Data Predictions Based on Multi-task Learning

The quality of datasets is one of the key factors that affect the accuracy of aerodynamic data models. For example, in the uniformly sampled Burgers' dataset, the insufficient high-speed data is overwhelmed by massive low-speed data. Predicting high-speed data is more difficult than predicting low-speed data, owing to that the number of high-speed data is limited, i.e. the quality of the Burgers' dataset is not satisfactory. To improve the quality of datasets, traditional methods usually employ the data resampling technology to produce enough data for the insufficient parts in the original datasets before modeling, which increases computational costs. Recently, the mixtures of experts have been used in natural language processing to deal with different parts of sentences, which provides a solution for eliminating the need for data resampling in aerodynamic data modeling. Motivated by this, we propose the multi-task learning (MTL), a datasets quality-adaptive learning scheme, which combines task allocation and aerodynamic characteristics learning together to disperse the pressure of the entire learning task. The task allocation divides a whole learning task into several independent subtasks, while the aerodynamic characteristics learning learns these subtasks simultaneously to achieve better precision. Two experiments with poor quality datasets are conducted to verify the data quality-adaptivity of the MTL to datasets. The results show than the MTL is more accurate than FCNs and GANs in poor quality datasets.

cs.LG↗

arXiv2020

Information Laundering for Model Privacy

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be deployed for public use. The private model can be obtained from general learning methods, and its deployment means that it will return a deterministic or random response for a given input query. An information-laundered model consists of probabilistic components that deliberately maneuver the intended input and output for queries to the model, so the model's adversarial acquisition is less likely. Under the proposed framework, we develop an information-theoretic principle to quantify the fundamental tradeoffs between model utility and privacy leakage and derive the optimal design.

cs.CR↗

arXiv2020

Quasi-Fine-Grained Uncertainty Relations

Nonlocality, which is the key feature of quantum theory, has been linked with the uncertainty principle by fine-grained uncertainty relations, by considering combinations of outcomes for different measurements. However, this approach assumes that information about the system to be fine-grained is local, and does not present an explicitly computable bound. Here, we generalize above approach to general quasi-fine-grained uncertainty relations (QFGURs) which applies in the presence of quantum memory and provides conspicuously computable bounds to quantitatively link the uncertainty to entanglement and Einstein-Podolsky-Rosen (EPR) steering, respectively. Moreover, our QFGURs provide a framework to unify three important forms of uncertainty relations, i.e., universal uncertainty relations, uncertainty principle in the presence of quantum memory, and fine-grained uncertainty relation. This result gives a direct significance to the uncertainty principle, and allows us to determine whether a quantum measurement exhibits typical quantum correlations, meanwhile, it reveals a fundamental connection between basic elements of quantum theory, specifically, uncertainty measures, combined outcomes for different measurements, quantum memory, entanglement and EPR steering.

quant-ph↗

arXiv2020

Flow Field Reconstructions with GANs based on Radial Basis Functions

Nonlinear sparse data regression and generation have been a long-term challenge, to cite the flow field reconstruction as a typical example. The huge computational cost of computational fluid dynamics (CFD) makes it much expensive for large scale CFD data producing, which is the reason why we need some cheaper ways to do this, of which the traditional reduced order models (ROMs) were promising but they couldn't generate a large number of full domain flow field data (FFD) to realize high-precision flow field reconstructions. Motivated by the problems of existing approaches and inspired by the success of the generative adversarial networks (GANs) in the field of computer vision, we prove an optimal discriminator theorem that the optimal discriminator of a GAN is a radial basis function neural network (RBFNN) while dealing with nonlinear sparse FFD regression and generation. Based on this theorem, two radial basis function-based GANs (RBF-GAN and RBFC-GAN), for regression and generation purposes, are proposed. Three different datasets are applied to verify the feasibility of our models. The results show that the performance of the RBF-GAN and the RBFC-GAN are better than that of GANs/cGANs by means of both the mean square error (MSE) and the mean square percentage error (MSPE). Besides, compared with GANs/cGANs, the stability of the RBF-GAN and the RBFC-GAN improve by 34.62% and 72.31%, respectively. Consequently, our proposed models can be used to generate full domain FFD from limited and sparse datasets, to meet the requirement of high-precision flow field reconstructions.

