SearcharxivSearch

arXiv subjects

Alireza Ahmadi

Publications and source records attributed to Alireza Ahmadi.

15 recordsLinked to original sources

Diffeological Tangent Spaces and Distributional Linearization for Lifted Euler--Reynolds Limits

We develop a diffeological framework for the geometry of Euler--Reynolds subsolutions of the incompressible Euler equations. Passing to a lifted formulation in which the velocity, quadratic flux, and trace-free Reynolds stress are treated as independent variables, we construct a diffeological limit space obtained as the weak closure of smooth strict subsolutions. Its internal tangent spaces provide an intrinsic notion of infinitesimal deformation despite the absence of any underlying manifold structure. We prove that ambient realizations of internal tangent vectors satisfy the linearized Euler--Reynolds equations in the sense of distributions, thereby establishing a natural first-order theory for lifted weak limit spaces. We further describe the tangent directions compatible with the Euler locus and identify the kernels of the natural velocity, flux, and full-state observables. These results distinguish observable perturbations from hidden stress-gauge directions that encode infinitesimal variations of the Reynolds stress. Finally, we introduce a finite-mixture model for lifted Euler--Reynolds states whose differential realizes explicit tangent directions and relates Reynolds stress to infinitesimal phase splitting. Under a genericity assumption, every deviatoric stress tensor is realized by such a first-order mixture defect, yielding phase-counting bounds and a minimality result for the observable hierarchy.

math.AP

Diffeologies on Locally Convex Spaces and Smooth Multiplication of Distributions

We investigate the canonical and $c^\infty$-diffeologies on Hausdorff locally convex spaces and their applications to Schwartz distributions. We prove that a Hausdorff locally convex space, endowed with its canonical diffeology, is convenient if and only if the canonical map to its internal tangent space at each point is a linear isomorphism. This yields a geometric characterization of Mackey completeness. We also compare several natural diffeologies on locally convex spaces and identify conditions under which they are preserved under completion, dualization, and the formation of inductive limits. As an application, we realize the space of microlocally multipliable distributions as a diffeological colimit and show that Hörmander-admissible multiplication is smooth. This establishes a framework for nonlinear distribution theory beyond the classical manifold setting.

math.DG

BonnBot-I: A Precise Weed Management and Crop Monitoring Platform

Cultivation and weeding are two of the primary tasks performed by farmers today. A recent challenge for weeding is the desire to reduce herbicide and pesticide treatments while maintaining crop quality and quantity. In this paper, we introduce BonnBot-I a precise weed management platform which can also performs field monitoring. Driven by crop monitoring approaches that can accurately locate and classify plants (weed and crop) we further improve their performance by fusing the platform available GNSS and wheel odometry. This improves the tracking accuracy of our crop monitoring approach from a normalized average error of 8.3% to 3.5%, evaluated on a new publicly available corn dataset. We also present a novel arrangement of weeding tools mounted on linear actuators evaluated in simulated environments. We replicate weed distributions from a real field, using the results from our monitoring approach, and show the validity of our work-space division techniques which require significantly less movement (a 50% reduction) to achieve similar results. Overall, BonnBot-I is a significant step forward in precise weed management with a novel method of selectively spraying and controlling weeds in an arable field.

cs.RO

BonnBot-I Plus: A Bio-diversity Aware Precise Weed Management Robotic Platform

In this article, we focus on the critical tasks of plant protection in arable farms, addressing a modern challenge in agriculture: integrating ecological considerations into the operational strategy of precision weeding robots like \bbot. This article presents the recent advancements in weed management algorithms and the real-world performance of \bbot\ at the University of Bonn's Klein-Altendorf campus. We present a novel Rolling-view observation model for the BonnBot-Is weed monitoring section which leads to an average absolute weeding performance enhancement of $3.4\%$. Furthermore, for the first time, we show how precision weeding robots could consider bio-diversity-aware concerns in challenging weeding scenarios. We carried out comprehensive weeding experiments in sugar-beet fields, covering both weed-only and mixed crop-weed situations, and introduced a new dataset compatible with precision weeding. Our real-field experiments revealed that our weeding approach is capable of handling diverse weed distributions, with a minimal loss of only $11.66\%$ attributable to intervention planning and $14.7\%$ to vision system limitations highlighting required improvements of the vision system.

