no code implementations • ECCV 2020 • Frank Dellaert, David M. Rosen, Jing Wu, Robert Mahony, Luca Carlone
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.
no code implementations • 25 Mar 2024 • Yixiao Ge, Pieter van Goor, Robert Mahony
Stochastic inference on Lie groups plays a key role in state estimation problems, such as inertial navigation, visual inertial odometry, pose estimation in virtual reality, etc.
no code implementations • 8 Mar 2024 • Tarek Bouazza, Robert Mahony, Tarek Hamel
Accurately estimating camera motion from image sequences poses a significant challenge in computer vision and robotics.
no code implementations • 30 Jan 2024 • Matthew Hampsey, Pieter van Goor, Ravi Banavar, Robert Mahony
In this paper, we propose a group structure on the cotangent bundle of a Lie group and leverage this to define momentum and configuration errors for trajectory tracking drawing on recent work on equivariant observer design.
no code implementations • 6 Nov 2023 • Matthew Hampsey, Pieter van Goor, Robert Mahony
Trajectory tracking for the kinematic unicycle has been heavily studied for several decades.
no code implementations • 3 Nov 2023 • Pieter van Goor, Tarek Hamel, Robert Mahony
An Inertial Navigation System (INS) is a system that integrates acceleration and angular velocity readings from an Inertial Measurement Unit (IMU), along with other sensors such as GNSS position, GNSS velocity, and magnetometer, to estimate the attitude, velocity, and position of a vehicle.
no code implementations • 12 Sep 2023 • Yixiao Ge, Pieter van Goor, Robert Mahony
With this structure, we show that a naive coordinate implementation of the EKF fails to account for geometry of the manifold in the update step and in the reset step.
no code implementations • 4 Sep 2023 • Yasir Latif, Peter Anastasiou, Yonhon Ng, Zebb Prime, Tien-Fu Lu, Matthew Tetlow, Robert Mahony, Tat-Jun Chin
In this work, we develop a novel payload that utilises a neuromorphic event sensor (for high frequency and highly accurate relative attitude estimation) paired in a closed loop with a piezoelectric stage (for active attitude corrections) to provide highly stable sensor-specific pointing.
1 code implementation • 3 Sep 2023 • Ziwei Wang, Yonhon Ng, Cedric Scheerlinck, Robert Mahony
We also demonstrate the integration of image convolution with linear spatial kernels Gaussian, Sobel, and Laplacian as an application of our architecture.
no code implementations • 22 Aug 2023 • Pieter van Goor, Tarek Hamel, Robert Mahony
Inertial Navigation Systems (INS) are algorithms that fuse inertial measurements of angular velocity and specific acceleration with supplementary sensors including GNSS and magnetometers to estimate the position, velocity and attitude, or extended pose, of a vehicle.
1 code implementation • 20 Jul 2023 • Ziwei Wang, Timothy Molloy, Pieter van Goor, Robert Mahony
Event-based cameras have become increasingly popular for tracking fast-moving objects due to their high temporal resolution, low latency, and high dynamic range.
no code implementations • 18 Apr 2023 • Zheyu Zhuang, Yizhak Ben-Shabat, Jiahao Zhang, Stephen Gould, Robert Mahony
It is composed of a visual servoing module that reaches and grasps assembly parts in an unstructured multi-instance and dynamic environment, an action recognition module that performs human action prediction for implicit communication, and a visual handover module that uses the perceptual understanding of human behaviour to produce an intuitive and efficient collaborative assembly experience.
no code implementations • 10 Mar 2023 • Tarek Bouazza, Pieter van Goor, Robert Mahony, Tarek Hamel
Feature-based homography estimation approaches rely on extensive image processing for feature extraction and matching, and do not adequately account for the information provided by the image.
no code implementations • 13 Nov 2022 • Matthew Hampsey, Pieter van Goor, Robert Mahony
Accurate tracking of planned trajectories in the presence of perturbations is an important problem in control and robotics.
no code implementations • 25 Oct 2022 • Hiya Gada, Pieter van Goor, Ravi Banavar, Robert Mahony
Observers for systems with Lie group symmetries are an active area of research that is seeing significant impact in a number of practical domains, including aerospace, robotics, and mechatronics.
no code implementations • 12 Sep 2022 • Yixiao Ge, Pieter van Goor, Robert Mahony
The kinematics of many nonlinear control systems, especially in the robotics field, admit a transitive Lie-group symmetry, which is useful in high performance observer design.
no code implementations • 8 Sep 2022 • Pieter van Goor, Tarek Hamel, Robert Mahony
Inertial Velocity-Aided Attitude (VAA) is an important problem in the control of Remotely Piloted Aerial Systems (RPAS), and involves estimating the velocity and attitude of a vehicle using gyroscope, accelerometer, and inertial-frame velocity (e. g. GPS velocity) measurements.
1 code implementation • 17 May 2022 • Ziwei Wang, Dingran Yuan, Yonhon Ng, Robert Mahony
Event cameras are bio-inspired sensors that capture per-pixel asynchronous intensity change rather than the synchronous absolute intensity frames captured by a classical camera sensor.
