arXiv subjects

Robert Mahony

Publications and source records attributed to Robert Mahony.

At least 73 records · Page 4Linked to original sources

arXiv2021

Attitude Observation for Second Order Attitude Kinematics

This paper addresses the problem of estimating the attitude and angular velocity of a rigid object by exploiting its second order kinematic model. The approach is particularly useful in cases where angular velocity measurements are not available and the attitude and angular velocity of an object need to be estimated from accelerometers and magnetometers. We propose a novel sensor modality that uses multiple accelerometers to measure the angular acceleration of an object as well as using magnetometers to measure partial attitude. We extend the approach of equivariant observer design to second order attitude kinematics by demonstrating that the special Euclidean group acts as a symmetry group on the system considered. The observer design is based on the lifted kinematics and we prove almost global asymptotic stability and local uniform exponential stability of the estimation error. The performance of the observer is demonstrated in simulation.

eess.SY↗

arXiv2021

Inertial Collaborative Localisation for Autonomous Vehicles using a Minimum Energy Filter

Collaborative Localisation has been studied extensively in recent years as a way to improve pose estimation of unmanned aerial vehicles in challenging environments. However little attention has been paid toward advancing the underlying filter design beyond standard Extended Kalman Filter-based approaches. In this paper, we detail a discrete-time collaborative localisation filter using the deterministic minimum-energy framework. The filter incorporates measurements from an inertial measurement unit and models the effects of sensor bias and gravitational acceleration. We present a simulation based on real-world vehicle trajectories and IMU data that demonstrates how collaborative localisation can improve performance over single-vehicle methods.

cs.RO↗

arXiv2021

An Equivariant Filter for Visual Inertial Odometry

Visual Inertial Odometry (VIO) is of great interest due the ubiquity of devices equipped with both a monocular camera and Inertial Measurement Unit (IMU). Methods based on the extended Kalman Filter remain popular in VIO due to their low memory requirements, CPU usage, and processing time when compared to optimisation-based methods. In this paper, we analyse the VIO problem from a geometric perspective and propose a novel formulation on a smooth quotient manifold where the equivalence relationship is the well-known invariance of VIO to choice of reference frame. We propose a novel Lie group that acts transitively on this manifold and is compatible with the visual measurements. This structure allows for the application of Equivariant Filter (EqF) design leading to a novel filter for the VIO problem. Combined with a very simple vision processing front-end, the proposed filter demonstrates state-of-the-art performance on the EuRoC dataset compared to other EKF-based VIO algorithms.

cs.RO↗

arXiv2021

Iterative Optimisation with an Innovation CNN for Pose Refinement

Object pose estimation from a single RGB image is a challenging problem due to variable lighting conditions and viewpoint changes. The most accurate pose estimation networks implement pose refinement via reprojection of a known, textured 3D model, however, such methods cannot be applied without high quality 3D models of the observed objects. In this work we propose an approach, namely an Innovation CNN, to object pose estimation refinement that overcomes the requirement for reprojecting a textured 3D model. Our approach improves initial pose estimation progressively by applying the Innovation CNN iteratively in a stochastic gradient descent (SGD) framework. We evaluate our method on the popular LINEMOD and Occlusion LINEMOD datasets and obtain state-of-the-art performance on both datasets.

cs.CV↗

arXiv2020

Event Camera Calibration of Per-pixel Biased Contrast Threshold

Event cameras output asynchronous events to represent intensity changes with a high temporal resolution, even under extreme lighting conditions. Currently, most of the existing works use a single contrast threshold to estimate the intensity change of all pixels. However, complex circuit bias and manufacturing imperfections cause biased pixels and mismatch contrast threshold among pixels, which may lead to undesirable outputs. In this paper, we propose a new event camera model and two calibration approaches which cover event-only cameras and hybrid image-event cameras. When intensity images are simultaneously provided along with events, we also propose an efficient online method to calibrate event cameras that adapts to time-varying event rates. We demonstrate the advantages of our proposed methods compared to the state-of-the-art on several different event camera datasets.

cs.CV↗

arXiv2020

A Minimum Energy Filter for Localisation of an Unmanned Aerial Vehicle

Accurate localisation of unmanned aerial vehicles is vital for the next generation of automation tasks. This paper proposes a minimum energy filter for velocity-aided pose estimation on the extended special Euclidean group. The approach taken exploits the Lie-group symmetry of the problem to combine Inertial Measurement Unit (IMU) sensor output with landmark measurements into a robust and high performance state estimate. We propose an asynchronous discrete-time implementation to fuse high bandwidth IMU with low bandwidth discrete-time landmark measurements typical of real-world scenarios. The filter's performance is demonstrated by simulation.

