检索结果-内蒙古大学图书馆

Uncertainty propagation in the internet of things

学校读者我要写书评

暂无评论

Discover Internet of Things 2024年第1期4卷 1-20页

作者： Pal, Shantanu Khalifa, Sara Miller, Dimity Dedeoglu, Volkan Dorri, Ali Ramachandran, Gowri Moghadam, Peyman Kusy, Brano Jurdak, Raja The School of Information Technology Faculty of Science Engineering and Built Environment Deakin University MelbourneVIC 3125 Australia The School of Information Systems Faculty of Science Queensland University of Technology BrisbaneQLD4000 Australia The School of Electrical Engineering and Robotics Faculty of Engineering Queensland University of Technology BrisbaneQLD4000 Australia The Distributed Sensing Systems Group Data61 CSIRO PullenvaleQLD 4069 Australia The School of Computer Science Faculty of Science Queensland University of Technology BrisbaneQLD 4000 Australia The CSIRO Robotics Data61 CSIRO PullenvaleQLD 4069 Australia

The Internet of Things (IoT) detects context through sensors capturing data from dynamic physical environments, in order to inform automation decisions within cyber physical systems (CPS). Diverse types of uncertainty in the IoT pipeline can propagate within and across nodes, involving complex interactions with security, privacy, and trust that remain largely unexplored. This paper conducts an in-depth analysis of the types of uncertainties in IoT and how they propagate within IoT nodes and networks. We consider adversarial uncertainty in the context of distributed IoT networks to capture perturbations due to malicious actors in the network that can influence IoT security, privacy and trust. We examine the propagation of adversarial uncertainty and well-known uncertainty types, namely aleatoric and epistemic uncertainty, within the five distinct stages of sensing, communication, storage, processing and decision-making in an IoT pipeline, across network layer boundaries, and across nodes within an IoT network. Using this mapping, we analyse the interactions between the uncertainty types and their propagation, and security, privacy, and trust in IoT. Based on this analysis, we discuss guidelines and considerations for mitigating uncertainty in IoT through a smart grid use case study. © The Author(s) 2024.

关键词： Differential privacy

Real-time Background Subtraction under Varying Lighting Conditions

学校读者我要写书评

暂无评论

Real-time Background Subtraction under Varying Lighting Cond...

IEEE International Conference on robotics and Automation (ICRA)

作者： Sisi Liang Darren Baker Robotics and Autonomous Systems Group Data61 CSIRO Brisbane QLD Australia

Background subtraction is an important topic in computer vision and video analysis. It is challenging to robustly segment foreground and background in complex scenarios. In the literature there are efforts to address some of the main challenges such as illumination change, dynamic backgrounds, hard shadows, and intermittent object motion. However, most of the research has focused on applying advanced mathematical and machine learning models rather than on improving performance in real-time applications. In this paper, we devise a method named EGMM to efficiently handle the illumination change problem and also operate at a real-time execution speed on commodity PC hardware. EGMM is an ensemble algorithm that fuses multiple Gaussian Mixture Models operating on gradient, texture and color features. Detection and removal of shadows is done using a chromaticity-based approach, and spatio-temporal history of foreground blobs is used to handle intermittent object motion. We benchmarked EGMM by creating datasets for two light change scenarios. The results demonstrate that EGMM achieves robust performance in complex illumination change cases, outperforms some state-of-the-art algorithms, and runs at 100 fps (GPU) at $1280\times720$ resolution. Moreover, experiments using the 2012 CDnet dataset show that EGMM achieves generally good performance in varying scenes with overall results better than conventional methods and runs at 1000 fps (GPU) at $320\times 240$ resolution.

