检索结果-内蒙古大学图书馆

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Ngoc Thinh Nguyen Niklas Fin Kompe Nicolas Mandel Neele Kohle Floris Ernst Institute for Robotics and Cognitive Systems (ROB) University of Luebeck Luebeck Germany

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

Weed control is important in agriculture and gardening but typically employed manual solutions are both time and labour consuming. By combining advanced developments in digitalization and AI (artificial intelligence), this paper presents two autonomous weed-control related processes: i) for the mapping of rumex weed in an unexplored agricultural field and ii) for the surveillance of the marked herbs. The processes employ a mobile robot equipped with a LIDAR sensor (mainly used for navigation and mapping) and a front stereo camera. A YOLOv8 object detector which is specifically trained for rumex detection is used to locate rumex plants in the camera image. For the first application of mapping, the weeds are marked on the map of the field while for the second task of surveillance, the Ant Colony Optimization looks for an efficient route connecting all those marked weeds which allows the robot to revisit and monitor them. The proposed processes are validated under both real experiments and simulation in realistic Gazebo environments.

关键词： Visualization Laser radar Navigation Surveillance Robot vision systems Detectors Cameras Robustness Mobile robots Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Mobile Robot Path Planning Under Kinematic Constraints by Metaheuristic B-Spline Optimization

Mobile Robot Path Planning Under Kinematic Constraints by Me...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Fabian Menebröker Jannik Stadtler Mahmoud Mohamed Department Robotics and Cognitive Systems Fraunhofer Institute for Material Flow and Logistics Dortmund Germany

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

Global path planning is a crucial component in mobile robot navigation. To provide a good basis that is both feasible and yields fast motion, it should include both robot kinematics and collision avoidance. We introduce a new end-to-end algorithm to solve the mobile robot path planning problem for non-holonomic robots. We consider maximum steering angle, velocity, and acceleration constraints to optimize paths for both collision-avoidance and short tracking time. To this end, we employ B-Splines and metaheuristic optimization algorithms. Experiments show the suitability of our algorithm.

关键词： Trajectory tracking Robot kinematics Metaheuristics Approximation algorithms Planning Mobile robots Reliability Splines (mathematics) Collision avoidance Convergence

来源：评论

学校读者我要写书评

暂无评论

Generation of 3D models of victims within their surroundings at rescue sites

Generation of 3D models of victims within their surroundings...

引用

作者： Kriebisch, Susann Bruder, Ralf Ernst, Floris University of Luebeck Ratzeburger Allee 160 Luebeck23562 Germany Institute for Robotics and Cognitive Systems University of Luebeck Ratzeburger Allee 160 Luebeck23562 Germany

The use of state-of-the-art technology in emergencies enables fast assessment of the situation. Modern rescue robots, but also rescuers with camera systems, record vast amounts of image data. In addition to the benefits for rescue operations, a quick overview based on this data can help medical staff in the search for suitable treatment strategies. However, such data must be examined and fused into an intuitive display. In this work, exemplary image streams of RGB-D cameras are searched for victims and transferred into separate 3D models per detected person for subsequent intuitive viewing, rotating, and zooming. The method was tested and preliminary evaluated for its functionality, detail accuracy and readability of textures at the German Rescue robotics Center. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Flexible and Efficient Surrogate Gradient Modeling with Forward Gradient Injection

arXiv

引用

arXiv 2024年

作者： Otte, Sebastian Adaptive AI Lab Institute of Robotics and Cognitive Systems University of Lübeck Germany

Automatic differentiation is a key feature of present deep learning frameworks. Moreover, they typically provide various ways to specify custom gradients within the computation graph, which is of particular importance for defining surrogate gradients in the realms of non-differentiable operations such as the Heaviside function in spiking neural networks (SNNs). PyTorch, for example, allows the custom specification of the backward pass of an operation by overriding its backward method. Other frameworks provide comparable options. While these methods are common practice and usually work well, they also have several disadvantages such as limited flexibility, additional source code overhead, poor usability, or a potentially strong negative impact on the effectiveness of automatic model optimization procedures. In this paper, an alternative way to formulate surrogate gradients is presented, namely, forward gradient injection (FGI). FGI applies a simple but effective combination of basic standard operations to inject an arbitrary gradient shape into the computational graph directly within the forward pass. It is demonstrated that using FGI is straightforward and convenient. Moreover, it is shown that FGI can significantly increase the model performance in comparison to custom backward methods in SNNs when using TorchScript. These results are complemented with a general performance study on recurrent SNNs with TorchScript and ***, revealing the potential for a training speedup of more than 7x and an inference speedup of more than 16x in comparison with pure PyTorch. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Generalization of a Stateful Graph Search Algorithm Applied to Heterogeneous Mobile Robot Path Planning