eess.SY↗

arXiv2020

Equivariant Filter Design for Kinematic Systems on Lie Groups

It is known that invariance and equivariance properties for systems on Lie groups can be exploited in the design of high performance and robust observers and filters for real-world robotic systems. This paper proposes an analysis framework that allows any kinematic system on a Lie group to be embedded in a natural manner into an equivariant kinematic system. This framework allows us to characterise the properties of, and relationships between, invariant systems, group affine systems, and equivariant systems. We propose a new filter design, the Equivariant Filter (EqF), that exploits the equivariance properties of the system embedding and can be applied to any kinematic system on a Lie group.

eess.SY↗

arXiv2020

Equivariant Systems Theory and Observer Design

A wide range of system models in modern robotics and avionics applications admit natural symmetries. Such systems are termed equivariant and the structure provided by the symmetry is a powerful tool in the design of observers. Significant progress has been made in the last ten years in the design of filters and observers for attitude and pose estimation, tracking of homographies, and velocity aided attitude estimation, by exploiting their inherent Lie-group state-space structure. However, little work has been done for systems on homogeneous spaces, that is systems on manifolds on which a Lie-group acts rather than systems on the Lie-group itself. Recent research in robotic vision has discovered symmetries and equivariant structure on homogeneous spaces for a host of problems including the key problems of visual odometry and visual simultaneous localisation and mapping. These discoveries motivate a deeper look at the structure of equivariant systems on homogeneous spaces. This paper provides a comprehensive development of the foundation theory required to undertake observer and filter design for such systems.

eess.SY↗

arXiv2020

Reducing the Sim-to-Real Gap for Event Cameras

Event cameras are paradigm-shifting novel sensors that report asynchronous, per-pixel brightness changes called 'events' with unparalleled low latency. This makes them ideal for high speed, high dynamic range scenes where conventional cameras would fail. Recent work has demonstrated impressive results using Convolutional Neural Networks (CNNs) for video reconstruction and optic flow with events. We present strategies for improving training data for event based CNNs that result in 20-40% boost in performance of existing state-of-the-art (SOTA) video reconstruction networks retrained with our method, and up to 15% for optic flow networks. A challenge in evaluating event based video reconstruction is lack of quality ground truth images in existing datasets. To address this, we present a new High Quality Frames (HQF) dataset, containing events and ground truth frames from a DAVIS240C that are well-exposed and minimally motion-blurred. We evaluate our method on HQF + several existing major event camera datasets.

cs.CV↗

arXiv2020

Shonan Rotation Averaging: Global Optimality by Surfing $SO(p)^n$

Shonan Rotation Averaging is a fast, simple, and elegant rotation averaging algorithm that is guaranteed to recover globally optimal solutions under mild assumptions on the measurement noise. Our method employs semidefinite relaxation in order to recover provably globally optimal solutions of the rotation averaging problem. In contrast to prior work, we show how to solve large-scale instances of these relaxations using manifold minimization on (only slightly) higher-dimensional rotation manifolds, re-using existing high-performance (but local) structure-from-motion pipelines. Our method thus preserves the speed and scalability of current SFM methods, while recovering globally optimal solutions.

cs.CV↗

arXiv2020

Robust Ego and Object 6-DoF Motion Estimation and Tracking

The problem of tracking self-motion as well as motion of objects in the scene using information from a camera is known as multi-body visual odometry and is a challenging task. This paper proposes a robust solution to achieve accurate estimation and consistent track-ability for dynamic multi-body visual odometry. A compact and effective framework is proposed leveraging recent advances in semantic instance-level segmentation and accurate optical flow estimation. A novel formulation, jointly optimizing SE(3) motion and optical flow is introduced that improves the quality of the tracked points and the motion estimation accuracy. The proposed approach is evaluated on the virtual KITTI Dataset and tested on the real KITTI Dataset, demonstrating its applicability to autonomous driving applications. For the benefit of the community, we make the source code public.

cs.RO↗

arXiv2020

An Equivariant Observer Design for Visual Localisation and Mapping

This paper builds on recent work on Simultaneous Localisation and Mapping (SLAM) in the non-linear observer community, by framing the visual localisation and mapping problem as a continuous-time equivariant observer design problem on the symmetry group of a kinematic system. The state-space is a quotient of the robot pose expressed on SE(3) and multiple copies of real projective space, used to represent both points in space and bearings in a single unified framework. An observer with decoupled Riccati-gains for each landmark is derived and we show that its error system is almost globally asymptotically stable and exponentially stable in-the-large.

cs.RO↗

arXiv2020

An Observer Design for Visual Simultaneous Localisation and Mapping with Output Equivariance

Visual Simultaneous Localisation and Mapping (VSLAM) is a key enabling technology for small embedded robotic systems such as aerial vehicles. Recent advances in equivariant filter and observer design offer the potential of a new generation of highly robust algorithms with low memory and computation requirements for embedded system applications. This paper studies observer design on the symmetry group proposed in previous work by the authors, in the case where inverse depth measurements are available. Exploiting this symmetry leads to a simple fully non-linear gradient based observer with almost global asymptotic and local exponential stability properties. Simulation experiments verify the observer design, and demonstrate that the proposed observer achieves similar accuracy to the widely used Extended Kalman Filter with significant gains in processing time (linear verses quadratic bounds with respect to number of landmarks) and qualitative improvements in robustness.

