Timothy L. Molloy

Jasmin James, Jason J. Ford, Timothy L. Molloy

In this paper we consider the problem of quickly detecting changes in an intermittent signal that can (repeatedly) switch between a normal and an anomalous state. We pose this intermittent signal detection problem as an optimal stopping problem and establish a quickest intermittent signal detection (ISD) rule with a threshold structure. We develop bounds to characterise the performance of our ISD rule and establish a new filter for estimating its detection delays. Finally, we examine the performance of our ISD rule in both a simulation study and an important vision based aircraft detection application where the ISD rule demonstrates improvements in detection range and false alarm rates relative to the current state of the art aircraft detection techniques.

Yitian Chen, Timothy L. Molloy, Tyler Summers et al.

In this paper, we propose and analyze a new method for online linear quadratic regulator (LQR) control with a priori unknown time-varying cost matrices. The cost matrices are revealed sequentially with the potential for future values to be previewed over a short window. Our novel method involves using the available cost matrices to predict the optimal trajectory, and a tracking controller to drive the system towards it. We adopted the notion of dynamic regret to measure the performance of this proposed online LQR control method, with our main result being that the (dynamic) regret of our method is upper bounded by a constant. Moreover, the regret upper bound decays exponentially with the preview window length, and is extendable to systems with disturbances. We show in simulations that our proposed method offers improved performance compared to other previously proposed online LQR methods.

Jason J. Ford, Jasmin James, Timothy L. Molloy

This paper provides the first description of a weak practical super-martingale phenomenon that can emerge in the test statistic in Shiryaev's Bayesian quickest change detection (QCD) problem. We establish that this super-martingale phenomenon can emerge under a condition on the relative entropy between pre and post change densities when the measurements are insufficiently informative to overcome the change time's geometric prior. We illustrate this super-martingale phenomenon in a simple Bayesian QCD problem which highlights the unsuitability of Shiryaev's test statistic for detecting subtle change events.

Jasmin James, Jason J. Ford, Timothy L. Molloy

Unmanned aerial vehicle (UAV) operations are steadily expanding into many important applications. A key technology for better enabling their commercial use is an onboard sense and avoid (SAA) technology which can detect potential mid-air collision threats in the same manner expected from a human pilot. Ideally, aircraft should be detected as early as possible whilst maintaining a low false alarm rate, however, textured clouds and other unstructured terrain make this trade-off a challenge. In this paper we present a new technique for the modelling and detection of aircraft above the horizon that is able to penalise non-aircraft artefacts (such as textured clouds and other unstructured terrain). We evaluate the performance of our proposed system on flight data of a Cessna 172 on a near collision course encounter with a ScanEagle UAV data collection aircraft. By penalising non-aircraft artefacts we are able to demonstrate, for a zero false alarm rate, a mean detection range of 2445m corresponding to an improvement in detection ranges by 9.8% (218m).

Philipp Braun, Timothy L. Molloy, Gal Barkai et al.

Solutions to pursuit-evasion and surveillance-evasion differential games are typically computed and expressed using open-loop representations, with the synthesis of feedback strategies significantly less common. We propose a numerical scheme for obtaining feedback strategies for the recently introduced prying-pedestrian surveillance-evasion differential game. The scheme involves computing feedback strategies as input-output maps approximated via neural networks trained using data obtained from open-loop representations of solutions. Simulations show the effectiveness of neural networks trained with an appropriate learning-loss function. Since optimal feedback strategies are discontinuous, as a second contribution, the potential loss/gain of individual players is subsequently studied for players using sample-and-hold feedback compared to continuous-time feedback.

Olivia Dry, Timothy L. Molloy, Wanxin Jin et al.

