PyTorchKR Papers

최신 논문

총 1,159편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1609.03519

Optimal Encoding and Decoding for Point Process Observations: an Approximate Closed-Form Filter

The process of dynamic state estimation (filtering) based on point process observations is in general intractable. Numerical sampling techniques are often practically useful, but lead to limited conceptual insight about optimal encoding/decoding strategies, which are of significant relevance to Computational Neuroscience. We develop an analytically tractable Bayesian approximation to optimal filtering based on point process observations, which allows us to introduce distributional assumptions about sensor properties, that greatly facilitate the analysis of optimal encoding in situations deviating from common assumptions of uniform coding. Numerical comparison with particle filtering demonstrate the quality of the approximation. The analytic framework leads to insights which are difficult to obtain from numerical algorithms, and is consistent with biological observations about the distribution of sensory cells' tuning curve centers.

arXiv:1610.06461

Efficient Estimation of Compressible State-Space Models with Application to Calcium Signal Deconvolution

In this paper, we consider linear state-space models with compressible innovations and convergent transition matrices in order to model spatiotemporally sparse transient events. We perform parameter and state estimation using a dynamic compressed sensing framework and develop an efficient solution consisting of two nested Expectation-Maximization (EM) algorithms. Under suitable sparsity assumptions on the innovations, we prove recovery guarantees and derive confidence bounds for the state estimates. We provide simulation studies as well as application to spike deconvolution from calcium imaging data which verify our theoretical results and show significant improvement over existing algorithms.

arXiv:1610.08616

Joint Target Detection and Tracking in Multipath Environment: A Variational Bayesian Approach

We consider multitarget detection and tracking problem for a class of multipath detection system where one target may generate multiple measurements via multiple propagation paths, and the association relationship among targets, measurements and propagation paths is unknown. In order to effectively utilize multipath measurements from one target to improve detection and tracking performance, a tracker has to handle high-dimensional estimation of latent variables including target active/dormant meta-state, target kinematic state, and multipath data association. Based on variational Bayesian inference, we propose a novel joint detection and tracking algorithm that incorporates multipath data association, target detection and target state estimation in a unified Bayesian framework. The posterior probabilities of these latent variables are derived in a closed-form iterative manner, which is effective for reducing the performance deterioration caused by the coupling between estimation errors and identification errors. Loopy belief propagation is exploited to approximately calculate the probability of multipath data association, saving the computational cost significantly. Simulation results of over-the-horizon radar multitarget tracking show that the proposed algorithm outperforms multihypothesis multipath track fusion and multi-detection (hypothesis-oriented) multiple hypothesis tracker, especially under low signal-to-noise ratio circumstance.

arXiv:1604.03635

Online Multi-Target Tracking Using Recurrent Neural Networks

We present a novel approach to online multi-target tracking based on recurrent neural networks (RNNs). Tracking multiple objects in real-world scenes involves many challenges, including a) an a-priori unknown and time-varying number of targets, b) a continuous state estimation of all present targets, and c) a discrete combinatorial problem of data association. Most previous methods involve complex models that require tedious tuning of parameters. Here, we propose for the first time, an end-to-end learning approach for online multi-target tracking. Existing deep learning methods are not designed for the above challenges and cannot be trivially applied to the task. Our solution addresses all of the above points in a principled way. Experiments on both synthetic and real data show promising results obtained at ~300 Hz on a standard CPU, and pave the way towards future research in this direction.

arXiv:1612.06669

Enhancing Observability in Distribution Grids using Smart Meter Data

Due to limited metering infrastructure, distribution grids are currently challenged by observability issues. On the other hand, smart meter data, including local voltage magnitudes and power injections, are communicated to the utility operator from grid buses with renewable generation and demand-response programs. This work employs grid data from metered buses towards inferring the underlying grid state. To this end, a coupled formulation of the power flow problem (CPF) is put forth. Exploiting the high variability of injections at metered buses, the controllability of solar inverters, and the relative time-invariance of conventional loads, the idea is to solve the non-linear power flow equations jointly over consecutive time instants. An intuitive and easily verifiable rule pertaining to the locations of metered and non-metered buses on the physical grid is shown to be a necessary and sufficient criterion for local observability in radial networks. To account for noisy smart meter readings, a coupled power system state estimation (CPSSE) problem is further developed. Both CPF and CPSSE tasks are tackled via augmented semi-definite program relaxations. The observability criterion along with the CPF and CPSSE solvers are numerically corroborated using synthetic and actual solar generation and load data on the IEEE 34-bus benchmark feeder.

