Autonomous path planning for radar and sonar sensing faces significant challenges arising from dynamic targets, obstacle occlusions, and low signal-to-noise (SNR) conditions. We propose a hierarchical sensor scheduling framework that combines a long-horizon strategic planner, based on the Rapidly-exploring Random Tree star (RRT*) algorithm, with a fast-adapting tactical planner. Efficient coordination of the two planners is achieved via a novel message passing mechanism, enabling guidance of the sensor out of complex environments while maintaining effective target tracking. Additionally, we introduce an RRT* rerooting strategy that significantly reduces computation time and so expedites the update of the strategic plan. Extensive simulation results demonstrate that our proposed fusion approach outperforms conventional stand-alone short-term and long-term planners in challenging scenarios and low-SNR regimes,

We present a sensor scheduling algorithm to plan the motion of multiple autonomous platforms for cooperative tracking of targets within a region that contains obstacles and occlusions. The platforms have kinematic constraints and their sensors have restricted field of view and range. The proposed algorithm is a variant of the Rapidly exploring Random Tree star algorithm (RRT*) that has been adapted to the problem of determining paths for multiple independent kinematically constrained platforms to optimise their tracking performance. To guide the scheduling algorithm, we define a tracking cost based on the Posterior Cramér Rao Bound (PCRB) derived from the predicted positions of the platforms and targets. Through simulations of generated paths, we show that the algorithm generates rational plans for tracking targets and that the tracking cost accurately predicts the realised performance of the platforms.

Probabilistic logics combine the ability to reason about complex scenes, with a rigorous approach to uncertainty. This paper explores the construction of probabilistic spatial logics through the combination of established qualitative spatial calculi together with Markov logic networks (MLNs). Qualitative spatial calculi provide the basis for automated representation and reasoning with complex spatial scenes; MLNs provide a rigorous basis for handling uncertainty and driving probabilistic inference. Our approach focuses specifically on the combination of an uncertain knowledge base with a certain spatial reasoning rule-base. The experiments explore how uncertain knowledge propagates through certain qualitative spatial inferences, using the specific example of reasoning with cardinal directions. The results provide a template for probabilistic qualitative spatial reasoning more generally, with applications to a wide range of common scenarios for situational awareness and automated reasoning under uncertainty.

Hidden Markov Chains (HMCs) and, more recently, Hidden semi-Markov Chains (HsMCs) have been used by several groups of researchers to provide a model for indoor localization. A homogeneous HMC is completely determined by the state initial probability vector and the state transition probability matrix. This is also true for the HsMC provided the state duration probability is given. These parameters are often chosen heuristically but when sufficient measurement training data are available, they can be learned using the well-known Baum-Welch algorithm. Given the model parameters, approaches such as the forward-only algorithm, the forward-backwards algorithm and the Viterbi algorithm can be applied for state sequence inference under the HMC/HsMC framework. In indoor localization applications, there is often insufficient prior information to specify such parameters in advance of the application and they have to be learned from limited amounts of training data. In this paper, we endeavour to evaluate the parameter learning accuracy of the Baum-Welch algorithm using varying amounts of training data, and evaluate the influence of applying inaccurate model parameters on these typical state estimation algorithms under both the HMC and HsMC frameworks. All of the evaluations are based on received signal strength (RSS) for application to indoor localization.

Sonobuoy fields, comprising a network of sonar transmitters and receivers, are used to find and track underwater targets. For a given environment and sonobuoy field layout, the performance of such a field depends on the scheduling, that is, deciding which source should transmit, and which waveform should be transmitted at any given time. In this paper, we explore the choice of cost function used in myopic scheduling and its effect on tracking performance. Specifically, we consider 5 different cost functions derived from the predicted error covariance matrix of the track. Importantly, our cost functions combine both positional and velocity covariance information to allow the scheduler to choose the optimum source-waveform action. Using realistic multistatic sonobuoy simulations, we demonstrate that each cost function results in a different choice of source-waveform actions, which in turn affects the performance of the scheduler. In particular, we show there is a trade-off between position and velocity error performance such that no one cost function is superior in both.

This paper considers the joint recursive estimation of the dynamic state and the time-varying process noise covariance for a linear state space model. The conjugate prior on the process noise covariance, the inverse Wishart distribution, provides a latent variable. A variational Bayesian inference framework is then adopted to iteratively estimate the posterior density functions of the dynamic state, process noise covariance and the introduced latent variable. The performance of the algorithm is demonstrated with simulated data in a target tracking application.

