The robust estimation of dynamically changing features, such as the position of prey, is one of the hallmarks of perception. On an abstract, algorithmic level, nonlinear Bayesian filtering, i.e. the estimation of temporally changing signals based on the history of observations, provides a mathematical framework for dynamic perception in real time. Since the general, nonlinear filtering problem is analytically intractable, particle filters are considered among the most powerful approaches to approximating the solution numerically. Yet, these algorithms prevalently rely on importance weights, and thus it remains an unresolved question how the brain could implement such an inference strategy with a neuronal population. Here, we propose the Neural Particle Filter (NPF), a weight-less particle filter that can be interpreted as the neuronal dynamics of a recurrently connected neural network that receives feed-forward input from sensory neurons and represents the posterior probability distribution in terms of samples. Specifically, this algorithm bridges the gap between the computational task of online state estimation and an implementation that allows networks of neurons in the brain to perform nonlinear Bayesian filtering. The model captures not only the properties of temporal and multisensory integration according to Bayesian statistics, but also allows online learning with a maximum likelihood approach. With an example from multisensory integration, we demonstrate that the numerical performance of the model is adequate to account for both filtering and identification problems. Due to the weightless approach, our algorithm alleviates the 'curse of dimensionality' and thus outperforms conventional, weighted particle filters in higher dimensions for a limited number of particles.
State-space models (SSMs) are increasingly used in ecology to model time-series such as animal movement paths and population dynamics. This type of hierarchical model is often structured to account for two levels of variability: biological stochasticity and measurement error. SSMs are flexible. They can model linear and nonlinear processes using a variety of statistical distributions. Recent ecological SSMs are often complex, with a large number of parameters to estimate. Through a simulation study, we show that even simple linear Gaussian SSMs can suffer from parameter- and state-estimation problems. We demonstrate that these problems occur primarily when measurement error is larger than biological stochasticity, the condition that often drives ecologists to use SSMs. Using an animal movement example, we show how these estimation problems can affect ecological inference. Biased parameter estimates of a SSM describing the movement of polar bears (\textit{Ursus maritimus}) result in overestimating their energy expenditure. We suggest potential solutions, but show that it often remains difficult to estimate parameters. While SSMs are powerful tools, they can give misleading results and we urge ecologists to assess whether the parameters can be estimated accurately before drawing ecological conclusions from their results.
Few-shot object detection (FSOD) aims at learning a detector that can fast adapt to previously unseen objects with scarce annotated examples, which is challenging and demanding. Existing methods solve this problem by performing subtasks of classification and localization utilizing a shared component (e.g., RoI head) in the detector, yet few of them take the distinct preferences of two subtasks towards feature embedding into consideration. In this paper, we carefully analyze the characteristics of FSOD, and present that a general few-shot detector should consider the explicit decomposition of two subtasks, as well as leveraging information from both of them to enhance feature representations. To the end, we propose a simple yet effective Adaptive Fully-Dual Network (AFD-Net). Specifically, we extend Faster R-CNN by introducing Dual Query Encoder and Dual Attention Generator for separate feature extraction, and Dual Aggregator for separate model reweighting. Spontaneously, separate state estimation is achieved by the R-CNN detector. Besides, for the acquisition of enhanced feature representations, we further introduce Adaptive Fusion Mechanism to adaptively perform feature fusion in different subtasks. Extensive experiments on PASCAL VOC and MS COCO in various settings show that, our method achieves new state-of-the-art performance by a large margin, demonstrating its effectiveness and generalization ability.
Assembly state detection, i.e., object state detection, has a critical meaning in computer vision tasks, especially in AR assisted assembly. Unlike other object detection problems, the visual difference between different object states can be subtle. For the better learning of such subtle appearance difference, we proposed a two-level group attention module (TGA), which consists of inter-group attention and intro-group attention. The relationship between feature groups as well as the representation within each feature group is simultaneously enhanced. We embedded the proposed TGA module in a popular object detector and evaluated it on two new datasets related to object state estimation. The result shows that our proposed attention module outperforms the baseline attention module.
State estimation plays a key role in the transition from the passive to the active operation of distribution systems, as it allows to monitor these networks and, successively, to perform control actions. However, designing state estimators for distribution systems carries a significant amount of challenges. This is due to the physical complexity of the networks, e.g., phase unbalance, and limited measurements. Furthermore, the features of the distribution system present significant local variations, e.g., voltage level and number and type of customers, which makes it hard to design a "one-size-fits-all" state estimator. The present paper introduces a unifying framework that allows to easily implement and compare diverse unbalanced static state estimation models. This is achieved by formulating state estimation as a general constrained optimization problem. The advantages of this approach are described and supported by numerical illustration on a large set of distribution feeders. The framework is also implemented and made available open-source.