cs.RO↗

arXiv2020

LyRN (Lyapunov Reaching Network): A Real-Time Closed Loop approach from Monocular Vision

We propose a closed-loop, multi-instance control algorithm for visually guided reaching based on novel learning principles. A control Lyapunov function methodology is used to design a reaching action for a complex multi-instance task in the case where full state information (poses of all potential reaching points) is available. The proposed algorithm uses monocular vision and manipulator joint angles as the input to a deep convolution neural network to predict the value of the control Lyapunov function (cLf) and corresponding velocity control. The resulting network output is used in real-time as visual control for the grasping task with the multi-instance capability emerging naturally from the design of the control Lyapunov function. We demonstrate the proposed algorithm grasping mugs (textureless and symmetric objects) on a table-top from an over-the-shoulder monocular RGB camera. The manipulator dynamically converges to the best-suited target among multiple identical instances from any random initial pose within the workspace. The system trained with only simulated data is able to achieve 90.3% grasp success rate in the real-world experiments with up to 85Hz closed-loop control on one GTX 1080Ti GPU and significantly outperforms a Pose-Based-Visual-Servo (PBVS) grasping system adapted from a state-of-the-art single shot RGB 6D pose estimation algorithm. A key contribution of the paper is the inclusion of a first-order differential constraint associated with the cLf as a regularisation term during learning, and we provide evidence that this leads to more robust and reliable reaching/grasping performance than vanilla regression on general control inputs.

cs.RO↗

arXiv2020

Dynamic SLAM: The Need For Speed

The static world assumption is standard in most simultaneous localisation and mapping (SLAM) algorithms. Increased deployment of autonomous systems to unstructured dynamic environments is driving a need to identify moving objects and estimate their velocity in real-time. Most existing SLAM based approaches rely on a database of 3D models of objects or impose significant motion constraints. In this paper, we propose a new feature-based, model-free, object-aware dynamic SLAM algorithm that exploits semantic segmentation to allow estimation of motion of rigid objects in a scene without the need to estimate the object poses or have any prior knowledge of their 3D models. The algorithm generates a map of dynamic and static structure and has the ability to extract velocities of rigid moving objects in the scene. Its performance is demonstrated on simulated, synthetic and real-world datasets.

cs.RO↗

arXiv2019

CED: Color Event Camera Dataset

Event cameras are novel, bio-inspired visual sensors, whose pixels output asynchronous and independent timestamped spikes at local intensity changes, called 'events'. Event cameras offer advantages over conventional frame-based cameras in terms of latency, high dynamic range (HDR) and temporal resolution. Until recently, event cameras have been limited to outputting events in the intensity channel, however, recent advances have resulted in the development of color event cameras, such as the Color-DAVIS346. In this work, we present and release the first Color Event Camera Dataset (CED), containing 50 minutes of footage with both color frames and events. CED features a wide variety of indoor and outdoor scenes, which we hope will help drive forward event-based vision research. We also present an extension of the event camera simulator ESIM that enables simulation of color events. Finally, we present an evaluation of three state-of-the-art image reconstruction methods that can be used to convert the Color-DAVIS346 into a continuous-time, HDR, color video camera to visualise the event stream, and for use in downstream vision applications.

cs.CV↗

arXiv2019

Asynchronous Spatial Image Convolutions for Event Cameras

Spatial convolution is arguably the most fundamental of 2D image processing operations. Conventional spatial image convolution can only be applied to a conventional image, that is, an array of pixel values (or similar image representation) that are associated with a single instant in time. Event cameras have serial, asynchronous output with no natural notion of an image frame, and each event arrives with a different timestamp. In this paper, we propose a method to compute the convolution of a linear spatial kernel with the output of an event camera. The approach operates on the event stream output of the camera directly without synthesising pseudo-image frames as is common in the literature. The key idea is the introduction of an internal state that directly encodes the convolved image information, which is updated asynchronously as each event arrives from the camera. The state can be read-off as-often-as and whenever required for use in higher level vision algorithms for real-time robotic systems. We demonstrate the application of our method to corner detection, providing an implementation of a Harris corner-response "state" that can be used in real-time for feature detection and tracking on robotic systems.

cs.CV↗

arXiv2018

Continuous-time Intensity Estimation Using Event Cameras

Event cameras provide asynchronous, data-driven measurements of local temporal contrast over a large dynamic range with extremely high temporal resolution. Conventional cameras capture low-frequency reference intensity information. These two sensor modalities provide complementary information. We propose a computationally efficient, asynchronous filter that continuously fuses image frames and events into a single high-temporal-resolution, high-dynamic-range image state. In absence of conventional image frames, the filter can be run on events only. We present experimental results on high-speed, high-dynamic-range sequences, as well as on new ground truth datasets we generate to demonstrate the proposed algorithm outperforms existing state-of-the-art methods.

cs.CV↗