Ben Upcroft

Dynamical tunnelling of ultracold atoms

The divergence of quantum and classical descriptions of particle motion is clearly apparent in quantum tunnelling between two regions of classically stable motion. An archetype of such non-classical motion is tunnelling through an energy barrier. In the 1980s, a new process, ‘dynamical’ tunnelling, was predicted, involving no potential energy barrier; however, a constant of the motion (other than energy) still forbids classically the quantum-allowed motion. This process should occur, for example, in periodically driven, nonlinear hamiltonian systems with one degree of freedom. Such systems may be chaotic, consisting of regions in phase space of stable, regular motion embedded in a sea of chaos. Previous studies predicted dynamical tunnelling between these stable regions. Here we observe dynamical tunnelling of ultracold atoms from a Bose–Einstein condensate in an amplitude-modulated optical standing wave. Atoms coherently tunnel back and forth between their initial state of oscillatory motion (corresponding to an island of regular motion) and the state oscillating 180° out of phase with the initial state.

On the performance of ConvNet features for place recognition

After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields such as visual navigation and SLAM. Unfortunately, there are fundamental differences and challenges involved. Computer vision datasets are very different in character to robotic camera data, real-time performance is essential, and performance priorities can be different. This paper comprehensively evaluates and compares the utility of three state-of-the-art ConvNets on the problems of particular relevance to navigation for robots; viewpoint-invariance and condition-invariance, and for the first time enables real-time place recognition performance using ConvNets with large maps by integrating a variety of existing (locality-sensitive hashing) and novel (semantic search space partitioning) optimization techniques. We present extensive experiments on four real world datasets cultivated to evaluate each of the specific challenges in place recognition. The results demonstrate that speed-ups of two orders of magnitude can be achieved with minimal accuracy degradation, enabling real-time performance. We confirm that networks trained for semantic place categorization also perform better at (specific) place recognition when faced with severe appearance changes and provide a reference for which networks and layers are optimal for different aspects of the place recognition problem.

Place Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free

Place recognition has long been an incompletely solved problem in that all approaches involve significant compromises. Current methods address many but never all of the critical challenges of place recognition – viewpoint-invariance, condition-invariance and minimizing training requirements. Here we present an approach that adapts state-of-the-art object proposal techniques to identify potential landmarks within an image for place recognition. We use the astonishing power of convolutional neural network features to identify matching landmark proposals between images to perform place recognition over extreme appearance and viewpoint variations. Our system does not require any form of training, all components are generic enough to be used off-the-shelf. We present a range of challenging experiments in varied viewpoint and environmental conditions. We demonstrate superior performance to current state-of-the- art techniques. Furthermore, by building on existing and widely used recognition frameworks, this approach provides a highly compatible place recognition system with the potential for easy integration of other techniques such as object detection and semantic scene interpretation.

Scene Signatures: Localised and Point-less Features for Localisation

This paper is about localising across extreme lighting and weather conditions. We depart from the traditional point-feature-based approach as matching under dramatic appearance changes is a brittle and hard thing. Point feature detectors are fixed and rigid procedures which pass over an image examining small, low-level structure such as corners or blobs. They apply the same criteria applied all images of all places. This paper takes a contrary view and asks what is possible if instead we learn a bespoke detector for every place. Our localisation task then turns into curating a large bank of spatially indexed detectors and we show that this yields vastly superior performance in terms of robustness in exchange for a reduced but tolerable metric precision. We present an unsupervised system that produces broad-region detectors for distinctive visual elements, called scene signatures, which can be associated across almost all appearance changes. We show, using 21km of data collected over a period of 3 months, that our system is capable of producing metric localisation estimates from night-to-day or summer-to-winter conditions.