Collaborative object localization aims to collaboratively estimate locations of objects observed from multiple views or perspectives, which is a critical ability for multi-agent systems such as connected vehicles. To enable collaborative localization, several model-based state estimation and learning-based localization methods have been developed. Given their encouraging performance, model-based state estimation often lacks the ability to model the complex relationships among multiple objects, while learning-based methods are typically not able to fuse the observations from an arbitrary number of views and cannot well model uncertainty. In this paper, we introduce a novel spatiotemporal graph filter approach that integrates graph learning and model-based estimation to perform multi-view sensor fusion for collaborative object localization. Our approach models complex object relationships using a new spatiotemporal graph representation and fuses multi-view observations in a Bayesian fashion to improve location estimation under uncertainty. We evaluate our approach in the applications of connected autonomous driving and multiple pedestrian localization. Experimental results show that our approach outperforms previous techniques and achieves the state-of-the-art performance on collaboration localization.
Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to obtain. In this paper, we explore a method that facilitates learning object manipulation skills directly from videos. Leveraging recent advances in 2D visual recognition and differentiable rendering, we develop an optimization based method to estimate a coarse 3D state representation for the hand and the manipulated object(s) without requiring any supervision. We use these trajectories as dense rewards for an agent that learns to mimic them through reinforcement learning. We evaluate our method on simple single- and two-object actions from the Something-Something dataset. Our approach allows an agent to learn actions from single videos, while watching multiple demonstrations makes the policy more robust. We show that policies learned in a simulated environment can be easily transferred to a real robot.
Recent advances in incorporating neural networks into particle filters provide the desired flexibility to apply particle filters in large-scale real-world applications. The dynamic and measurement models in this framework are learnable through the differentiable implementation of particle filters. Past efforts in optimising such models often require the knowledge of true states which can be expensive to obtain or even unavailable in practice. In this paper, in order to reduce the demand for annotated data, we present an end-to-end learning objective based upon the maximisation of a pseudo-likelihood function which can improve the estimation of states when large portion of true states are unknown. We assess performance of the proposed method in state estimation tasks in robotics with simulated and real-world datasets.
Time-synchronized state estimation is a challenge for distribution systems because of limited real-time observability. This paper addresses this challenge by formulating a deep learning (DL)-based approach to perform unbalanced three-phase distribution system state estimation (DSSE). Initially, a data-driven approach for judicious measurement selection to facilitate reliable state estimation is provided. Then, a deep neural network (DNN) is trained to perform DSSE for systems that are incompletely observed by synchrophasor measurement devices (SMDs). Robustness of the proposed methodology is demonstrated by considering realistic measurement error models for SMDs. A comparative study of the DNN-based DSSE with classical linear state estimation indicates that the DL-based approach gives better accuracy with a significantly smaller number of SMDs.
Wireless sensor network has recently received much attention due to its broad applicability and ease-of-installation. This paper is concerned with a distributed state estimation problem, where all sensor nodes are required to achieve a consensus estimation. The weighted least squares (WLS) estimator is an appealing way to handle this problem since it does not need any prior distribution information. To this end, we first exploit the equivalent relation between the information filter and WLS estimator. Then, we establish an optimization problem under the relation coupled with a consensus constraint. Finally, the consensus-based distributed WLS problem is tackled by the alternating direction method of multiplier (ADMM). Numerical simulation together with theoretical analysis testify the convergence and consensus estimations between nodes.
In this paper, a novel approach to the output-feedback inverse reinforcement learning (IRL) problem is developed by casting the IRL problem, for linear systems with quadratic cost functions, as a state estimation problem. Two observer-based techniques for IRL are developed, including a novel observer method that re-uses previous state estimates via history stacks. Theoretical guarantees for convergence and robustness are established under appropriate excitation conditions. Simulations demonstrate the performance of the developed observers and filters under noisy and noise-free measurements.