We propose Zeroth-Order Random Matrix Search for Learning from Demonstrations (ZORMS-LfD). ZORMS-LfD enables the costs, constraints, and dynamics of constrained optimal control problems, in both continuous and discrete time, to be learned from expert demonstrations without requiring smoothness of the learning-loss landscape. In contrast, existing state-of-the-art first-order methods require the existence and computation of gradients of the costs, constraints, dynamics, and learning loss with respect to states, controls and/or parameters. Most existing methods are also tailored to discrete time, with constrained problems in continuous time receiving only cursory attention. We demonstrate that ZORMS-LfD matches or surpasses the performance of state-of-the-art methods in terms of both learning loss and compute time across a variety of benchmark problems. On unconstrained continuous-time benchmark problems, ZORMS-LfD achieves similar loss performance to state-of-the-art first-order methods with an over $80$\% reduction in compute time. On constrained continuous-time benchmark problems where there is no specialized state-of-the-art method, ZORMS-LfD is shown to outperform the commonly used gradient-free Nelder-Mead optimization method.

Timothy L. Molloy, Girish N. Nair

We investigate partially observed Markov decision processes (POMDPs) with cost functions regularized by entropy terms describing state, observation, and control uncertainty. Standard POMDP techniques are shown to offer bounded-error solutions to these entropy-regularized POMDPs, with exact solutions possible when the regularization involves the joint entropy of the state, observation, and control trajectories. Our joint-entropy result is particularly surprising since it constitutes a novel, tractable formulation of active state estimation.

Timothy L. Molloy, Girish N. Nair

We study the problem of controlling a partially observed Markov decision process (POMDP) to either aid or hinder the estimation of its state trajectory. We encode the estimation objectives via the smoother entropy, which is the conditional entropy of the state trajectory given measurements and controls. Consideration of the smoother entropy contrasts with previous approaches that instead resort to marginal (or instantaneous) state entropies due to tractability concerns. By establishing novel expressions for the smoother entropy in terms of the POMDP belief state, we show that both the problems of minimising and maximising the smoother entropy in POMDPs can surprisingly be reformulated as belief-state Markov decision processes with concave cost and value functions. The significance of these reformulations is that they render the smoother entropy a tractable optimisation objective, with structural properties amenable to the use of standard POMDP solution techniques for both active estimation and obfuscation. Simulations illustrate that optimisation of the smoother entropy leads to superior trajectory estimation and obfuscation compared to alternative approaches.

Timothy L. Molloy, Tobias Fischer, Michael Milford et al.

A key challenge in visual place recognition (VPR) is recognizing places despite drastic visual appearance changes due to factors such as time of day, season, weather or lighting conditions. Numerous approaches based on deep-learnt image descriptors, sequence matching, domain translation, and probabilistic localization have had success in addressing this challenge, but most rely on the availability of carefully curated representative reference images of the possible places. In this paper, we propose a novel approach, dubbed Bayesian Selective Fusion, for actively selecting and fusing informative reference images to determine the best place match for a given query image. The selective element of our approach avoids the counterproductive fusion of every reference image and enables the dynamic selection of informative reference images in environments with changing visual conditions (such as indoors with flickering lights, outdoors during sunshowers or over the day-night cycle). The probabilistic element of our approach provides a means of fusing multiple reference images that accounts for their varying uncertainty via a novel training-free likelihood function for VPR. On difficult query images from two benchmark datasets, we demonstrate that our approach matches and exceeds the performance of several alternative fusion approaches along with state-of-the-art techniques that are provided with prior (unfair) knowledge of the best reference images. Our approach is well suited for long-term robot autonomy where dynamic visual environments are commonplace since it is training-free, descriptor-agnostic, and complements existing techniques such as sequence matching.

Jasmin James, Jason J. Ford, Timothy L. Molloy

Commercial operation of unmanned aerial vehicles (UAVs) would benefit from an onboard ability to sense and avoid (SAA) potential mid-air collision threats. In this paper we present a new approach for detection of aircraft below the horizon. We address some of the challenges faced by existing vision-based SAA methods such as detecting stationary aircraft (that have no relative motion to the background), rejecting moving ground vehicles, and simultaneous detection of multiple aircraft. We propose a multi-stage, vision-based aircraft detection system which utilises deep learning to produce candidate aircraft that we track over time. We evaluate the performance of our proposed system on real flight data where we demonstrate detection ranges comparable to the state of the art with the additional capability of detecting stationary aircraft, rejecting moving ground vehicles, and tracking multiple aircraft.