eess.SP↗

arXiv2020

The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation

In order to function in unstructured environments, robots need the ability to recognize unseen novel objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However, the type of large-scale real-world dataset required for this task typically does not exist for most robotic settings, which motivates the use of synthetic data. We propose a novel method that separately leverages synthetic RGB and synthetic depth for unseen object instance segmentation. Our method is comprised of two stages where the first stage operates only on depth to produce rough initial masks, and the second stage refines these masks with RGB. Surprisingly, our framework is able to learn from synthetic RGB-D data where the RGB is non-photorealistic. To train our method, we introduce a large-scale synthetic dataset of random objects on tabletops. We show that our method, trained on this dataset, can produce sharp and accurate masks, outperforming state-of-the-art methods on unseen object instance segmentation. We also show that our method can segment unseen objects for robot grasping. Code, models and video can be found at https://rse-lab.cs.washington.edu/projects/unseen-object-instance-segmentation/.

cs.CV↗

arXiv2020

LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation

Current 6D object pose estimation methods usually require a 3D model for each object. These methods also require additional training in order to incorporate new objects. As a result, they are difficult to scale to a large number of objects and cannot be directly applied to unseen objects. We propose a novel framework for 6D pose estimation of unseen objects. We present a network that reconstructs a latent 3D representation of an object using a small number of reference views at inference time. Our network is able to render the latent 3D representation from arbitrary views. Using this neural renderer, we directly optimize for pose given an input image. By training our network with a large number of 3D shapes for reconstruction and rendering, our network generalizes well to unseen objects. We present a new dataset for unseen object pose estimation--MOPED. We evaluate the performance of our method for unseen object pose estimation on MOPED as well as the ModelNet and LINEMOD datasets. Our method performs competitively to supervised methods that are trained on those objects. Code and data is available at https://keunhong.com/publications/latentfusion/.

cs.CV↗

arXiv2020

Manipulation Trajectory Optimization with Online Grasp Synthesis and Selection

In robot manipulation, planning the motion of a robot manipulator to grasp an object is a fundamental problem. A manipulation planner needs to generate a trajectory of the manipulator arm to avoid obstacles in the environment and plan an end-effector pose for grasping. While trajectory planning and grasp planning are often tackled separately, how to efficiently integrate the two planning problems remains a challenge. In this work, we present a novel method for joint motion and grasp planning. Our method integrates manipulation trajectory optimization with online grasp synthesis and selection, where we apply online learning techniques to select goal configurations for grasping, and introduce a new grasp synthesis algorithm to generate grasps online. We evaluate our planning approach and demonstrate that our method generates robust and efficient motion plans for grasping in cluttered scenes. Our video can be found at https://www.youtube.com/watch?v=LIcACf8YkGU .

cs.RO↗

arXiv2020

Scaling Local Control to Large-Scale Topological Navigation

Visual topological navigation has been revitalized recently thanks to the advancement of deep learning that substantially improves robot perception. However, the scalability and reliability issue remain challenging due to the complexity and ambiguity of real world images and mechanical constraints of real robots. We present an intuitive solution to show that by accurately measuring the capability of a local controller, large-scale visual topological navigation can be achieved while being scalable and robust. Our approach achieves state-of-the-art results in trajectory following and planning in large-scale environments. It also generalizes well to real robots and new environments without retraining or finetuning.

cs.RO↗

arXiv2020

Self-supervised 6D Object Pose Estimation for Robot Manipulation

To teach robots skills, it is crucial to obtain data with supervision. Since annotating real world data is time-consuming and expensive, enabling robots to learn in a self-supervised way is important. In this work, we introduce a robot system for self-supervised 6D object pose estimation. Starting from modules trained in simulation, our system is able to label real world images with accurate 6D object poses for self-supervised learning. In addition, the robot interacts with objects in the environment to change the object configuration by grasping or pushing objects. In this way, our system is able to continuously collect data and improve its pose estimation modules. We show that the self-supervised learning improves object segmentation and 6D pose estimation performance, and consequently enables the system to grasp objects more reliably. A video showing the experiments can be found at https://youtu.be/W1Y0Mmh1Gd8.

