PyTorchKR Papers

최신 논문

총 1,050편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2211.15044

Machine Learning Accelerated PDE Backstepping Observers

State estimation is important for a variety of tasks, from forecasting to substituting for unmeasured states in feedback controllers. Performing real-time state estimation for PDEs using provably and rapidly converging observers, such as those based on PDE backstepping, is computationally expensive and in many cases prohibitive. We propose a framework for accelerating PDE observer computations using learning-based approaches that are much faster while maintaining accuracy. In particular, we employ the recently-developed Fourier Neural Operator (FNO) to learn the functional mapping from the initial observer state and boundary measurements to the state estimate. By employing backstepping observer gains for previously-designed observers with particular convergence rate guarantees, we provide numerical experiments that evaluate the increased computational efficiency gained with FNO. We consider the state estimation for three benchmark PDE examples motivated by applications: first, for a reaction-diffusion (parabolic) PDE whose state is estimated with an exponential rate of convergence; second, for a parabolic PDE with exact prescribed-time estimation; and, third, for a pair of coupled first-order hyperbolic PDEs that modeling traffic flow density and velocity. The ML-accelerated observers trained on simulation data sets for these PDEs achieves up to three orders of magnitude improvement in computational speed compared to classical methods. This demonstrates the attractiveness of the ML-accelerated observers for real-time state estimation and control.

arXiv:2211.14033

Minimal regret state estimation of time-varying systems

Kalman and H-infinity filters, the most popular paradigms for linear state estimation, are designed for very specific specific noise and disturbance patterns, which may not appear in practice. State observers based on the minimization of regret measures are a promising alternative, as they aim to adapt to recognizable patterns in the estimation error. In this paper, we show that the regret minimization problem for finite horizon estimation can be cast into a simple convex optimization problem. For this purpose, we first rewrite linear time-varying system dynamics using a novel system level synthesis parametrization for state estimation, capable of handling both disturbance and measurement noise. We then provide a tractable formulation for the minimization of regret based on semi-definite programming. Both contributions make the minimal regret observer design easily implementable in practice. Finally, numerical experiments show that the computed observer can significantly outperform both H-2 and H-infinity filters.

arXiv:2211.13411

Remote State Estimation with Privacy Against Eavesdroppers

We study the problem of remote state estimation in the presence of a passive eavesdropper, under the challenging network environment of no packet receipt acknowledgments. A remote legitimate user estimates the state of a linear plant from the state information received from a sensor via an insecure and unreliable network. The transmission from the sensor may be intercepted by the eavesdropper. To maintain state confidentiality, we propose an encoding scheme. Our scheme transmits noise based on a pseudo-random indicator, pre-arranged at the legitimate user and sensor. The transmission of noise harms the eavesdropper's performance, more than that of the legitimate user. Using the proposed encoding scheme, we impair the eavesdropper's expected estimation performance, whilst minimising expected performance degradation at the legitimate user. We explore the trade-off between state confidentiality and legitimate user performance degradation.

arXiv:2211.14125공식 코드 · Papers with Code

PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation

Accurate 6D object pose estimation is an important task for a variety of robotic applications such as grasping or localization. It is a challenging task due to object symmetries, clutter and occlusion, but it becomes more challenging when additional information, such as depth and 3D models, is not provided. We present a transformer-based approach that takes an RGB image as input and predicts a 6D pose for each object in the image. Besides the image, our network does not require any additional information such as depth maps or 3D object models. First, the image is passed through an object detector to generate feature maps and to detect objects. Then, the feature maps are fed into a transformer with the detected bounding boxes as additional information. Afterwards, the output object queries are processed by a separate translation and rotation head. We achieve state-of-the-art results for RGB-only approaches on the challenging YCB-V dataset. We illustrate the suitability of the resulting model as pose sensor for a 6-DoF state estimation task. Code is available at https://github.com/aau-cns/poet.

