检索结果-内蒙古大学图书馆

Model Identification of a Small Fully-Actuated Aquatic Surface Vehicle Using a Long Short-Term Memory Neural Network

学校读者我要写书评

暂无评论

Model Identification of a Small Fully-Actuated Aquatic Surfa...

IEEE International Conference on robotics and Automation (ICRA)

作者： Marin Dimitrov Keir Groves David Howard Barry Lennox University of Manchester UK Robotics and Autonomous Systems Group Data61 CSIRO Australia

A long short-term memory neural network is used to provide a system model that captures the temporal-dynamics of a holonomic, fully-actuated aquatic surface vehicle. As is true in many fields, new developments in robotics often are made in simulation first before being applied to real systems. To simulate an aquatic or aerial robot, a dynamic system model of the robot is required. The more representative the dynamic model is of the real robot, the smaller the simulation-to-reality gap becomes. The performance of the neural network is compared against a classical parametric model, where coefficients of the parametric model were identified using the same data that was used to train the neural network. The results show that the neural network consistently outperforms the classical parametric model and significantly reduces the error between real velocities and estimated velocities. The neural network also demonstrated the ability to capture complex hydrodynamic effects that were not captured in the parametric model. In addition to the performance improvements, the neural network method can be easily adapted to similarly actuated aquatic vehicles by simply retraining, whereas the classical approach would require manual selection of new equation terms. The neural network model that was created has been used in a vehicle simulation and is presently being used as a research tool.

关键词： Adaptation models Neural networks Predictive models Tools Mathematical models Unmanned aerial vehicles Parametric statistics

deepNIR: datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sa, Inkyu Lim, JongYoon Ahn, Ho Seok MacDonald, Bruce CSIRO Data61 Robotics and Autonomous Systems Group Robot Perception Team Switzerland CARES Department of Electrical Computer and Software Engineering University of Auckland New Zealand

This paper presents datasets utilised for synthetic near-infrared (NIR) image generation and bounding-box level fruit detection systems. A high-quality dataset is one of the essential building blocks that can lead to success in model generalisation and the deployment of data-driven deep neural networks. In particular, synthetic data generation tasks often require more training samples than other supervised approaches. Therefore, in this paper, we share the NIR+RGB datasets that are re-processed from two public datasets (i.e., nirscene and SEN12MS), expanded our previous study, deepFruits, and our novel NIR+RGB sweet pepper(capsicum) dataset. We oversampled from the original nirscene dataset at 10, 100, 200, and 400 ratios that yielded a total of 127 k pairs of images. From the SEN12MS satellite multispectral dataset, we selected Summer (45 k) and All seasons (180 k) subsets and applied a simple yet important conversion;digital number (DN) to pixel value conversion followed by image standardisation. Our sweet pepper dataset consists of 1615 pairs of NIR+RGB images that were collected from commercial farms. We quantitatively and qualitatively demonstrate that these NIR+RGB datasets are sufficient to be used for synthetic NIR image generation. We achieved Frechet Inception Distance (FID) of 11.36, 26.53, and 40.15 for nirscene1, SEN12MS, and sweet pepper datasets respectively. In addition, we release manual annotations of 11 fruit bounding boxes that can be exported as various formats using cloud service. Four newly added fruits [blueberry, cherry, kiwi, and wheat] compound 11 novel bounding box datasets on top of our previous work presented in the deepFruits project [apple, avocado, capsicum, mango, orange, rockmelon, strawberry]. The total number of bounding box instances of the dataset is 162 k and it is ready to use from cloud service. For the evaluation of the dataset, Yolov5 single stage detector is exploited and reported impressive mean-average-precision, mAP[0.

关键词： Generative adversarial networks

Temporally Coherent Embeddings for Self-Supervised Video Representation Learning

学校读者我要写书评

暂无评论

Temporally Coherent Embeddings for Self-Supervised Video Rep...