cs.RO

A remark on stability and the D-topology of mapping spaces

We discuss how stability is related to the D-topology of mapping spaces, equipped with the functional diffeology. Indeed, we show that stable classes of mapping spaces are D-open. After a reformulation of the classical stability theorem of manifolds with respect to the D-topology, we prove a version of the stability theorem in the class of diffeological étale manifolds.

math.DG

Submersions, immersions, and étale maps in diffeology

Although structural maps such as subductions and inductions appear naturally in diffeology, one of the challenges is providing suitable analogous for submersions, immersions, and étale maps (i.e., local diffeomorphisms) consistent with the classical versions of these maps between manifolds. In this paper, we consider diffeological submersions, immersions, and étale maps as an adaptation of these maps to diffeology by a nonlinear approach. In the case of manifolds, there is no difference between the classical and diffeological versions of these maps. Moreover, we study their diffeological properties from different aspects in a systematic fashion with respect to the germs of plots. We also discuss notions of embeddings of diffeological spaces and regard diffeological embeddings similar to those of manifolds. In particular, we show that diffeological embeddings are inductions. In order to characterize the considered maps from their linear behaviors, we introduce a class of diffeological spaces, so-called diffeological étale manifolds, which not only contains the usual manifolds but also includes irrational tori. We state and prove versions of the rank and implicit function theorems, as well as the fundamental theorem on flows in this class. As an application, we use the results of this work to facilitate the computations of the internal tangent spaces and diffeological dimensions in a few interesting cases.

math.DG

On diffeologies for power sets and measures

We consider a differential geometric setting on power sets and Borel algebras. Our chosen framework is based on diffeologies, and we make a link between the various diffeological structures that we propose, having in mind set-valued maps, relations, set-valued gradients, differentiable measures, and shape analysis. This work intends to establish rigorous properties on sample diffeologies that seem of interest to us.

math.DG

Diffeological Čech cohomology

Motivated by problems in which data are given over covering generating families, we suggest a new cohomology theory for diffeological spaces, called diffeological Čech cohomology, which is an exact $ \partial $-functor of the section functor for sheaves on diffeological spaces. As applications, under the situations of a setup, i) the generalized Mayer-Vietoris sequence for a diffeological space is established; ii) a version of the de Rham theorem is obtained, which connects diffeological Čech cohomology to the de Rham cohomology. Moreover, we characterize the isomorphism classes of diffeological fiber, principal, and vector bundles as (non-abelian) diffeological Čech cohomology in degree 1.

math.DG

Towards Autonomous Visual Navigation in Arable Fields

Autonomous navigation of a robot in agricultural fields is essential for every task from crop monitoring to weed management and fertilizer application. Many current approaches rely on accurate GPS, however, such technology is expensive and also prone to failure (e.g. through lack of coverage). As such, autonomous navigation through sensors that can interpret their environment (such as cameras) is important to achieve the goal of autonomy in agriculture. In this paper, we introduce a purely vision-based navigation scheme that is able to reliably guide the robot through row-crop fields without manual intervention. Independent of any global localization or mapping, this approach is able to accurately follow the crop-rows and switch between the rows, only using onboard cameras. With the help of a novel crop-row detection and a novel crop-row switching technique, our navigation scheme can be deployed in a wide range of fields with different canopy types in various growth stages with limited parameter tuning, creating a crop agnostic navigation approach. We have extensively evaluated our approach in three different fields under various illumination conditions using our agricultural robotic platform (BonnBot-I). For navigation, our approach is evaluated on five crop types and achieves an average navigation accuracy of 3.82cm relative to manual teleoperation.

cs.RO

Explicitly incorporating spatial information to recurrent networks for agriculture

In agriculture, the majority of vision systems perform still image classification. Yet, recent work has highlighted the potential of spatial and temporal cues as a rich source of information to improve the classification performance. In this paper, we propose novel approaches to explicitly capture both spatial and temporal information to improve the classification of deep convolutional neural networks. We leverage available RGB-D images and robot odometry to perform inter-frame feature map spatial registration. This information is then fused within recurrent deep learnt models, to improve their accuracy and robustness. We demonstrate that this can considerably improve the classification performance with our best performing spatial-temporal model (ST-Atte) achieving absolute performance improvements for intersection-over-union (IoU[%]) of 4.7 for crop-weed segmentation and 2.6 for fruit (sweet pepper) segmentation. Furthermore, we show that these approaches are robust to variable framerates and odometry errors, which are frequently observed in real-world applications.