The advancements in connected and autonomous vehicles in these times demand the availability of tools providing the agents with the capability to be aware and predict their own states and context dynamics. This article presents a novel approach to develop an initial level of collective awareness in a network of intelligent agents. A specific collective self awareness functionality is considered, namely, agent centered detection of abnormal situations present in the environment around any agent in the network. Moreover, the agent should be capable of analyzing how such abnormalities can influence the future actions of each agent. Data driven dynamic Bayesian network (DBN) models learned from time series of sensory data recorded during the realization of tasks (agent network experiences) are here used for abnormality detection and prediction. A set of DBNs, each related to an agent, is used to allow the agents in the network to each synchronously aware possible abnormalities occurring when available models are used on a new instance of the task for which DBNs have been learned. A growing neural gas (GNG) algorithm is used to learn the node variables and conditional probabilities linking nodes in the DBN models; a Markov jump particle filter (MJPF) is employed for state estimation and abnormality detection in each agent using learned DBNs as filter parameters. Performance metrics are discussed to asses the algorithms reliability and accuracy. The impact is also evaluated by the communication channel used by the network to share the data sensed in a distributed way by each agent of the network. The IEEE 802.11p protocol standard has been considered for communication among agents. Real data sets are also used acquired by autonomous vehicles performing different tasks in a controlled environment.
This paper presents a novel approach to detect abnormalities in dynamic systems based on multisensory data and feature selection. The proposed method produces multiple inference models by considering several features of the observed data. This work facilitates the obtainment of the most precise features for predicting future instances and detecting abnormalities. Growing neural gas (GNG) is employed for clustering multisensory data into a set of nodes that provide a semantic interpretation of data and define local linear models for prediction purposes. Our method uses a Markov Jump particle filter (MJPF) for state estimation and abnormality detection. The proposed method can be used for selecting the optimal set features to be shared in networking operations such that state prediction, decision-making, and abnormality detection processes are favored. This work is evaluated by using a real dataset consisting of a moving vehicle performing some tasks in a controlled environment.
In this paper, we consider the state estimation problem for nonlinear stochastic discrete-time systems. We combine Lyapunov's method in control theory and deep reinforcement learning to design the state estimator. We theoretically prove the convergence of the bounded estimate error solely using the data simulated from the model. An actor-critic reinforcement learning algorithm is proposed to learn the state estimator approximated by a deep neural network. The convergence of the algorithm is analysed. The proposed Lyapunov-based reinforcement learning state estimator is compared with a number of existing nonlinear filtering methods through Monte Carlo simulations, showing its advantage in terms of estimate convergence even under some system uncertainties such as covariance shift in system noise and randomly missing measurements. To the best of our knowledge, this is the first reinforcement learning based nonlinear state estimator with bounded estimate error performance guarantee.
Estimating accurate forward and inverse dynamics models is a crucial component of model-based control for sophisticated robots such as robots driven by hydraulics, artificial muscles, or robots dealing with different contact situations. Analytic models to such processes are often unavailable or inaccurate due to complex hysteresis effects, unmodelled friction and stiction phenomena,and unknown effects during contact situations. A promising approach is to obtain spatio-temporal models in a data-driven way using recurrent neural networks, as they can overcome those issues. However, such models often do not meet accuracy demands sufficiently, degenerate in performance for the required high sampling frequencies and cannot provide uncertainty estimates. We adopt a recent probabilistic recurrent neural network architecture, called Re-current Kalman Networks (RKNs), to model learning by conditioning its transition dynamics on the control actions. RKNs outperform standard recurrent networks such as LSTMs on many state estimation tasks. Inspired by Kalman filters, the RKN provides an elegant way to achieve action conditioning within its recurrent cell by leveraging additive interactions between the current latent state and the action variables. We present two architectures, one for forward model learning and one for inverse model learning. Both architectures significantly outperform exist-ing model learning frameworks as well as analytical models in terms of prediction performance on a variety of real robot dynamics models.
This paper presents a generic motion model to capture mobile robots' dynamic behaviors (translation and rotation). The model is based on statistical models driven by white random processes and is formulated into a full state estimation algorithm based on the error-state extended Kalman filtering framework (ESEKF). Major benefits of this method are its versatility, being applicable to different robotic systems without accurately modeling the robots' specific dynamics, and ability to estimate the robot's (angular) acceleration, jerk, or higher-order dynamic states with low delay. Mathematical analysis with numerical simulations are presented to show the properties of the statistical model-based estimation framework and to reveal its connection to existing low-pass filters. Furthermore, a new paradigm is developed for robots observability analysis by developing Lie derivatives and associated partial differentiation directly on manifolds. It is shown that this new paradigm is much simpler and more natural than existing methods based on quaternion parameterizations. It is also scalable to high dimensional systems. A novel \textbf{\textit{thin}} set concept is introduced to characterize the unobservable subset of the system states, providing the theoretical foundation to observability analysis of robotic systems operating on manifolds and in high dimension. Finally, extensive experiments including full state estimation and extrinsic calibration (both POS-IMU and IMU-IMU) on a quadrotor UAV, a handheld platform and a ground vehicle are conducted. Comparisons with existing methods show that the proposed method can effectively estimate all extrinsic parameters, the robot's translation/angular acceleration and other state variables (e.g., position, velocity, attitude) of high accuracy and low delay.