Generalization of a Stateful Graph Search Algorithm Applied ...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Fabian Menebröker Dennis Lünsch Marc Hantzsch Utku Pazarci Department Robotics and Cognitive Systems Fraunhofer Institute for Material Flow and Logistics Dortmund Germany

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Path planning for systems with dynamics and constraints is an open problem in many domains, including the planning of mobile robots (MRs). Graph-based approaches are a powerful tool for planning problems, but they commonly rely on abstracting the system state by using fixed edge *** this paper, we present two approaches for stateful graph search. First, a generalized stateful graph search algorithm is introduced that is able to account for system dynamics and constraints in a continuous state space. Secondly, a greedy specialization of the aforementioned algorithm for planning MRs is proposed which solves the problem more efficiently and in accordance with the VDA 5050 standard for heterogeneous fleets of MRs. The approaches are evaluated in a simulated multi-MR scenario and their effectiveness is demonstrated.

关键词： Greedy algorithms Computer aided software engineering System dynamics Heuristic algorithms Search problems Approximation algorithms Path planning Planning Mobile robots Standards

来源：评论

学校读者我要写书评

暂无评论

B-Spline-to-Bézier Conversion and Applications on Path Planning

B-Spline-to-Bézier Conversion and Applications on Path Plan...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Ngoc Thinh Nguyen Pranav Tej Gangavarapu Floris Ernst University of Luebeck (UzL) Institute for Robotics and Cognitive Systems Luebeck Germany

In this paper, we present a new approach to calculate the B-spline-to-Bézler conversion matrix which converts the control points of a uniform B-spline curve into the control points of an equivalent Bézier curve. It takes into account the order of the curve intervals and hence can provide the conversion of the whole curve at once. The algorithm is implemented so that the computation time only increases proportionally with the number of control points until a constant value before getting saturated. Applications include but are not limited to the efficient usage in different optimal path planning algorithms for navigation in 2D non-convex polytopic region as being presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Balanced Resonate-and-Fire Neurons

arXiv

引用

arXiv 2024年

作者： Higuchi, Saya Kairat, Sebastian Bohté, Sander M. Otte, Sebastian Adaptive AI Lab Institute of Robotics and Cognitive Systems University of Lübeck Germany Amsterdam Netherlands

The resonate-and-fire (RF) neuron, introduced over two decades ago, is a simple, efficient, yet biologically plausible spiking neuron model, which can extract frequency patterns within the time domain due to its resonating membrane dynamics. However, previous RF formulations suffer from intrinsic shortcomings that limit effective learning and prevent exploiting the principled advantage of RF neurons. Here, we introduce the balanced RF (BRF) neuron, which alleviates some of the intrinsic limitations of vanilla RF neurons and demonstrates its effectiveness within recurrent spiking neural networks (RSNNs) on various sequence learning tasks. We show that networks of BRF neurons achieve overall higher task performance, produce only a fraction of the spikes, and require significantly fewer parameters as compared to modern RSNNs. Moreover, BRF-RSNN consistently provide much faster and more stable training convergence, even when bridging many hundreds of time steps during backpropagation through time (BPTT). These results underscore that our BRF-RSNN is a strong candidate for future large-scale RSNN architectures, further lines of research in SNN methodology, and more efficient hardware implementations. Copyright © 2024, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Understanding the Convergence in Balanced Resonate-and-Fire Neurons

arXiv

引用

arXiv 2024年

作者： Higuchi, Saya Bohté, Sander M. Otte, Sebastian Adaptive AI Lab Institute of Robotics & Cognitive Systems University of Lübeck Germany Amsterdam Netherlands

