PyTorchKR Papers

최신 논문

총 174편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2311.09142공식 코드 · Papers with Code

Machine-learning parameter tracking with partial state observation

Complex and nonlinear dynamical systems often involve parameters that change with time, accurate tracking of which is essential to tasks such as state estimation, prediction, and control. Existing machine-learning methods require full state observation of the underlying system and tacitly assume adiabatic changes in the parameter. Formulating an inverse problem and exploiting reservoir computing, we develop a model-free and fully data-driven framework to accurately track time-varying parameters from partial state observation in real time. In particular, with training data from a subset of the dynamical variables of the system for a small number of known parameter values, the framework is able to accurately predict the parameter variations in time. Low- and high-dimensional, Markovian and non-Markovian nonlinear dynamical systems are used to demonstrate the power of the machine-learning based parameter-tracking framework. Pertinent issues affecting the tracking performance are addressed.

arXiv:2310.09011공식 코드 · Papers with Code

Multi-Sensor Multi-Scan Radar Sensing of Multiple Extended Targets

We propose an efficient solution to the state estimation problem in multi-scan multi-sensor multiple extended target sensing scenarios. We first model the measurement process by a doubly inhomogeneous-generalized shot noise Cox process and then estimate the parameters using a jump Markov chain Monte Carlo sampling technique. The proposed approach scales linearly in the number of measurements and can take spatial properties of the sensors into account, herein, sensor noise covariance, detection probability, and resolution. Numerical experiments using radar measurement data suggest that the algorithm offers improvements in high clutter scenarios with closely spaced targets over state-of-the-art clustering techniques used in existing multiple extended target tracking algorithms.

arXiv:2310.11699공식 코드 · Papers with Code

MISAR: A Multimodal Instructional System with Augmented Reality

Augmented reality (AR) requires the seamless integration of visual, auditory, and linguistic channels for optimized human-computer interaction. While auditory and visual inputs facilitate real-time and contextual user guidance, the potential of large language models (LLMs) in this landscape remains largely untapped. Our study introduces an innovative method harnessing LLMs to assimilate information from visual, auditory, and contextual modalities. Focusing on the unique challenge of task performance quantification in AR, we utilize egocentric video, speech, and context analysis. The integration of LLMs facilitates enhanced state estimation, marking a step towards more adaptive AR systems. Code, dataset, and demo will be available at https://github.com/nguyennm1024/misar.

arXiv:2310.04459공식 코드 · Papers with Code

Extended Kalman Filter State Estimation for Autonomous Competition Robots

Autonomous mobile robot competitions judge based on a robot's ability to quickly and accurately navigate the game field. This means accurate localization is crucial for creating an autonomous competition robot. Two common localization methods are odometry and computer vision landmark detection. Odometry provides frequent velocity measurements, while landmark detection provides infrequent position measurements. The state can also be predicted with a physics model. These three types of localization can be "fused" to create a more accurate state estimate using an Extended Kalman Filter (EKF). The EKF is a nonlinear full-state estimator that approximates the state estimate with the lowest covariance error when given the sensor measurements, the model prediction, and their variances. In this paper, we demonstrate the effectiveness of the EKF by implementing it on a 4-wheel mecanum-drive robot simulation. The position and velocity accuracy of fusing together various combinations of these three data sources are compared. We also discuss the assumptions and limitations of an EKF.

arXiv:2310.01145공식 코드 · Papers with Code

Parallel-in-Time Probabilistic Numerical ODE Solvers

Probabilistic numerical solvers for ordinary differential equations (ODEs) treat the numerical simulation of dynamical systems as problems of Bayesian state estimation. Aside from producing posterior distributions over ODE solutions and thereby quantifying the numerical approximation error of the method itself, one less-often noted advantage of this formalism is the algorithmic flexibility gained by formulating numerical simulation in the framework of Bayesian filtering and smoothing. In this paper, we leverage this flexibility and build on the time-parallel formulation of iterated extended Kalman smoothers to formulate a parallel-in-time probabilistic numerical ODE solver. Instead of simulating the dynamical system sequentially in time, as done by current probabilistic solvers, the proposed method processes all time steps in parallel and thereby reduces the span cost from linear to logarithmic in the number of time steps. We demonstrate the effectiveness of our approach on a variety of ODEs and compare it to a range of both classic and probabilistic numerical ODE solvers.

arXiv:2309.14514공식 코드 · Papers with Code

Accurate and Interactive Visual-Inertial Sensor Calibration with Next-Best-View and Next-Best-Trajectory Suggestion