关键词：

GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Knights, Joshua Hausler, Stephen Sridharan, Sridha Fookes, Clinton Moghadam, Peyman CSIRO Robotics and Autonomous Systems DATA61 CSIRO Australia Brisbane Australia

LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak performance. However, obtaining accurate ground truth data for new training data can be prohibitively expensive, especially in complex or GPS-deprived environments. To address this issue we propose GeoAdapt, which introduces a novel auxiliary classification head to generate pseudo-labels for retraining on unseen environments in a self-supervised manner. GeoAdapt uses geometric consistency as a prior to improve the robustness of our generated pseudo-labels against domain shift, improving the performance and reliability of our Test-Time Adaptation approach. Comprehensive experiments show that GeoAdapt significantly boosts place recognition performance across moderate to severe domain shifts, and is competitive with fully supervised test-time adaptation approaches. Our code is available at https://***/csiro-robotics/GeoAdapt. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

Credible Online Dynamics Learning for Hybrid UAVs

学校读者我要写书评

暂无评论

Credible Online Dynamics Learning for Hybrid UAVs

IEEE International Conference on robotics and Automation (ICRA)

作者： David Rohr Nicholas Lawrance Olov Andersson Roland Siegwart Autonomous Systems Lab ETH Zurich Zurich Switzerland Robotics and Autonomous Systems Group CSIRO Data61 QLD Australia

Hybrid unmanned aerial vehicles (H-UAVs) are highly versatile platforms with the ability to transition between rotary- and fixed-wing flight. However, their (aero)dynamics tend to be highly nonlinear which increases the risk of introducing safety-critical modeling errors in a controller. Designing a safe, yet not too cautious controller, requires a credible model which provides accurate dynamics uncertainty quantification. We present a data-efficient, probabilistic semi-parametric dynamics modeling approach that allows for online, filter-based inference. The proposed model leverages prior knowledge using a nominal parametric model, and combines it with residuals in the form of sparse Gaussian processes to account for possibly unmodeled forces and moments. Uncertain nominal and residual parameters are jointly estimated using Bayesian filtering. The resulting model accuracy and the reliability of its predicted uncertainty are analyzed for both a simulated and a real example, where we learn the 6DoF nonlinear dynamics of a tiltwing H-UAV from a few minutes of flight data. Compared to a residual-free nominal model, the proposed semi-parametric approach provides increased model accuracy in relevant parts of the flight envelope and substantially higher credibility overall.

关键词：

Wild-Places: A Large-Scale dataset for Lidar Place Recognition in Unstructured Natural Environments

学校读者我要写书评

暂无评论

Wild-Places: A Large-Scale Dataset for Lidar Place Recogniti...

IEEE International Conference on robotics and Automation (ICRA)

作者： Joshua Knights Kavisha Vidanapathirana Milad Ramezani Sridha Sridharan Clinton Fookes Peyman Moghadam Robotics and Autonomous Systems Group DATA61 CSIRO Australia School of Electrical Engineering and Robotics Queensland University of Technology (QUT) Australia

Many existing datasets for lidar place recognition are solely representative of structured urban environments, and have recently been saturated in performance by deep learning based approaches. Natural and unstructured environments present many additional challenges for the tasks of long-term localisation but these environments are not represented in currently available datasets. To address this we introduce Wild-Places, a challenging large-scale dataset for lidar place recognition in unstructured, natural environments. Wild-Places contains eight lidar sequences collected with a handheld sensor payload over the course of fourteen months, containing a total of 63K undistorted lidar submaps along with accurate 6DoF ground truth. This dataset contains multi-ple revisits both within and between sequences, allowing for both intra-sequence (i.e., loop closure detection) and inter-sequence (i.e., re-localisation) tasks. We also benchmark several state-of-the-art approaches to demonstrate the challenges that this dataset introduces, particularly the case of long-term place recognition due to natural environments changing over time. Our dataset and code is available at https://***/Wild-Places

关键词：

Wild-Places: A Large-Scale dataset for Lidar Place Recognition in Unstructured Natural Environments

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Knights, Joshua Vidanapathirana, Kavisha Ramezani, Milad Sridharan, Sridha Fookes, Clinton Moghadam, Peyman Robotics and Autonomous Systems Group DATA61 CSIRO Australia Australia

— Many existing datasets for lidar place recognition are solely representative of structured urban environments, and have recently been saturated in performance by deep learning based approaches. Natural and unstructured environments present many additional challenges for the tasks of long-term localisation but these environments are not represented in currently available datasets. To address this we introduce Wild-Places, a challenging large-scale dataset for lidar place recognition in unstructured, natural environments. Wild-Places contains eight lidar sequences collected with a handheld sensor payload over the course of fourteen months, containing a total of 63K undistorted lidar submaps along with accurate 6DoF ground truth. This dataset contains multiple revisits both within and between sequences, allowing for both intra-sequence (i.e., loop closure detection) and inter-sequence (i.e., re-localisation) tasks. We also benchmark several state-of-the-art approaches to demonstrate the challenges that this dataset introduces, particularly the case of long-term place recognition due to natural environments changing over time. Our dataset and code is available at https://***/Wild-Places Copyright © 2022, The Authors. All rights reserved.