arXiv:1610.00681

Team-Optimal Distributed MMSE Estimation in General and Tree Networks

We construct team-optimal estimation algorithms over distributed networks for state estimation in the finite-horizon mean-square error (MSE) sense. Here, we have a distributed collection of agents with processing and cooperation capabilities. These agents observe noisy samples of a desired state through a linear model and seek to learn this state by interacting with each other. Although this problem has attracted significant attention and been studied extensively in fields including machine learning and signal processing, all the well-known strategies do not achieve team-optimal learning performance in the finite-horizon MSE sense. To this end, we formulate the finite-horizon distributed minimum MSE (MMSE) when there is no restriction on the size of the disclosed information, i.e., oracle performance, over an arbitrary network topology. Subsequently, we show that exchange of local estimates is sufficient to achieve the oracle performance only over certain network topologies. By inspecting these network structures, we propose recursive algorithms achieving the oracle performance through the disclosure of local estimates. For practical implementations we also provide approaches to reduce the complexity of the algorithms through the time-windowing of the observations. Finally, in the numerical examples, we demonstrate the superior performance of the introduced algorithms in the finite-horizon MSE sense due to optimal estimation.

arXiv:1703.07334

Pop-up SLAM: Semantic Monocular Plane SLAM for Low-texture Environments

Existing simultaneous localization and mapping (SLAM) algorithms are not robust in challenging low-texture environments because there are only few salient features. The resulting sparse or semi-dense map also conveys little information for motion planning. Though some work utilize plane or scene layout for dense map regularization, they require decent state estimation from other sources. In this paper, we propose real-time monocular plane SLAM to demonstrate that scene understanding could improve both state estimation and dense mapping especially in low-texture environments. The plane measurements come from a pop-up 3D plane model applied to each single image. We also combine planes with point based SLAM to improve robustness. On a public TUM dataset, our algorithm generates a dense semantic 3D model with pixel depth error of 6.2 cm while existing SLAM algorithms fail. On a 60 m long dataset with loops, our method creates a much better 3D model with state estimation error of 0.67%.

arXiv:1703.06380

Direct Monocular Odometry Using Points and Lines

Most visual odometry algorithm for a monocular camera focuses on points, either by feature matching, or direct alignment of pixel intensity, while ignoring a common but important geometry entity: edges. In this paper, we propose an odometry algorithm that combines points and edges to benefit from the advantages of both direct and feature based methods. It works better in texture-less environments and is also more robust to lighting changes and fast motion by increasing the convergence basin. We maintain a depth map for the keyframe then in the tracking part, the camera pose is recovered by minimizing both the photometric error and geometric error to the matched edge in a probabilistic framework. In the mapping part, edge is used to speed up and increase stereo matching accuracy. On various public datasets, our algorithm achieves better or comparable performance than state-of-the-art monocular odometry methods. In some challenging texture-less environments, our algorithm reduces the state estimation error over 50%.

arXiv:1701.06731

Weak Adaptive Submodularity and Group-Based Active Diagnosis with Applications to State Estimation with Persistent Sensor Faults

In this paper, we consider adaptive decision-making problems for stochastic state estimation with partial observations. First, we introduce the concept of weak adaptive submodularity, a generalization of adaptive submodularity, which has found great success in solving challenging adaptive state estimation problems. Then, for the problem of active diagnosis, i.e., discrete state estimation via active sensing, we show that an adaptive greedy policy has a near-optimal performance guarantee when the reward function possesses this property. We further show that the reward function for group-based active diagnosis, which arises in applications such as medical diagnosis and state estimation with persistent sensor faults, is also weakly adaptive submodular. Finally, in experiments of state estimation for an aircraft electrical system with persistent sensor faults, we observe that an adaptive greedy policy performs equally well as an exhaustive search.

arXiv:1705.05495

A Bayesian Filtering Algorithm for Gaussian Mixture Models

A Bayesian filtering algorithm is developed for a class of state-space systems that can be modelled via Gaussian mixtures. In general, the exact solution to this filtering problem involves an exponential growth in the number of mixture terms and this is handled here by utilising a Gaussian mixture reduction step after both the time and measurement updates. In addition, a square-root implementation of the unified algorithm is presented and this algorithm is profiled on several simulated systems. This includes the state estimation for two non-linear systems that are strictly outside the class considered in this paper.