arXiv:2211.11404

Approximating a Laplacian Prior for Joint State and Model Estimation within an UKF

A major challenge in state estimation with model-based observers are low-quality models that lack of relevant dynamics. We address this issue by simultaneously estimating the system's states and its model uncertainties by a square root UKF. Concretely, we extend the state by the parameter vector of a linear combination containing suitable functions that approximate the lacking dynamics. Presuming that only a few dynamical terms are relevant, the parameter vector is claimed to be sparse. In Bayesian setting, properties like sparsity are expressed by a prior distribution. One common choice for sparsity is a Laplace distribution. However, due to some disadvantages of a Laplacian prior, the regularized horseshoe distribution, a Gaussian that approximately features sparsity, is applied. Results exhibit small estimation errors with model improvements detected by an automated model reduction technique.

arXiv:2211.10827

Structure-Enhanced Deep Reinforcement Learning for Optimal Transmission Scheduling

Remote state estimation of large-scale distributed dynamic processes plays an important role in Industry 4.0 applications. In this paper, by leveraging the theoretical results of structural properties of optimal scheduling policies, we develop a structure-enhanced deep reinforcement learning (DRL) framework for optimal scheduling of a multi-sensor remote estimation system to achieve the minimum overall estimation mean-square error (MSE). In particular, we propose a structure-enhanced action selection method, which tends to select actions that obey the policy structure. This explores the action space more effectively and enhances the learning efficiency of DRL agents. Furthermore, we introduce a structure-enhanced loss function to add penalty to actions that do not follow the policy structure. The new loss function guides the DRL to converge to the optimal policy structure quickly. Our numerical results show that the proposed structure-enhanced DRL algorithms can save the training time by 50% and reduce the remote estimation MSE by 10% to 25%, when compared to benchmark DRL algorithms.

arXiv:2211.10097

Nonlinear Moving Horizon Estimation and Model Predictive Control for Buildings with Unknown HVAC Dynamics

We present a solution for modeling and online identification for heating, ventilation, and air conditioning (HVAC) control in buildings. Our approach comprises: (a) a resistance-capacitance (RC) model based on first order energy balance for deriving the zone temperature dynamics, and (b) a neural network for modeling HVAC dynamics. State estimation and model identification are simultaneously performed using nonlinear moving horizon estimation (MHE) with physical constraints for system states. We leverage the identified model in model predictive control (MPC) for occupant comfort satisfaction and HVAC energy savings and verify the approach using simulations. Our system relies only on building management system data, does not require extensive data storage, and does not require a detailed building model. This can significantly aid the large scale adoption of MPC for future occupant-centric control of grid-interactive buildings.

arXiv:2211.09741

Learning 4DVAR inversion directly from observations

Variational data assimilation and deep learning share many algorithmic aspects in common. While the former focuses on system state estimation, the latter provides great inductive biases to learn complex relationships. We here design a hybrid architecture learning the assimilation task directly from partial and noisy observations, using the mechanistic constraint of the 4DVAR algorithm. Finally, we show in an experiment that the proposed method was able to learn the desired inversion with interesting regularizing properties and that it also has computational interests.

arXiv:2211.08474

Resilient Set-based State Estimation for Linear Time-Invariant Systems Using Zonotopes

This paper considers the problem of set-based state estimation for linear time-invariant (LTI) systems under time-varying sensor attacks. Provided that the LTI system is stable and observable via every single sensor and that at least one sensor is uncompromised, we guarantee that the true state is always contained in the estimated set. We use zonotopes to represent these sets for computational efficiency. However, we show that intelligently designed stealthy attacks may cause exponential growth in the algorithm's worst-case complexity. We present several strategies to handle this complexity issue and illustrate our resilient zonotope-based state estimation algorithm on a rotating target system.

arXiv:2211.05922

Internal feedback in the cortical perception-action loop enables fast and accurate behavior