cs.RO

Registration Techniques for Deformable Objects

In general, the problem of non-rigid registration is about matching two different scans of a dynamic object taken at two different points in time. These scans can undergo both rigid motions and non-rigid deformations. Since new parts of the model may come into view and other parts get occluded in between two scans, the region of overlap is a subset of both scans. In the most general setting, no prior template shape is given and no markers or explicit feature point correspondences are available. So, this case is a partial matching problem that takes into account the assumption that consequent scans undergo small deformations while having a significant amount of overlapping area [28]. The problem which this thesis is addressing is mapping deforming objects and localizing cameras in the environment at the same time.

cs.CV

Virtual Temporal Samples for Recurrent Neural Networks: applied to semantic segmentation in agriculture

This paper explores the potential for performing temporal semantic segmentation in the context of agricultural robotics without temporally labelled data. We achieve this by proposing to generate virtual temporal samples from labelled still images. By exploiting the relatively static scene and assuming that the robot (camera) moves we are able to generate virtually labelled temporal sequences with no extra annotation effort. Normally, to train a recurrent neural network (RNN), labelled samples from a video (temporal) sequence are required which is laborious and has stymied work in this direction. By generating virtual temporal samples, we demonstrate that it is possible to train a lightweight RNN to perform semantic segmentation on two challenging agricultural datasets. Our results show that by training a temporal semantic segmenter using virtual samples we can increase the performance by an absolute amount of $4.6$ and $4.9$ on sweet pepper and sugar beet datasets, respectively. This indicates that our virtual data augmentation technique is able to accurately classify agricultural images temporally without the use of complicated synthetic data generation techniques nor with the overhead of labelling large amounts of temporal sequences.

cs.CV

An Empirical Study on User Reviews Targeting Mobile Apps' Security & Privacy

Application markets provide a communication channel between app developers and their end-users in form of app reviews, which allow users to provide feedback about the apps. Although security and privacy in mobile apps are one of the biggest issues, it is unclear how much people are aware of these or discuss them in reviews. In this study, we explore the privacy and security concerns of users using reviews in the Google Play Store. For this, we conducted a study by analyzing around 2.2M reviews from the top 539 apps of this Android market. We found that 0.5\% of these reviews are related to the security and privacy concerns of the users. We further investigated these apps by performing dynamic analysis which provided us valuable insights into their actual behaviors. Based on the different perspectives, we categorized the apps and evaluated how the different factors influence the users' perception of the apps. It was evident from the results that the number of permissions that the apps request plays a dominant role in this matter. We also found that sending out the location can affect the users' thoughts about the app. The other factors do not directly affect the privacy and security concerns for the users.

cs.CR

Visual Servoing-based Navigation for Monitoring Row-Crop Fields

Autonomous navigation is a pre-requisite for field robots to carry out precision agriculture tasks. Typically, a robot has to navigate through a whole crop field several times during a season for monitoring the plants, for applying agrochemicals, or for performing targeted intervention actions. In this paper, we propose a framework tailored for navigation in row-crop fields by exploiting the regular crop-row structure present in the fields. Our approach uses only the images from on-board cameras without the need for performing explicit localization or maintaining a map of the field and thus can operate without expensive RTK-GPS solutions often used in agriculture automation systems. Our navigation approach allows the robot to follow the crop-rows accurately and handles the switch to the next row seamlessly within the same framework. We implemented our approach using C++ and ROS and thoroughly tested it in several simulated environments with different shapes and sizes of field. We also demonstrated the system running at frame-rate on an actual robot operating on a test row-crop field. The code and data have been published.

cs.RO

Role of Non-quantized Fluxes in Coulombic and Casimir Scaling Regimes of the Thick Center Vortex Potentials

We discuss a non-quantized Gaussian flux limited to vary in a specific region of space which describes the Coulombic potential as well as confinement at intermediate distances for color potentials in various representations. Our calculations show if uncorrelated vortices are not quantized with center elements, the N-ality dependence of asymptotic string tensions is lost while the ratio of the Coulombic strengths and intermediate string tensions are in agreement with Casimir scaling. Using both uncorrelated quantized and non-quantized fluxes in the potential between static color sources results in the correct N-ality dependence at large distances and very good agreement with Casimir scaling at short and intermediate distances.

hep-ph