关键词： Optical radar

FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mohamed, Shaheer Haghighat, Maryam Fernando, Tharindu Sridharan, Sridha Fookes, Clinton Moghadam, Peyman The Robotics and Autonomous Systems DATA61 CSIRO BrisbaneQLD4069 Australia Brisbane Australia

Hyperspectral images (HSIs) contain rich spectral and spatial information. Motivated by the success of transformers in the field of natural language processing and computer vision where they have shown the ability to learn long range dependencies within input data, recent research has focused on using transformers for HSIs. However, current state-of-the-art hyperspectral transformers only tokenize the input HSI sample along the spectral dimension, resulting in the under-utilization of spatial information. Moreover, transformers are known to be data-hungry and their performance relies heavily on large-scale pretraining, which is challenging due to limited annotated hyperspectral data. Therefore, the full potential of HSI transformers has not been fully realized. To overcome these limitations, we propose a novel factorized spectral-spatial transformer that incorporates factorized self-supervised pretraining procedures, leading to significant improvements in performance. The factorization of the inputs allows the spectral and spatial transformers to better capture the interactions within the hyperspectral data cubes. Inspired by masked image modeling pretraining, we also devise efficient masking strategies for pretraining each of the spectral and spatial transformers. We conduct experiments on six publicly available datasets for HSI classification task and demonstrate that our model achieves state-of-the-art performance in all the datasets. The code for our model will be made available at https://***/csiro-robotics/FactoFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

Deep Robust Multi-Robot Re-localisation in Natural Environments

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ramezani, Milad Griffiths, Ethan Haghighat, Maryam Pitt, Alex Moghadam, Peyman The Robotics and Autonomous Systems DATA61 CSIRO BrisbaneQLD4069 Australia Brisbane Australia

The success of re-localisation has crucial implications for the practical deployment of robots operating within a prior map or relative to one another in real-world scenarios. Using single-modality, place recognition and localisation can be compromised in challenging environments such as forests. To address this, we propose a strategy to prevent lidar-based re-localisation failure using lidar-image cross-modality. Our solution relies on self-supervised 2D-3D feature matching to predict alignment and misalignment. Leveraging a deep network for lidar feature extraction and relative pose estimation between point clouds, we train a model to evaluate the estimated transformation. A model predicting the presence of misalignment is learned by analysing image-lidar similarity in the embedding space and the geometric constraints available within the region seen in both modalities in Euclidean space. Experimental results using real datasets (offline and online modes) demonstrate the effectiveness of the proposed pipeline for robust re-localisation in unstructured, natural environments. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical radar

Point Cloud Segmentation Using Sparse Temporal Local Attention

学校读者我要写书评

暂无评论

Point Cloud Segmentation Using Sparse Temporal Local Attenti...

2021 Australasian Conference on robotics and Automation, ACRA 2021

作者： Knights, Joshua Moghadam, Peyman Fookes, Clinton Sridharan, Sridha Robotics and Autonomous Systems CSIRO Data61 Australia Queensland University of Technology Australia

ISBN: (纸本)9781713841487

Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment. However despite the sensor outputs from autonomous vehicles being naturally temporal in nature, there is still limited exploration of exploiting point cloud sequences for 3D semantic segmentation. In this paper we propose a novel Sparse Temporal Local Attention (STELA) module which aggregates intermediate features from a local neighbourhood in previous point cloud frames to provide a rich temporal context to the decoder. Using the sparse local neighbourhood enables our approach to gather features more flexibly than those which directly match point features, and more efficiently than those which perform expensive global attention over the whole point cloud frame. We achieve a competitive mIoU of 64.3% on the SemanticKitti dataset, and demonstrate significant improvement over the single-frame baseline in our ablation studies. © 2021 Australasian robotics and Automation Association. All rights reserved.

关键词： autonomous vehicles