Visual-Inertial (VI) sensors are popular in robotics, self-driving vehicles, and augmented and virtual reality applications. In order to use them for any computer vision or state-estimation task, a good calibration is essential. However, collecting informative calibration data in order to render the calibration parameters observable is not trivial for a non-expert. In this work, we introduce a novel VI calibration pipeline that guides a non-expert with the use of a graphical user interface and information theory in collecting informative calibration data with Next-Best-View and Next-Best-Trajectory suggestions to calibrate the intrinsics, extrinsics, and temporal misalignment of a VI sensor. We show through experiments that our method is faster, more accurate, and more consistent than state-of-the-art alternatives. Specifically, we show how calibrations with our proposed method achieve higher accuracy estimation results when used by state-of-the-art VI Odometry as well as VI-SLAM approaches. The source code of our software can be found on: https://github.com/chutsu/yac.

arXiv:2309.14263공식 코드 · Papers with Code

Target Controllability and Target Observability of Structured Network Systems

The duality between controllability and observability enables methods developed for full-state control to be applied to full-state estimation, and vice versa. In applications in which control or estimation of all state variables is unfeasible, the generalized notions of output controllability and functional observability establish the minimal conditions for the control and estimation of a target subset of state variables, respectively. Given the seemly unrelated nature of these properties, thus far methods for target control and target estimation have been developed independently in the literature. Here, we characterize the graph-theoretic conditions for target controllability and target observability (which are, respectively, special cases of output controllability and functional observability for structured systems). This allow us to rigorously establish a weak and strong duality between these generalized properties. When both properties are equivalent (strongly dual), we show that efficient algorithms developed for target controllability can be used for target observability, and vice versa, for the optimal placement of sensors and drivers. These results are applicable to large-scale networks, in which control and monitoring are often sought for small subsets of nodes.

arXiv:2309.09505공식 코드 · Papers with Code

Outlier-Insensitive Kalman Filtering: Theory and Applications

State estimation of dynamical systems from noisy observations is a fundamental task in many applications. It is commonly addressed using the linear Kalman filter (KF), whose performance can significantly degrade in the presence of outliers in the observations, due to the sensitivity of its convex quadratic objective function. To mitigate such behavior, outlier detection algorithms can be applied. In this work, we propose a parameter-free algorithm which mitigates the harmful effect of outliers while requiring only a short iterative process of the standard update step of the KF. To that end, we model each potential outlier as a normal process with unknown variance and apply online estimation through either expectation maximization or alternating maximization algorithms. Simulations and field experiment evaluations demonstrate competitive performance of our method, showcasing its robustness to outliers in filtering scenarios compared to alternative algorithms.

arXiv:2309.07016공식 코드 · Papers with Code

Adaptive KalmanNet: Data-Driven Kalman Filter with Fast Adaptation

Combining the classical Kalman filter (KF) with a deep neural network (DNN) enables tracking in partially known state space (SS) models. A major limitation of current DNN-aided designs stems from the need to train them to filter data originating from a specific distribution and underlying SS model. Consequently, changes in the model parameters may require lengthy retraining. While the KF adapts through parameter tuning, the black-box nature of DNNs makes identifying tunable components difficult. Hence, we propose Adaptive KalmanNet (AKNet), a DNN-aided KF that can adapt to changes in the SS model without retraining. Inspired by recent advances in large language model fine-tuning paradigms, AKNet uses a compact hypernetwork to generate context-dependent modulation weights. Numerical evaluation shows that AKNet provides consistent state estimation performance across a continuous range of noise distributions, even when trained using data from limited noise settings.

arXiv:2309.05075공식 코드 · Papers with Code

Secure Set-Based State Estimation for Linear Systems under Adversarial Attacks on Sensors