Doppler radars are low cost and light weight sensors that have a potential to find wide applications in building a large team of mobile vehicle platforms. Because of the nonlinearity associated with the measurement from Doppler radars, it is both interesting and challenging to extract meaningful information from the low cost sensors. Building upon the authors' previous work on self localization with a feature-based map with known landmark associations using Doppler radars and an Extended Kalman Filter (EKF), this paper investigates the effects of positioning and the number of landmarks in a feature-based map on the accuracy of the position estimation of a robot. The computations of Cramer-Rao Lower Bound (CRLB) at the terminating sample show that the CRLB has a drastic reduction when the number of landmarks is increased from 1 to 2 while the root mean square errors (RMSE) of EKF indicate a gradual error reduction for the first 4 landmarks. The results presented in this paper will provide an essential guideline on the experiment design for feature-based robot self-localization.

This paper describes the implementation of a miniature open-source and cost-effective SLAM-robot, utilizing a novel occupancy-grid SLAM algorithm based on the concept of random-finite-sets (RFS). This robotic platform is remotely controlled to move and scan unknown environments using a differential drive system algorithm, sending instantaneous position feedback to the remote operator. The mobile robot utilizes a LIDAR-Lite 2 laser range finder to map the environment while simultaneously estimating its position and orientation within the map. Even though there are many mobile robots that implement this behavior, the main advantage in this proposed robotic platform is modeling of LIDAR measurements at each scan as a RFS. This model provides robustness against the random count of received returns, due to false and missed detections, allowing the use of an inexpensive LIDAR sensor and commercial off the shelf hardware.

In this paper, we investigate cooperative passive sensor trajectory planning for tracking a target where the tracking error is sensor trajectory dependent. We consider the problem under a scenario of tracking a moving target using two unmanned bearings-only sensors. The basic idea is to maximise the target information acquired from the processing measurements of the two sensors by cooperatively scheduling their future trajectories at which sensor measurements will be taken. In the literature this problem is modeled by a partially observed Markov decision process and optimal action which maximises an expected reward function is sought. Three reward functions, namely, the Expected Reward, the Determinant, and Trace of the associated Fisher Information Matrix (FIM) for the underlying problem are analysed and discussed. These rewards may only be evaluated practically through various approximations. We show that the correlation between two sensor states is weakened significantly for the Expected Reward due to linearisation and thus the closed-form Expected Reward as well as the Trace of FIM are inappropriate for this sensor trajectory scheduling problem. Finally, we present simulation results which are based on the example of a non-cooperative target chasing via two cooperative bearing-only sensors.

Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) are the two popular techniques in the context of dimensionality reduction and classification. By extracting discriminant features, LDA is optimal when the distributions of the features for each class are unimodal and separated by the scatter of means. On the other hand, PCA extract descriptive features which helps itself to outperform LDA in some classification tasks and less sensitive to different training data sets. The idea of Parametric Subspace Analysis (PSA) proposed in this paper is to include a parameter for regulating the combination of PCA and LDA. By combining descriptive (of PCA) and discriminant (of LDA) features, a better performance for dimensionality reduction and classification tasks is obtained with PSA and can be seen via our experimental results.

An algorithm is developed for joint tracking and detection of multiple maneuvering targets using a wireless sensor network. The target existence probability framework is adopted in which a collection of tentative tracks, each characterised by a posterior density and existence probability, is maintained. Track state posterior densities are approximated using the unscented Kalman filter and the interacting multiple model algorithm. The advantage of this approach compared to particle filter- based approaches is that it enables more computationally efficient tracking of multiple targets. The performance of the algorithm is examined as a function of signal-to-noise ratio and the number of bits per observation for a scenario involving three maneuvering targets. Good performance is achieved in all cases considered.

In this paper we consider state estimation problems where there are multiple independent processes evolving but the estimation scheme can only select a limited set of processes to measure at each time step. Within a Gauss-Markov framework, we show the optimality of a scheduling scheme under various scenarios. These types of problems are common in sensor scheduling applications

Networks of small low-cost sensors for target tracking are becoming increasingly important for many applications. A major problem is that these small sensors usually have limited observability due to power constraints and the transition between sensor observation and target states is nonlinear. As a consequence, nonlinear filtering techniques, such as particle filtering, are often chosen by researchers in this context. We focus on a network of sensors where each sensor provides binary data at each epoch: target present or target absent. At this point it is not clear that existing approaches can effectively handle the tracking of multiple targets using such networks. In addition, algorithmic computational complexity is an issue if particle filters are used. In this paper, we present a new method, the virtual measurement (VM) approach, for multi-target tracking using distributed binary sensor networks. The central idea of this approach is to define a mapping between the space of binary sensor observations and the so-called VM space, such that, any point within a VM space is a transform of the target state, as if it were generated by an equivalent "large sensor". With VMs, conventional multi-target tracking (MTT) algorithms can be used in a straightforward way for tracking multiple targets over the sensing field of binary sensor networks. Computer simulated examples of MTT demonstrate the effectiveness and robustness of the VM approach