arXiv:1705.08815

Power Systems Data Fusion based on Belief Propagation

The increasing complexity of the power grid, due to higher penetration of distributed resources and the growing availability of interconnected, distributed metering devices re- quires novel tools for providing a unified and consistent view of the system. A computational framework for power systems data fusion, based on probabilistic graphical models, capable of combining heterogeneous data sources with classical state estimation nodes and other customised computational nodes, is proposed. The framework allows flexible extension of the notion of grid state beyond the view of flows and injection in bus-branch models, and an efficient, naturally distributed inference algorithm can be derived. An application of the data fusion model to the quantification of distributed solar energy is proposed through numerical examples based on semi-synthetic simulations of the standard IEEE 14-bus test case.

arXiv:1706.02495

The Generalized Cross Validation Filter

Generalized cross validation (GCV) is one of the most important approaches used to estimate parameters in the context of inverse problems and regularization techniques. A notable example is the determination of the smoothness parameter in splines. When the data are generated by a state space model, like in the spline case, efficient algorithms are available to evaluate the GCV score with complexity that scales linearly in the data set size. However, these methods are not amenable to on-line applications since they rely on forward and backward recursions. Hence, if the objective has been evaluated at time $t-1$ and new data arrive at time t, then O(t) operations are needed to update the GCV score. In this paper we instead show that the update cost is $O(1)$, thus paving the way to the on-line use of GCV. This result is obtained by deriving the novel GCV filter which extends the classical Kalman filter equations to efficiently propagate the GCV score over time. We also illustrate applications of the new filter in the context of state estimation and on-line regularized linear system identification.

arXiv:1611.06011

Online Visual Multi-Object Tracking via Labeled Random Finite Set Filtering

This paper proposes an online visual multi-object tracking algorithm using a top-down Bayesian formulation that seamlessly integrates state estimation, track management, clutter rejection, occlusion and mis-detection handling into a single recursion. This is achieved by modeling the multi-object state as labeled random finite set and using the Bayes recursion to propagate the multi-object filtering density forward in time. The proposed filter updates tracks with detections but switches to image data when mis-detection occurs, thereby exploiting the efficiency of detection data and the accuracy of image data. Furthermore the labeled random finite set framework enables the incorporation of prior knowledge that mis-detections of long tracks which occur in the middle of the scene are likely to be due to occlusions. Such prior knowledge can be exploited to improve occlusion handling, especially long occlusions that can lead to premature track termination in on-line multi-object tracking. Tracking performance are compared to state-of-the-art algorithms on well-known benchmark video datasets.

arXiv:1710.00725

Learning hard quantum distributions with variational autoencoders

Studying general quantum many-body systems is one of the major challenges in modern physics because it requires an amount of computational resources that scales exponentially with the size of the system.Simulating the evolution of a state, or even storing its description, rapidly becomes intractable for exact classical algorithms. Recently, machine learning techniques, in the form of restricted Boltzmann machines, have been proposed as a way to efficiently represent certain quantum states with applications in state tomography and ground state estimation. Here, we introduce a new representation of states based on variational autoencoders. Variational autoencoders are a type of generative model in the form of a neural network. We probe the power of this representation by encoding probability distributions associated with states from different classes. Our simulations show that deep networks give a better representation for states that are hard to sample from, while providing no benefit for random states. This suggests that the probability distributions associated to hard quantum states might have a compositional structure that can be exploited by layered neural networks. Specifically, we consider the learnability of a class of quantum states introduced by Fefferman and Umans. Such states are provably hard to sample for classical computers, but not for quantum ones, under plausible computational complexity assumptions. The good level of compression achieved for hard states suggests these methods can be suitable for characterising states of the size expected in first generation quantum hardware.

arXiv:1605.07148

Backprop KF: Learning Discriminative Deterministic State Estimators

Generative state estimators based on probabilistic filters and smoothers are one of the most popular classes of state estimators for robots and autonomous vehicles. However, generative models have limited capacity to handle rich sensory observations, such as camera images, since they must model the entire distribution over sensor readings. Discriminative models do not suffer from this limitation, but are typically more complex to train as latent variable models for state estimation. We present an alternative approach where the parameters of the latent state distribution are directly optimized as a deterministic computation graph, resulting in a simple and effective gradient descent algorithm for training discriminative state estimators. We show that this procedure can be used to train state estimators that use complex input, such as raw camera images, which must be processed using expressive nonlinear function approximators such as convolutional neural networks. Our model can be viewed as a type of recurrent neural network, and the connection to probabilistic filtering allows us to design a network architecture that is particularly well suited for state estimation. We evaluate our approach on synthetic tracking task with raw image inputs and on the visual odometry task in the KITTI dataset. The results show significant improvement over both standard generative approaches and regular recurrent neural networks.