Set-based state estimation plays a vital role in the safety verification of dynamical systems, which becomes significantly challenging when the system's sensors are susceptible to cyber-attacks. Existing methods often impose limitations on the attacker's capabilities, restricting the number of attacked sensors to be strictly less than half of the total number of sensors. This paper proposes a Secure Set-Based State Estimation (S3E) algorithm that addresses this limitation. The S3E algorithm guarantees that the true system state is contained within the estimated set, provided the initialization set encompasses the true initial state and the system is redundantly observable from the set of uncompromised sensors. The algorithm gives the estimated set as a collection of constrained zonotopes, which can be employed as robust certificates for verifying whether the system adheres to safety constraints. Furthermore, we demonstrate that the estimated set remains unaffected by attack signals of sufficiently large and also establish sufficient conditions for attack detection, identification, and filtering. This compels the attacker to inject only stealthy signals of small magnitude to evade detection, thus preserving the accuracy of the estimated set. When a few number of sensors (less than half) can be compromised, we prove that the estimated set remains bounded by a contracting set that converges to a ball whose radius is solely determined by the noise magnitude and is independent of the attack signals. To address the computational complexity of the algorithm, we offer several strategies for complexity-performance trade-offs. The efficacy of the proposed algorithm is illustrated through its application to a three-story building model.

arXiv:2309.03979공식 코드 · Papers with Code

Separable Self and Mixed Attention Transformers for Efficient Object Tracking

The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational complexity of their attention blocks. This paper proposes an efficient self and mixed attention transformer-based architecture for lightweight tracking. The proposed backbone utilizes the separable mixed attention transformers to fuse the template and search regions during feature extraction to generate superior feature encoding. Our prediction head performs global contextual modeling of the encoded features by leveraging efficient self-attention blocks for robust target state estimation. With these contributions, the proposed lightweight tracker deploys a transformer-based backbone and head module concurrently for the first time. Our ablation study testifies to the effectiveness of the proposed combination of backbone and head modules. Simulations show that our Separable Self and Mixed Attention-based Tracker, SMAT, surpasses the performance of related lightweight trackers on GOT10k, TrackingNet, LaSOT, NfS30, UAV123, and AVisT datasets, while running at 37 fps on CPU, 158 fps on GPU, and having 3.8M parameters. For example, it significantly surpasses the closely related trackers E.T.Track and MixFormerV2-S on GOT10k-test by a margin of 7.9% and 5.8%, respectively, in the AO metric. The tracker code and model is available at https://github.com/goutamyg/SMAT

arXiv:2309.03058공식 코드 · Papers with Code

Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter

Recent years have witnessed a growing interest in tracking algorithms that augment Kalman Filters (KFs) with Deep Neural Networks (DNNs). By transforming KFs into trainable deep learning models, one can learn from data to reliably track a latent state in complex and partially known dynamics. However, unlike classic KFs, conventional DNN-based systems do not naturally provide an uncertainty measure, such as error covariance, alongside their estimates, which is crucial in various applications that rely on KF-type tracking. This work bridges this gap by studying error covariance extraction in DNN-aided KFs. We begin by characterizing how uncertainty can be extracted from existing DNN-aided algorithms and distinguishing between approaches by their ability to associate internal features with meaningful KF quantities, such as the Kalman Gain (KG) and prior covariance. We then identify that uncertainty extraction from existing architectures necessitates additional domain knowledge not required for state estimation. Based on this insight, we propose Bayesian KalmanNet, a novel DNN-aided KF that integrates Bayesian deep learning techniques with the recently proposed KalmanNet and transforms the KF into a stochastic machine learning architecture. This architecture employs sampling techniques to predict error covariance reliably without requiring additional domain knowledge, while retaining KalmanNet's ability to accurately track in partially known dynamics. Our numerical study demonstrates that Bayesian KalmanNet provides accurate and reliable tracking in various scenarios representing partially known dynamic systems.

arXiv:2309.00480공식 코드 · Papers with Code

Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network

The global navigation satellite systems (GNSS) play a vital role in transport systems for accurate and consistent vehicle localization. However, GNSS observations can be distorted due to multipath effects and non-line-of-sight (NLOS) receptions in challenging environments such as urban canyons. In such cases, traditional methods to classify and exclude faulty GNSS observations may fail, leading to unreliable state estimation and unsafe system operations. This work proposes a deep-learning-based method to detect NLOS receptions and predict GNSS pseudorange errors by analyzing GNSS observations as a spatio-temporal modeling problem. Compared to previous works, we construct a transformer-like attention mechanism to enhance the long short-term memory (LSTM) networks, improving model performance and generalization. For the training and evaluation of the proposed network, we used labeled datasets from the cities of Hong Kong and Aachen. We also introduce a dataset generation process to label the GNSS observations using lidar maps. In experimental studies, we compare the proposed network with a deep-learning-based model and classical machine-learning models. Furthermore, we conduct ablation studies of our network components and integrate the NLOS detection with data out-of-distribution in a state estimator. As a result, our network presents improved precision and recall ratios compared to other models. Additionally, we show that the proposed method avoids trajectory divergence in real-world vehicle localization by classifying and excluding NLOS observations.