cs.RO↗

arXiv2019

Versatile Multipartite Einstein-Podolsky-Rosen Steering via a Quantum Frequency Comb

Multipartite Einstein-Podolsky-Rosen steering is an essential resource for quantum communication networks where the reliability of equipment at all of the nodes cannot be fully trusted. Here, we present experimental generation of a highly versatile and flexible repository of multipartite steering using an optical frequency comb and ultrafast pulse shaping. Simply modulating the optical spectral resolution of the detection system using the pulse shaper, this scheme is able to produce on-demand 4, 8 and 16-mode Gaussian steering without changing the photonics architecture. We find that the steerability increases with higher spectral resolution. For 16-mode state, we identify as many as 65534 possible bipartition steering existing in this intrinsic multimode quantum resource, and demonstrate that the prepared state steerability is robust to mode losses. Moreover, we verify four types of monogamy relations of Gaussian steering and demonstrate strong violation for one of them. Our method offers a powerful foundation for constructing quantum networks in real-world scenario.

quant-ph↗

arXiv2019

DeepIM: Deep Iterative Matching for 6D Pose Estimation

Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the observed image can produce accurate results. In this work, we propose a novel deep neural network for 6D pose matching named DeepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using an untangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks for 6D pose estimation demonstrate that DeepIM achieves large improvements over state-of-the-art methods. We furthermore show that DeepIM is able to match previously unseen objects.

cs.CV↗

arXiv2019

PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

Tracking 6D poses of objects from videos provides rich information to a robot in performing different tasks such as manipulation and navigation. In this work, we formulate the 6D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3D rotation and the 3D translation of an object are decoupled. This factorization allows our approach, called PoseRBPF, to efficiently estimate the 3D translation of an object along with the full distribution over the 3D rotation. This is achieved by discretizing the rotation space in a fine-grained manner, and training an auto-encoder network to construct a codebook of feature embeddings for the discretized rotations. As a result, PoseRBPF can track objects with arbitrary symmetries while still maintaining adequate posterior distributions. Our approach achieves state-of-the-art results on two 6D pose estimation benchmarks. A video showing the experiments can be found at https://youtu.be/lE5gjzRKWuA

cs.CV↗

arXiv2019

Object Discovery in Videos as Foreground Motion Clustering

We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in videos into different objects. We introduce a novel pixel-trajectory recurrent neural network that learns feature embeddings of foreground pixel trajectories linked across time. By clustering the pixel trajectories using the learned feature embeddings, our method establishes correspondences between foreground object masks across video frames. To demonstrate the effectiveness of our framework for object discovery, we conduct experiments on commonly used datasets for motion segmentation, where we achieve state-of-the-art performance.

cs.CV↗

arXiv2019

Neural Autonomous Navigation with Riemannian Motion Policy

End-to-end learning for autonomous navigation has received substantial attention recently as a promising method for reducing modeling error. However, its data complexity, especially around generalization to unseen environments, is high. We introduce a novel image-based autonomous navigation technique that leverages in policy structure using the Riemannian Motion Policy (RMP) framework for deep learning of vehicular control. We design a deep neural network to predict control point RMPs of the vehicle from visual images, from which the optimal control commands can be computed analytically. We show that our network trained in the Gibson environment can be used for indoor obstacle avoidance and navigation on a real RC car, and our RMP representation generalizes better to unseen environments than predicting local geometry or predicting control commands directly.

cs.RO↗

arXiv2019

Estimation of the Evolutionary Spectra with Application to Stationarity Test

In this work, we propose a new inference procedure for understanding non-stationary processes, under the framework of evolutionary spectra developed by Priestley. Among various frameworks of modeling non-stationary processes, the distinguishing feature of the evolutionary spectra is its focus on the physical meaning of frequency. The classical estimate of the evolutionary spectral density is based on a double-window technique consisting of a short-time Fourier transform and a smoothing. However, smoothing is known to suffer from the so-called bias leakage problem. By incorporating Thomson's multitaper method that was originally designed for stationary processes, we propose an improved estimate of the evolutionary spectral density, and analyze its bias/variance/resolution tradeoff. As an application of the new estimate, we further propose a non-parametric rank-based stationarity test, and provide various experimental studies.

stat.ME↗