arXiv:1705.10422

Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation

Multisensory polices are known to enhance both state estimation and target tracking. However, in the space of end-to-end sensorimotor control, this multi-sensor outlook has received limited attention. Moreover, systematic ways to make policies robust to partial sensor failure are not well explored. In this work, we propose a specific customization of Dropout, called \textit{Sensor Dropout}, to improve multisensory policy robustness and handle partial failure in the sensor-set. We also introduce an additional auxiliary loss on the policy network in order to reduce variance in the band of potential multi- and uni-sensory policies to reduce jerks during policy switching triggered by an abrupt sensor failure or deactivation/activation. Finally, through the visualization of gradients, we show that the learned policies are conditioned on the same latent states representation despite having diverse observations spaces - a hallmark of true sensor-fusion. Simulation results of the multisensory policy, as visualized in TORCS racing game, can be seen here: https://youtu.be/QAK2lcXjNZc.

arXiv:1705.10888

Identification of Gaussian Process State Space Models

The Gaussian process state space model (GPSSM) is a non-linear dynamical system, where unknown transition and/or measurement mappings are described by GPs. Most research in GPSSMs has focussed on the state estimation problem, i.e., computing a posterior of the latent state given the model. However, the key challenge in GPSSMs has not been satisfactorily addressed yet: system identification, i.e., learning the model. To address this challenge, we impose a structured Gaussian variational posterior distribution over the latent states, which is parameterised by a recognition model in the form of a bi-directional recurrent neural network. Inference with this structure allows us to recover a posterior smoothed over sequences of data. We provide a practical algorithm for efficiently computing a lower bound on the marginal likelihood using the reparameterisation trick. This further allows for the use of arbitrary kernels within the GPSSM. We demonstrate that the learnt GPSSM can efficiently generate plausible future trajectories of the identified system after only observing a small number of episodes from the true system.

arXiv:1711.08135

Contracting Nonlinear Observers: Convex Optimization and Learning from Data

A new approach to design of nonlinear observers (state estimators) is proposed. The main idea is to (i) construct a convex set of dynamical systems which are contracting observers for a particular system, and (ii) optimize over this set for one which minimizes a bound on state-estimation error on a simulated noisy data set. We construct convex sets of continuous-time and discrete-time observers, as well as contracting sampled-data observers for continuous-time systems. Convex bounds for learning are constructed using Lagrangian relaxation. The utility of the proposed methods are verified using numerical simulation.

arXiv:1709.06310

Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios

Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. These cameras do not suffer from motion blur and have a very high dynamic range, which enables them to provide reliable visual information during high speed motions or in scenes characterized by high dynamic range. However, event cameras output only little information when the amount of motion is limited, such as in the case of almost still motion. Conversely, standard cameras provide instant and rich information about the environment most of the time (in low-speed and good lighting scenarios), but they fail severely in case of fast motions, or difficult lighting such as high dynamic range or low light scenes. In this paper, we present the first state estimation pipeline that leverages the complementary advantages of these two sensors by fusing in a tightly-coupled manner events, standard frames, and inertial measurements. We show on the publicly available Event Camera Dataset that our hybrid pipeline leads to an accuracy improvement of 130% over event-only pipelines, and 85% over standard-frames-only visual-inertial systems, while still being computationally tractable. Furthermore, we use our pipeline to demonstrate - to the best of our knowledge - the first autonomous quadrotor flight using an event camera for state estimation, unlocking flight scenarios that were not reachable with traditional visual-inertial odometry, such as low-light environments and high-dynamic range scenes.

arXiv:1802.02209

IONet: Learning to Cure the Curse of Drift in Inertial Odometry

Inertial sensors play a pivotal role in indoor localization, which in turn lays the foundation for pervasive personal applications. However, low-cost inertial sensors, as commonly found in smartphones, are plagued by bias and noise, which leads to unbounded growth in error when accelerations are double integrated to obtain displacement. Small errors in state estimation propagate to make odometry virtually unusable in a matter of seconds. We propose to break the cycle of continuous integration, and instead segment inertial data into independent windows. The challenge becomes estimating the latent states of each window, such as velocity and orientation, as these are not directly observable from sensor data. We demonstrate how to formulate this as an optimization problem, and show how deep recurrent neural networks can yield highly accurate trajectories, outperforming state-of-the-art shallow techniques, on a wide range of tests and attachments. In particular, we demonstrate that IONet can generalize to estimate odometry for non-periodic motion, such as a shopping trolley or baby-stroller, an extremely challenging task for existing techniques.