arXiv:2307.08571공식 코드 · Papers with Code

Parametric and State Estimation of Stationary MEMS-IMUs: A Tutorial

Inertial navigation systems (INS) are widely used in almost any operational environment, including aviation, marine, and land vehicles. Inertial measurements from accelerometers and gyroscopes allow the INS to estimate position, velocity, and orientation of its host vehicle. However, as inherent sensor measurement errors propagate into the state estimates, accuracy degrades over time. To mitigate the resulting drift in state estimates, different approaches of parametric and state estimation are proposed to compensate for undesirable errors, using frequency-domain filtering or external information fusion. Another approach uses multiple inertial sensors, a field with rapid growth potential and applications. The increased sampling of the observed phenomenon results in the improvement of several key factors such as signal accuracy, frequency resolution, noise rejection, and higher redundancy. This study offers an analysis tutorial of basic multiple inertial operation, with a new perspective on the error relationship to time, and number of sensors. To that end, a stationary and levelled sensors array is taken, and its robustness against the instrumental errors is analyzed. Subsequently, the hypothesized analytical model is compared with the experimental results, and the level of agreement between them is thoroughly discussed. Ultimately, our results showcase the vast potential of employing multiple sensors, as we observe improvements spanning from the signal level to the navigation states. This tutorial is suitable for both newcomers and people experienced with multiple inertial sensors.

arXiv:2307.04692공식 코드 · Papers with Code

Spoofing-Resilient LiDAR-GPS Factor Graph Localization with Chimera Authentication

Many vehicle platforms typically use sensors such as LiDAR or camera for locally-referenced navigation with GPS for globally-referenced navigation. However, due to the unencrypted nature of GPS signals, all civilian users are vulner-able to spoofing attacks, where a malicious spoofer broadcasts fabricated signals and causes the user to track a false position fix. To protect against such GPS spoofing attacks, Chips-Message Robust Authentication (Chimera) has been developed and will be tested on the Navigation Technology Satellite 3 (NTS-3) satellite being launched later this year. However, Chimera authentication is not continuously available and may not provide sufficient protection for vehicles which rely on more frequent GPS measurements. In this paper, we propose a factor graph-based state estimation framework which integrates LiDAR and GPS while simultaneously detecting and mitigating spoofing attacks experienced between consecutive Chimera authentications. Our proposed framework combines GPS pseudorange measurements with LiDAR odometry to provide a robust navigation solution. A chi-squared detector, based on pseudorange residuals, is used to detect and mitigate any potential GPS spoofing attacks. We evaluate our method using real-world LiDAR data from the KITTI dataset and simulated GPS measurements, both nominal and with spoofing. Across multiple trajectories and Monte Carlo runs, our method consistently achieves position errors under 5 m during nominal conditions, and successfully bounds positioning error to within odometry drift levels during spoofed conditions.

arXiv:2306.07276공식 코드 · Papers with Code

Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving

Evaluating the performance of perception modules in autonomous driving is one of the most critical tasks in developing the complex intelligent system. While module-level unit test metrics adopted from traditional computer vision tasks are feasible to some extent, it remains far less explored to measure the impact of perceptual noise on the driving quality of autonomous vehicles in a consistent and holistic manner. In this work, we propose a principled framework that provides a coherent and systematic understanding of the impact an error in the perception module imposes on an autonomous agent's planning that actually controls the vehicle. Specifically, the planning process is formulated as expected utility maximisation, where all input signals from upstream modules jointly provide a world state description, and the planner strives for the optimal action by maximising the expected utility determined by both world states and actions. We show that, under practical conditions, the objective function can be represented as an inner product between the world state description and the utility function in a Hilbert space. This geometric interpretation enables a novel way to analyse the impact of noise in world state estimation on planning and leads to a universal metric for evaluating perception. The whole framework resembles the idea of transcendental idealism in the classical philosophical literature, which gives the name to our approach.