Decentralised particle filtering for multiple target tracking in wireless sensor networks

This paper presents algorithms for consistent joint localisation and tracking of multiple targets in wireless sensor networks under the decentralised data fusion (DDF) paradigm where particle representations of the state posteriors are communicated. This work differs from previous work as more generalised methods have been developed to account for correlated estimation errors that arise due to common past information between two discrete particle sets. The particle sets are converted to continuous distributions for communication and inter-nodal fusion. Common past information is then removed by a division operation of two estimates so that only new information is updated at the node. In previous work, the continuous distribution used was limited to a Gaussian kernel function. This new method is compared to the optimal centralised solution where each node sends all observation information to a central fusion node when received. Results presented include a real-time application of the DDF operation of division on data logged from field trials.

DeepFruits: A Fruit Detection System Using Deep Neural Networks

This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic platform; it is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed Faster Region-based CNN (Faster R-CNN). We adapt this model, through transfer learning, for the task of fruit detection using imagery obtained from two modalities: colour (RGB) and Near-Infrared (NIR). Early and late fusion methods are explored for combining the multi-modal (RGB and NIR) information. This leads to a novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0.807 to 0.838 for the detection of sweet pepper. In addition to improved accuracy, this approach is also much quicker to deploy for new fruits, as it requires bounding box annotation rather than pixel-level annotation (annotating bounding boxes is approximately an order of magnitude quicker to perform). The model is retrained to perform the detection of seven fruits, with the entire process taking four hours to annotate and train the new model per fruit.

Simple online and realtime tracking

This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is identified as a key factor influencing tracking performance, where changing the detector can improve tracking by up to 18.9%. Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers. Furthermore, due to the simplicity of our tracking method, the tracker updates at a rate of 260 Hz which is over 20x faster than other state-of-the-art trackers.

Consistent methods for Decentralised Data Fusion using Particle Filters

This paper presents two solutions for performing decentralised particle filtering in view of non-linear, non-Gaussian tracking in sensor networks. The issue is that no known methods exist to deal with correlated estimation errors due to common past information between two discrete particle sets. The first method transforms the particles to a Gaussian mixture model, the second approximates the set by a Parzen density estimate. Both of these representations accommodate consistent fusion and maintain accurate summaries of the particles. Requiring less bandwidth than particle representations, transformations to GMMs or Parzen representations for communication provide an added advantage. The accuracy in which the algorithms summarise the particle set, fusion methods and bandwidth requirements of each representation will be compared. Our results show that whilst less GMM components are required to summarise the sample statistics, the decentralised fusion solution using Parzen representations yields a more accurate result

Rich probabilistic representations for bearing only decentralised data fusion

The aim of this paper is to demonstrate the validity of using Gaussian mixture models (GMM) for representing probabilistic distributions in a decentralised data fusion (DDF) framework. GMMs are a powerful and compact stochastic representation allowing efficient communication of feature properties in large scale decentralised sensor networks. It will be shown that GMMs provide a basis for analytical solutions to the update and prediction operations for general Bayesian filtering. Furthermore, a variant on the covariance intersect algorithm for Gaussian mixtures will be presented ensuring a conservative update for the fusion of correlated information between two nodes in the network. In addition, purely visual sensory data will be used to show that decentralised data fusion and tracking of non-Gaussian states observed by multiple autonomous vehicles is feasible.

A decentralised particle filtering algorithm for multi-target tracking across multiple flight vehicles

This paper presents a decentralised particle filtering algorithm that enables multiple vehicles to jointly track 3D features under limited communication bandwidth. This algorithm, applied within a decentralised data fusion (DDF) framework, deals with correlated estimation errors due to common past information when fusing two discrete particle sets. Our solution is to transform the particles into Gaussian mixture models (GMMs) for communication and fusion. Not only can decentralised fusion be approximated by GMMs, but this representation also provides summaries of the particle set. Less bandwidth per communication step is required to communicate a GMM than the particle set itself hence conversion to GMMs for communication is an advantage. Real airborne data is used to demonstrate the accuracy of our decentralised particle filtering algorithm for airborne tracking and mapping