1 code implementation • 11 Oct 2021 • Ziwei Wang, Liyuan Pan, Yonhon Ng, Zheyu Zhuang, Robert Mahony
We provide a SHEF dataset targeted at evaluating disparity estimation algorithms and introduce a stereo disparity estimation algorithm that uses edge information extracted from the event stream correlated with the edge detected in the frame data.
no code implementations • 20 Aug 2021 • Robert Mahony, Pieter van Goor, Tarek Hamel
The equivariant filter exploits the symmetry and respects the geometry of an equivariant system model and yields high performance robust filters for a wide range of mechatronic and navigation systems.
no code implementations • 29 Jul 2021 • Robert Mahony
This potential is then used as the model to shape the energy of the true system such that its free solutions include the desired reference trajectory.
no code implementations • 12 Jul 2021 • Pieter van Goor, Tarek Hamel, Robert Mahony
The kinematics of many mechanical systems encountered in robotics and other fields, such as single-bearing attitude estimation and SLAM, are naturally posed on homogeneous spaces: That is, their state lies in a smooth manifold equipped with a transitive Lie-group symmetry.
no code implementations • 11 May 2021 • Yonhon Ng, Pieter van Goor, Tarek Hamel, Robert Mahony
The state of a second order kinematic system on a matrix Lie group is naturally posed on the tangent bundle of the group with the inputs lying in the tangent of the tangent bundle known as the double tangent bundle.
no code implementations • 14 Apr 2021 • Yonhon Ng, Pieter van Goor, Robert Mahony, Tarek Hamel
This paper addresses the problem of estimating the attitude and angular velocity of a rigid object by exploiting its second order kinematic model.
no code implementations • 22 Jan 2021 • Gerard Kennedy, Zheyu Zhuang, Xin Yu, Robert Mahony
Object pose estimation from a single RGB image is a challenging problem due to variable lighting conditions and viewpoint changes.
1 code implementation • 17 Dec 2020 • Ziwei Wang, Yonhon Ng, Pieter van Goor, Robert Mahony
Currently, most of the existing works use a single contrast threshold to estimate the intensity change of all pixels.
1 code implementation • ICCV 2021 • Ziwei Wang, Yonhon Ng, Cedric Scheerlinck, Robert Mahony
Conversely, conventional image sensors measure absolute intensity of slowly changing scenes effectively but do poorly on high dynamic range or quickly changing scenes.
1 code implementation • 27 Oct 2020 • Pieter van Goor, Tarek Hamel, Robert Mahony
Simulation experiments of an example application show that the EqF significantly outperforms the extended Kalman filter and that the reduced linearisation error leads to a clear improvement in performance.
1 code implementation • 6 Aug 2020 • Frank Dellaert, David M. Rosen, Jing Wu, Robert Mahony, Luca Carlone
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.
2 code implementations • 28 Jul 2020 • Jun Zhang, Mina Henein, Robert Mahony, Viorela Ila
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.
no code implementations • 9 Jun 2020 • Pieter van Goor, Robert Mahony, Tarek Hamel, Jochen Trumpf
Visual Simultaneous Localisation and Mapping (VSLAM) is a well-known problem in robotics with a large range of applications.
1 code implementation • 22 May 2020 • Jun Zhang, Mina Henein, Robert Mahony, Viorela Ila
Combining Simultaneous Localisation and Mapping (SLAM) estimation and dynamic scene modelling can highly benefit robot autonomy in dynamic environments.
Robotics
1 code implementation • ECCV 2020 • Timo Stoffregen, Cedric Scheerlinck, Davide Scaramuzza, Tom Drummond, Nick Barnes, Lindsay Kleeman, Robert Mahony
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.
Ranked #3 on Video Reconstruction on MVSEC
1 code implementation • 20 Feb 2020 • Mina Henein, Jun Zhang, Robert Mahony, Viorela Ila
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.
Robotics
no code implementations • 24 Apr 2019 • Cedric Scheerlinck, Henri Rebecq, Timo Stoffregen, Nick Barnes, Robert Mahony, Davide Scaramuzza
Event cameras are novel, bio-inspired visual sensors, whose pixels output asynchronous and independent timestamped spikes at local intensity changes, called 'events'.
no code implementations • 2 Dec 2018 • Cedric Scheerlinck, Nick Barnes, Robert Mahony
In this paper, we propose a method to compute the convolution of a linear spatial kernel with the output of an event camera.
no code implementations • 1 Nov 2018 • Cedric Scheerlinck, Nick Barnes, Robert Mahony
Event cameras provide asynchronous, data-driven measurements of local temporal contrast over a large dynamic range with extremely high temporal resolution.
no code implementations • 16 Jan 2017 • Chuong V. Nguyen, Michael Milford, Robert Mahony
In this paper, we present a novel stereo-polarization system for detecting and tracking water hazards based on polarization and color variation of reflected light, with consideration of the effect of polarized light from sky as function of reflection and azimuth angles.
no code implementations • 9 Jun 2016 • Minh-Duc Hua, Jochen Trumpf, Tarek Hamel, Robert Mahony, Pascal Morin
This paper presents a new algorithm for online estimation of a sequence of homographies applicable to image sequences obtained from robotic vehicles equipped with vision sensors.