International Conference on Pattern Recognition

作者： Joshua Knights Ben Harwood Daniel Ward Anthony Vanderkop Olivia Mackenzie-Ross Peyman Moghadam Robotics and Autonomous Systems Data61 CSIRO Brisbane QLD Australia

This paper presents TCE: Temporally Coherent Embeddings for self-supervised video representation learning. The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding space, rather than indirectly learning it through ranking or predictive proxy tasks. In the same way that high-level visual information in the world changes smoothly, we believe that nearby frames in learned representations will benefit from demonstrating similar properties. Using this assumption, we train our TCE model to encode videos such that adjacent frames exist close to each other and videos are separated from one another. Using TCE we learn robust representations from large quantities of unlabeled video data. We thoroughly analyse and evaluate our self-supervised learned TCE models on a downstream task of video action recognition using multiple challenging benchmarks (Kinetics400, UCF101, HMDB51). With a simple but effective 2D-CNN backbone and only RGB stream inputs, TCE pre-trained representations outperform all previous self-supervised 2D-CNN and 3D-CNN pre-trained on UCF101. The code and pre-trained models for this paper can be downloaded at: https://***/csiro-robotics/TCE.

关键词： Training Visualization Benchmark testing Network architecture Hardware data models Spatiotemporal phenomena

LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Vidanapathirana, Kavisha Ramezani, Milad Moghadam, Peyman Sridharan, Sridha Fookes, Clinton The Robotics and Autonomous Systems Group DATA61 CSIRO BrisbaneQLD4069 Australia Brisbane Australia

Retrieval-based place recognition is an efficient and effective solution for re-localization within a pre-built map, or global data association for Simultaneous Localization and Mapping (SLAM). The accuracy of such an approach is heavily dependent on the quality of the extracted scene-level representation. While end-to-end solutions - which learn a global descriptor from input point clouds - have demonstrated promising results, such approaches are limited in their ability to enforce desirable properties at the local feature level. In this paper, we introduce a local consistency loss to guide the network towards learning local features which are consistent across revisits, hence leading to more repeatable global descriptors resulting in an overall improvement in 3D place recognition performance. We formulate our approach in an end-to-end trainable architecture called LoGG3D-Net. Experiments on two large-scale public benchmarks (KITTI and MulRan) show that our method achieves mean F1max scores of 0.939 and 0.968 on KITTI and MulRan respectively, achieving state-of-the-art performance while operating in near real-time. The open-source implementation is available at: https://***/csirorobotics/LoGG3D-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Benchmarking

Semantic Segmentation of Fruits on Multi-sensor Fused data in Natural Orchards

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kang, Hanwen Wang, Xing College of Engineering South China Agricultural University Guangzhou China Mechanical and Aerospace Engineering Monash University Melbourne Australia Robotics and Autonomous Systems Group Data61 CSIRO Brisbane Australia

Semantic segmentation is a fundamental task for agricultural robots to understand the surrounding environments in natural orchards. The recent development of the LiDAR techniques enables the robot to acquire accurate range measurements of the view in the unstructured orchards. Compared to RGB images, 3D point clouds have geometrical properties. By combining the LiDAR and camera, rich information on geometries and textures can be obtained. In this work, we propose a deep-learning-based segmentation method to perform accurate semantic segmentation on fused data from a LiDAR-Camera visual sensor. Two critical problems are explored and solved in this work. The first one is how to efficiently fused the texture and geometrical features from multi-sensor data. The second one is how to efficiently train the 3D segmentation network under severely imbalance class conditions. Moreover, an implementation of 3D segmentation in orchards including LiDAR-Camera data fusion, data collection and labelling, network training, and model inference is introduced in detail. In the experiment, we comprehensively analyze the network setup when dealing with highly unstructured and noisy point clouds acquired from an apple orchard. Overall, our proposed method achieves 86.2% mIoU on the segmentation of fruits on the high-resolution point cloud (100k-200k points). The experiment results show that the proposed method can perform accurate segmentation in real orchard environments. © 2022, CC BY.

关键词： Fruits

Point cloud segmentation using sparse temporal local attention

学校读者我要写书评

暂无评论

arXiv 2021年

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

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. Copyright © 2021, The Authors. All rights reserved.