arXiv:2306.03897공식 코드 · Papers with Code

DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup

We address the tasks of Bayesian state estimation and forecasting for a model-free process in an unsupervised learning setup. For a model-free process, we do not have any a-priori knowledge of the process dynamics. In the article, we propose DANSE -- a Data-driven Nonlinear State Estimation method. DANSE provides a closed-form posterior of the state of the model-free process, given linear measurements of the state. In addition, it provides a closed-form posterior for forecasting. A data-driven recurrent neural network (RNN) is used in DANSE to provide the parameters of a prior of the state. The prior depends on the past measurements as input, and then we find the closed-form posterior of the state using the current measurement as input. The data-driven RNN captures the underlying non-linear dynamics of the model-free process. The training of DANSE, mainly learning the parameters of the RNN, is executed using an unsupervised learning approach. In unsupervised learning, we have access to a training dataset comprising only a set of measurement data trajectories, but we do not have any access to the state trajectories. Therefore, DANSE does not have access to state information in the training data and can not use supervised learning. Using simulated linear and non-linear process models (Lorenz attractor and Chen attractor), we evaluate the unsupervised learning-based DANSE. We show that the proposed DANSE, without knowledge of the process model and without supervised learning, provides a competitive performance against model-driven methods, such as the Kalman filter (KF), extended KF (EKF), unscented KF (UKF), a data-driven deep Markov model (DMM) and a recently proposed hybrid method called KalmanNet. In addition, we show that DANSE works for high-dimensional state estimation.

arXiv:2306.02150공식 코드 · Papers with Code

An information field theory approach to Bayesian state and parameter estimation in dynamical systems

Dynamical system state estimation and parameter calibration problems are ubiquitous across science and engineering. Bayesian approaches to the problem are the gold standard as they allow for the quantification of uncertainties and enable the seamless fusion of different experimental modalities. When the dynamics are discrete and stochastic, one may employ powerful techniques such as Kalman, particle, or variational filters. Practitioners commonly apply these methods to continuous-time, deterministic dynamical systems after discretizing the dynamics and introducing fictitious transition probabilities. However, approaches based on time-discretization suffer from the curse of dimensionality since the number of random variables grows linearly with the number of time-steps. Furthermore, the introduction of fictitious transition probabilities is an unsatisfactory solution because it increases the number of model parameters and may lead to inference bias. To address these drawbacks, the objective of this paper is to develop a scalable Bayesian approach to state and parameter estimation suitable for continuous-time, deterministic dynamical systems. Our methodology builds upon information field theory. Specifically, we construct a physics-informed prior probability measure on the function space of system responses so that functions that satisfy the physics are more likely. This prior allows us to quantify model form errors. We connect the system's response to observations through a probabilistic model of the measurement process. The joint posterior over the system responses and all parameters is given by Bayes' rule. To approximate the intractable posterior, we develop a stochastic variational inference algorithm. In summary, the developed methodology offers a powerful framework for Bayesian estimation in dynamical systems.

arXiv:2305.15445공식 코드 · Papers with Code

Deep Learning-enabled MCMC for Probabilistic State Estimation in District Heating Grids

Flexible district heating grids form an important part of future, low-carbon energy systems. We examine probabilistic state estimation in such grids, i.e., we aim to estimate the posterior probability distribution over all grid state variables such as pressures, temperatures, and mass flows conditional on measurements of a subset of these states. Since the posterior state distribution does not belong to a standard class of probability distributions, we use Markov Chain Monte Carlo (MCMC) sampling in the space of network heat exchanges and evaluate the samples in the grid state space to estimate the posterior. Converting the heat exchange samples into grid states by solving the non-linear grid equations makes this approach computationally burdensome. However, we propose to speed it up by employing a deep neural network that is trained to approximate the solution of the exact but slow non-linear solver. This novel approach is shown to deliver highly accurate posterior distributions both for classic tree-shaped as well as meshed heating grids, at significantly reduced computational costs that are acceptable for online control. Our state estimation approach thus enables tightening the safety margins for temperature and pressure control and thereby a more efficient grid operation.

arXiv:2305.10065공식 코드 · Papers with Code

Recursive Dynamic State Estimation for Power Systems with an Incomplete Nonlinear DAE Model

Power systems are highly complex, large-scale engineering systems subject to many uncertainties, which makes accurate mathematical modeling challenging. This paper proposes a novel, centralized dynamic state estimator for power systems that lack models of some components. Including the available dynamic evolution equations, algebraic network equations, and phasor measurements, we apply the least squares criterion to estimate all dynamic and algebraic states recursively. The approach results in an algorithm that generalizes the iterated extended Kalman filter and does not require static network observability. We further derive a graph theoretic condition for placing phasor measurement units that guarantees the uniqueness of the solution. A numerical study evaluates the performance under short circuits in the network and load changes and shows superior tracking performance compared to robust procedures from the literature within computational times that are feasible for real-time application.