Real-time state estimation and forecasting is critical for efficient operation of power grids. In this paper, a physics-informed Gaussian process regression (PhI-GPR) method is presented and used for probabilistic forecasting and estimating the phase angle, angular speed, and wind mechanical power of a three-generator power grid system using sparse measurements. In standard data-driven Gaussian process regression (GPR), parameterized models for the prior statistics are fit by maximizing the marginal likelihood of observed data, whereas in PhI-GPR, we compute the prior statistics by solving stochastic equations governing power grid dynamics. The short-term forecast of a power grid system dominated by wind generation is complicated by the stochastic nature of the wind and the resulting uncertain mechanical wind power. Here, we assume that the power-grid dynamic is governed by the swing equations, and we treat the unknown terms in the swing equations (specifically, the mechanical wind power) as random processes, which turns these equations into stochastic differential equations. We solve these equations for the mean and variance of the power grid system using the Monte Carlo simulations method. We demonstrate that the proposed PhI-GPR method can accurately forecast and estimate both observed and unobserved states, including the mean behavior and associated uncertainty. For observed states, we show that PhI-GPR provides a forecast comparable to the standard data-driven GPR, with both forecasts being significantly more accurate than the autoregressive integrated moving average (ARIMA) forecast. We also show that the ARIMA forecast is much more sensitive to observation frequency and measurement errors than the PhI-GPR forecast.
A goal-oriented visual dialogue involves multi-turn interactions between two agents, Questioner and Oracle. During which, the answer given by Oracle is of great significance, as it provides golden response to what Questioner concerns. Based on the answer, Questioner updates its belief on target visual content and further raises another question. Notably, different answers drive into different visual beliefs and future questions. However, existing methods always indiscriminately encode answers after much longer questions, resulting in a weak utilization of answers. In this paper, we propose an Answer-Driven Visual State Estimator (ADVSE) to impose the effects of different answers on visual states. First, we propose an Answer-Driven Focusing Attention (ADFA) to capture the answer-driven effect on visual attention by sharpening question-related attention and adjusting it by answer-based logical operation at each turn. Then based on the focusing attention, we get the visual state estimation by Conditional Visual Information Fusion (CVIF), where overall information and difference information are fused conditioning on the question-answer state. We evaluate the proposed ADVSE to both question generator and guesser tasks on the large-scale GuessWhat?! dataset and achieve the state-of-the-art performances on both tasks. The qualitative results indicate that the ADVSE boosts the agent to generate highly efficient questions and obtains reliable visual attentions during the reasonable question generation and guess processes.
Nowadays, the prevalence of sensor networks has enabled tracking of the states of dynamic objects for a wide spectrum of applications from autonomous driving to environmental monitoring and urban planning. However, tracking real-world objects often faces two key challenges: First, due to the limitation of individual sensors, state estimation needs to be solved in a collaborative and distributed manner. Second, the objects' movement behavior is unknown, and needs to be learned using sensor observations. In this work, for the first time, we formally formulate the problem of simultaneous state estimation and behavior learning in a sensor network. We then propose a simple yet effective solution to this new problem by extending the Gaussian process-based Bayes filters (GP-BayesFilters) to an online, distributed setting. The effectiveness of the proposed method is evaluated on tracking objects with unknown movement behaviors using both synthetic data and data collected from a multi-robot platform.
Phasor measurement units (PMUs) provide high-fidelity data that improve situation awareness of electric power grid operations. PMU datastreams inform wide-area state estimation, monitor area control error, and facilitate event detection in real time. As PMU data become more available and increasingly reliable, these devices are found in new roles within control systems, such as remedial action schemes and early warning detection systems. As with other cyber physical systems, maintaining data integrity and security pose a significant challenge for power system operators. In this paper, we present a comprehensive analysis of multiple machine learning techniques to detect malicious data injection within PMU data streams. The two datasets used in this study come from two PMU networks: an inter-university, research-grade distribution network spanning three institutions in the U.S. Pacific Northwest, and a utility transmission network from the Bonneville Power Administration. We implement the detection algorithms with TensorFlow, an open-source software library for machine learning, and the results demonstrate potential for distributing the training workload and achieving higher performance, while maintaining effectiveness in the detection of spoofed data.