关键词： autonomous vehicles

Shape, size, and fabrication effects in 3D printed granular jamming grippers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Howard, Gerard Howard, David O'Connor, Jack Brett, James Delaney, Gary W. Robotics and Autonomous System Group Data61 CSIRO Australia School of Mechanical and Mining University of Queensland Australia Computational Modelling Group Data61 CSIRO Australia

Granular jamming is a popular soft actuation mechanism that provides high stiffness variability with minimum volume variation. Jamming is particularly interesting from a design perspective, as a myriad of design parameters can potentially be exploited to induce a diverse variety of useful behaviours. To date, grain shape has been largely ignored. Here, we focus on the use of 3D printing to expose design variables related to grain shape and size. Grains are represented by parameterised superquadrics (superellipsoids);four diverse shapes are investigated along with three size variations. Grains are 3D printed at high resolution and performance is assessed in experimental pull-off testing on a variety of benchmark test objects. We show that grain shape and size are key determinants in granular gripping performance. Moreover, there is no universally-optimal grain shape for gripping. Optical imaging assesses the accuracy of printed shapes compared to their ideal models. Results suggest that optimisation of grain shape is a key enabler for high-performance, bespoke, actuation behaviour and can be exploited to expand the range and performance of granular grippers across a range of diverse usage scenarios. Copyright © 2021, The Authors. All rights reserved.

关键词： 3D printers

Sample Efficient Dynamics Learning for Symmetrical Legged Robots: Leveraging Physics Invariance and Geometric Symmetries

学校读者我要写书评

暂无评论

Sample Efficient Dynamics Learning for Symmetrical Legged Ro...

IEEE International Conference on robotics and Automation (ICRA)

作者： Jee-eun Lee Jaemin Lee Tirthankar Bandyopadhyay Luis Sentis Department of Aerospace Engineering and Engineering Mechanics Human Centered Robotics Laboratory The University of Texas at Austin USA Department of Mechanical and Civil Engineering California Institute of Technology Pasadena CA USA Robotics and Autonomous Systems Group Data61 CSIRO QLD Australia Faculty of Department of Aerospace Engineering and Engineering Mechanics The University of Texas at Austin USA

Model generalization of the underlying dynamics is critical for achieving data efficiency when learning for robot control. This paper proposes a novel approach for learning dynamics leveraging the symmetry in the underlying robotic system, which allows for robust extrapolation from fewer samples. Existing frameworks that represent all data in vector space fail to consider the structured information of the robot, such as leg symmetry, rotational symmetry, and physics invariance. As a result, these schemes require vast amounts of training data to learn the system's redundant elements because they are learned independently. Instead, we propose considering the geometric prior by representing the system in symmetrical object groups and designing neural network architecture to assess invariance and equivariance between the objects. Finally, we demonstrate the effectiveness of our approach by comparing the generalization to unseen data of the proposed model and the existing models. We also implement a controller of a climbing robot based on learned inverse dynamics models. The results show that our method generates accurate control inputs that help the robot reach the desired state while requiring less training data than existing methods.

关键词：

Automated design of pneumatic soft grippers through design-dependent multi-material topology optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pinskier, Josh Kumar, Prabhat Langelaar, Matthijs Howard, David Robotics and Autonomous Systems Group CSIRO Data61 Brisbane Australia Department of Mechanical and Aerospace Engineering Indian Institute of Technology Telangana Hyderabad502285 India Department of Precision and Microsystems Engineering TU Delft Delft Netherlands

Soft robotic grasping has rapidly spread through the academic robotics community in recent years and pushed into industrial applications. At the same time, multimaterial 3D printing has become widely available, enabling the monolithic manufacture of devices containing rigid and elastic sections. We propose a novel design technique that leverages both technologies and can automatically design bespoke soft robotic grippers for fruit-picking and similar applications. We demonstrate the novel topology optimisation formulation that generates multi-material soft grippers, can solve internal and external pressure boundaries, and investigate methods to produce air-tight designs. Compared to existing methods, it vastly expands the searchable design space while increasing simulation accuracy. © 2022, CC BY-NC-SA.

关键词： Topology