Resonate-and-Fire (RF) neurons are an interesting complementary model for integrator neurons in spiking neural networks (SNNs). Due to their resonating membrane dynamics they can extract frequency patterns within the time domain. While established RF variants suffer from intrinsic shortcomings, the recently proposed balanced resonate-and-fire (BRF) neuron marked a significant methodological advance in terms of task performance, spiking and parameter efficiency, as well as, general stability and robustness, demonstrated for recurrent SNNs in various sequence learning tasks. One of the most intriguing result, however, was an immense improvement in training convergence speed and smoothness, overcoming the typical convergence dilemma in backprop-based SNN training. This paper aims at providing further intuitions about how and why these convergence advantages emerge. We show that BRF neurons, in contrast to well-established ALIF neurons, span a very clean and smooth—almost convex—error landscape. Furthermore, empirical results reveal that the convergence benefits are predominantly coupled with a divergence boundary-aware optimization, a major component of the BRF formulation that addresses the numerical stability of the time-discrete resonator approximation. These results are supported by a formal investigation of the membrane dynamics indicating that the gradient is transferred back through time without loss of magnitude. Copyright © 2024, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Towards Realistic 3D Ultrasound Synthesis: Deformable Augmentation using Conditional Variational Autoencoders

Towards Realistic 3D Ultrasound Synthesis: Deformable Augmen...

引用

Annual IEEE Symposium on Computer-Based Medical systems

作者： Daniel Wulff Timon Dohnke Ngoc Thinh Nguyen Floris Ernst Institute for Robotics and Cognitive Systems University of Lübeck Lübeck Germany

For training deep neural networks, large data sets are required. Especially in the medical 3D ultrasound (US) image domain, the amount of available data is limited. A common method to enlarge small data sets is using data augmentation. However, simple geometric augmentation techniques like rotation or sheering can lead to unrealistic US images. In this study, a novel structure-dependent deformable augmentation method for 3D US patches is proposed. The approach is based on learning realistic motion patterns from 3D liver US images using a conditional variational auto encoder (CVAE) where the condition represents the anatomical structure type. The CVAE augmentation performance is compared to a baseline variational auto encoder (VAE). It is shown that the CVAE generates deformable augmentations 18.5 percentage points more similar to realistic deformations than the VAE. Furthermore, the method is evaluated in an expert study where experienced radiologists were asked to rate the realism of US patches. The results show that the experts could not distinguish between CVAE augmented and original US patches. Applying the proposed method in a target detection application improved the performance of a neural network by 41 %. The proposed augmentation method is able to apply realistic deformation to 3D US patches which can be used to enlarge a small data set for usage in deep learning applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Target Tracking in 4D US Based on Template Matching and Target Forecasting Using Spatio-Temporal Autoencoders

Target Tracking in 4D US Based on Template Matching and Targ...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Daniel Wulff Ricardo Sarau Floris Ernst Institute for Robotics and Cognitive Systems University of Lübeck Lübeck Germany

4D ultrasound (US) imaging is a promising imaging modality for diagnosis as well as therapy guidance. It provides volumetric images of soft-tissue structures in real-time without harming the patient with ionizing radiation. Soft tissue targets in the liver are affected by breathing-induced movements resulting in high dimensional motion patterns including deformations affecting the target appearance. Thus, using 4D US for target tracking in radiation therapy to enhance the treatment accuracy is promising but challenging. In this study, a novel approach for target tracking in 4D US is proposed based on predicting the appearance of the target for the next US frame. A spatio-temporal autoencoder as well as a recurrent neural network are implemented and trained based on a labeled 4D US data set with a mean spatial resolution of $1.0\times 0.7\times 1.5$ mm 3 for predicting volumetric target patches and target locations. Four template matching-based tracking algorithms are implemented and evaluated in terms of tracking accuracy. The results indicate that using predicted targets for template matching reduce the tracking error by 62 %, on average. By using a naive template matching algorithm, a mean tracking error of $7.55\pm 12.31$ mm was measured. In contrast, using predicted targets, a mean tracking error of $2.85\pm 2.04$ mm was determined. Since the proposed spatio-temporal autoencoder is independent of the tracking algorithm, it can be combined with any tracking algorithm, making it a promising approach for improving target tracking accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：