Animals move smoothly and reliably in unpredictable environments. Models of sensorimotor control have assumed that sensory information from the environment leads to actions, which then act back on the environment, creating a single, unidirectional perception-action loop. This loop contains internal delays in sensory and motor pathways, which can lead to unstable control. We show here that these delays can be compensated by internal feedback signals that flow backwards, from motor towards sensory areas. Internal feedback is ubiquitous in neural sensorimotor systems and recent advances in control theory show how internal feedback compensates internal delays. This is accomplished by filtering out self-generated and other predictable changes in early sensory areas so that unpredicted, actionable information can be rapidly transmitted toward action by the fastest components. For example, fast, giant neurons are necessarily less accurate than smaller neurons, but they are crucial for fast and accurate behavior. We use a mathematically tractable control model to show that internal feedback has an indispensable role in achieving state estimation, localization of function -- how different parts of cortex control different parts of the body -- and attention, all of which are crucial for effective sensorimotor control. This control model can explain anatomical, physiological and behavioral observations, including motor signals in visual cortex, heterogeneous kinetics of sensory receptors and the presence of giant Betz cells in motor cortex, Meynert cells in visual cortex and giant von Economo cells in the prefrontal cortex of humans as well as internal feedback patterns and unexplained heterogeneity in other neural systems.

arXiv:2211.05566

Secure State Estimation against Sparse Attacks on a Time-varying Set of Sensors

This paper studies the problem of secure state estimation of a linear time-invariant (LTI) system with bounded noise in the presence of sparse attacks on an unknown, time-varying set of sensors. In other words, at each time, the attacker has the freedom to choose an arbitrary set of no more that $p$ sensors and manipulate their measurements without restraint. To this end, we propose a secure state estimation scheme and guarantee a bounded estimation error subject to $2p$-sparse observability and a mild, technical assumption that the system matrix has no degenerate eigenvalues. The proposed scheme comprises a design of decentralized observer for each sensor based on the local observable subspace decomposition. At each time step, the local estimates of sensors are fused by solving an optimization problem to obtain a secure estimation, which is then followed by a local detection-and-resetting process of the decentralized observers. The estimation error is shown to be upper-bounded by a constant which is determined only by the system parameters and noise magnitudes. Moreover, we optimize the detector threshold to ensure that the benign sensors do not trigger the detector. The efficacy of the proposed algorithm is demonstrated by its application on a benchmark example of IEEE 14-bus system.

arXiv:2211.05223

Distributed State Estimation for Linear Time-invariant Systems with Aperiodic Sampled Measurement

This paper deals with the state estimation of linear time-invariant systems using distributed observers with local sampled-data measurement and aperiodic communication. Each observer agent perceives partial information of the system to be observed but does not satisfy the observability condition. Consequently, distributed observers are designed to exponentially estimate the state of the system to be observed by time-varying sampling and asynchronous communication. Additionally, explicit upper bounds on allowable sampling periods for convergent estimation errors are given. Finally, a numerical example is provided to demonstrate the validity of the theoretical results

arXiv:2211.04979

Perceived personality state estimation in dyadic and small group interaction with deep learning methods

Dyadic and small group collaboration is an evolutionary advantageous behaviour and the need for such collaboration is a regular occurrence in day to day life. In this paper we estimate the perceived personality traits of individuals in dyadic and small groups over thin-slices of interaction on four multimodal datasets. We find that our transformer based predictive model performs similarly to human annotators tasked with predicting the perceived big-five personality traits of participants. Using this model we analyse the estimated perceived personality traits of individuals performing tasks in small groups and dyads. Permutation analysis shows that in the case of small groups undergoing collaborative tasks, the perceived personality of group members clusters, this is also observed for dyads in a collaborative problem solving task, but not in dyads under non-collaborative task settings. Additionally, we find that the group level average perceived personality traits provide a better predictor of group performance than the group level average self-reported personality traits.

arXiv:2211.04631

Maximum likelihood recursive state estimation in state-space models: A new approach based on statistical analysis of incomplete data

This paper revisits the work of Rauch et al. (1965) and develops a novel method for recursive maximum likelihood particle filtering for general state-space models. The new method is based on statistical analysis of incomplete observations of the systems. Score function and conditional observed information of the incomplete observations/data are introduced and their distributional properties are discussed. Some identities concerning the score function and information matrices of the incomplete data are derived. Maximum likelihood estimation of state-vector is presented in terms of the score function and observed information matrices. In particular, to deal with nonlinear state-space, a sequential Monte Carlo method is developed. It is given recursively by an EM-gradient-particle filtering which extends the work of Lange (1995) for state estimation. To derive covariance matrix of state-estimation errors, an explicit form of observed information matrix is proposed. It extends Louis (1982) general formula for the same matrix to state-vector estimation. Under (Neumann) boundary conditions of state transition probability distribution, the inverse of this matrix coincides with the Cramer-Rao lower bound on the covariance matrix of estimation errors of unbiased state-estimator. In the case of linear models, the method shows that the Kalman filter is a fully efficient state estimator whose covariance matrix of estimation error coincides with the Cramer-Rao lower bound. Some numerical examples are discussed to exemplify the main results.

arXiv:2211.03803공식 코드 · Papers with Code

Quantum-probabilistic Hamiltonian learning for generative modelling & anomaly detection

The Hamiltonian of an isolated quantum mechanical system determines its dynamics and physical behaviour. This study investigates the possibility of learning and utilising a system's Hamiltonian and its variational thermal state estimation for data analysis techniques. For this purpose, we employ the method of Quantum Hamiltonian-based models for the generative modelling of simulated Large Hadron Collider data and demonstrate the representability of such data as a mixed state. In a further step, we use the learned Hamiltonian for anomaly detection, showing that different sample types can form distinct dynamical behaviours once treated as a quantum many-body system. We exploit these characteristics to quantify the difference between sample types. Our findings show that the methodologies designed for field theory computations can be utilised in machine learning applications to employ theoretical approaches in data analysis techniques.

arXiv:2210.14985

Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing

Autonomous drones can operate in remote and unstructured environments, enabling various real-world applications. However, the lack of effective vision-based algorithms has been a stumbling block to achieving this goal. Existing systems often require hand-engineered components for state estimation, planning, and control. Such a sequential design involves laborious tuning, human heuristics, and compounding delays and errors. This paper tackles the vision-based autonomous-drone-racing problem by learning deep sensorimotor policies. We use contrastive learning to extract robust feature representations from the input images and leverage a two-stage learning-by-cheating framework for training a neural network policy. The resulting policy directly infers control commands with feature representations learned from raw images, forgoing the need for globally-consistent state estimation, trajectory planning, and handcrafted control design. Our experimental results indicate that our vision-based policy can achieve the same level of racing performance as the state-based policy while being robust against different visual disturbances and distractors. We believe this work serves as a stepping-stone toward developing intelligent vision-based autonomous systems that control the drone purely from image inputs, like human pilots.

arXiv:2210.14816

Deep Subspace Encoders for Nonlinear System Identification

Using Artificial Neural Networks (ANN) for nonlinear system identification has proven to be a promising approach, but despite of all recent research efforts, many practical and theoretical problems still remain open. Specifically, noise handling and models, issues of consistency and reliable estimation under minimisation of the prediction error are the most severe problems. The latter comes with numerous practical challenges such as explosion of the computational cost in terms of the number of data samples and the occurrence of instabilities during optimization. In this paper, we aim to overcome these issues by proposing a method which uses a truncated prediction loss and a subspace encoder for state estimation. The truncated prediction loss is computed by selecting multiple truncated subsections from the time series and computing the average prediction loss. To obtain a computationally efficient estimation method that minimizes the truncated prediction loss, a subspace encoder represented by an artificial neural network is introduced. This encoder aims to approximate the state reconstructability map of the estimated model to provide an initial state for each truncated subsection given past inputs and outputs. By theoretical analysis, we show that, under mild conditions, the proposed method is locally consistent, increases optimization stability, and achieves increased data efficiency by allowing for overlap between the subsections. Lastly, we provide practical insights and user guidelines employing a numerical example and state-of-the-art benchmark results.

arXiv:2210.09481

FPGA Hardware Acceleration for Feature-Based Relative Navigation Applications

Estimation of rigid transformation between two point clouds is a computationally challenging problem in vision-based relative navigation. Targeting a real-time navigation solution utilizing point-cloud and image registration algorithms, this paper develops high-performance avionics for power and resource constrained pose estimation framework. A Field-Programmable Gate Array (FPGA) based embedded architecture is developed to accelerate estimation of relative pose between the point-clouds, aided by image features that correspond to the individual point sets. At algorithmic level, the pose estimation method is an adaptation of Optimal Linear Attitude and Translation Estimator (OLTAE) for relative attitude and translation estimation. At the architecture level, the proposed embedded solution is a hardware/software co-design that evaluates the OLTAE computations on the bare-metal hardware for high-speed state estimation. The finite precision FPGA evaluation of the OLTAE algorithm is compared with a double-precision evaluation on MATLAB for performance analysis and error quantification. Implementation results of the proposed finite-precision OLTAE accelerator demonstrate the high-performance compute capabilities of the FPGA-based pose estimation while offering relative numerical errors below 7%.

arXiv:2210.08339공식 코드 · Papers with Code

Reachable Polyhedral Marching (RPM): An Exact Analysis Tool for Deep-Learned Control Systems

Neural networks are increasingly used in robotics as policies, state transition models, state estimation models, or all of the above. With these components being learned from data, it is important to be able to analyze what behaviors were learned and how this affects closed-loop performance. In this paper we take steps toward this goal by developing methods for computing control invariant sets and regions of attraction (ROAs) of dynamical systems represented as neural networks. We focus our attention on feedforward neural networks with the rectified linear unit (ReLU) activation, which are known to implement continuous piecewise-affine (PWA) functions. We describe the Reachable Polyhedral Marching (RPM) algorithm for enumerating the affine pieces of a neural network through an incremental connected walk. We then use this algorithm to compute exact forward and backward reachable sets, from which we provide methods for computing control invariant sets and ROAs. Our approach is unique in that we find these sets incrementally, without Lyapunov-based tools. In our examples we demonstrate the ability of our approach to find non-convex control invariant sets and ROAs on tasks with learned van der Pol oscillator and pendulum models. Further, we provide an accelerated algorithm for computing ROAs that leverages the incremental and connected enumeration of affine regions that RPM provides. We show this acceleration to lead to a 15x speedup in our examples. Finally, we apply our methods to find a set of states that are stabilized by an image-based controller for an aircraft runway control problem.

arXiv:2210.06947공식 코드 · Papers with Code

Decentralized State Estimation In A Dimension-Reduced Linear Regression

Decentralized state estimation in a communication-constrained sensor network is considered. The exchanged estimates are dimension-reduced to reduce the communication load using a linear mapping to a lower-dimensional space. The mean squared error optimal linear mapping depends on the particular estimation method used. Several dimension-reducing algorithms are proposed, where each algorithm corresponds to a commonly applied decentralized estimation method. All except one of the algorithms are shown to be optimal. For the remaining algorithm, we provide a convergence analysis where it is theoretically shown that this algorithm converges to a stationary point and numerically shown that the convergence rate is fast. A message-encoding solution is proposed that allows for efficient communication when using the proposed dimension reduction techniques. We also derive different properties from the proposed framework and show its superiority in relation to baseline methods. The applicability of the different algorithms is demonstrated using a simple fusion example and a more realistic target tracking scenario.