1,720,969 research outputs found
Perception and environment modeling in robotic agriculture contexts
No full textPrecision Agriculture (PA) is now a term used throughout the agricultural domain worldwide. It gained popularity and increasing interest from the research community due to the wide range of potential benefits and to the availability of new off-the-shelf sensing technologies. PA methods, indeed, promise to increase the quantity and quality of agricultural outputs, while using less input (e.g., water, energy, fertilizers, pesticides, . . . ). The aim is to save costs, reduce environmental impact and produce more and better food. In this domain, a promising solution that is rapidly growing up is robotic farming. By combining the aerial survey capabilities of Unmanned Aerial Vehicles (UAVs) with multi-purpose agricultural Unmanned Ground Vehicles (UGVs), a robotic system will be able to survey a field from the air, perform a targeted intervention on the ground, and provide detailed information for decision support, all with minimal user intervention. In the last years, despite great progress in automating farming activities by using robotic platforms, most of the existing systems do not provide a sufficient autonomy level. Making farming robots more autonomous brings the benefits of completing tasks faster and adapting to different purposes and farm fields, which make them more useful and increase their profitability. However, making farming robots more autonomous involves increasing their perception and awareness of their surrounding environment. A typical agricultural scenario presents unique characteristics, such as highly repetitive visual and geometrical patterns, and the lack of distinguishable landmarks. These features do not allow to directly apply most of the state-of-the-art perception methods from other robotic domains.
This thesis focuses on perception methods that enable robots to autonomously operate in farming environments, specifically a localization method and a collaborative mapping between aerial and ground robots. They improve the robot perception capabilities by exploiting the unique context-based characteristics of farm fields and by fusing together several heterogeneous sensors. Additionally, this thesis addresses the problem of crop/weed mapping by employing end-to-end visual classifiers. This thesis also presents contributions in perception-based control methods. Such approaches allow the robot to navigate the environment while taking into account the perception constraints. The following is a full list of contributions:
• Development of crop/weed detection and classification algorithms based on deep neural networks.
• A method to summarize a big dataset by information entropy maximization. The manual annotation of the summarized dataset allows the trained network to obtain a similar classification accuracy while sensibly reducing the manual annotation effort.
• A model-based dataset generation method for crop and weed detection. The generated data can be used to both augment or to supplement a real-world training dataset. The synthetic data are made available as open-source.
• A multi-cue positioning system for ground farming robots that fuses several heterogeneous sensors and incorporates context-based characteristics.
• A novel multimodal environment representation that at the same time enhances the key characteristics of the farm field, while filtering out redundant information.
• A collaborative mapping method that registers maps acquired by both aerial and ground vehicles.
• Perception-based control methods that steer the robot to the desired location while satisfying perception constraints.
• A novel temporal registration method that registers maps over time to monitor the evolution of the farm field (work in progress).
Moreover, another important outcome of this thesis is a set of open-source software modules released and datasets generated, which I hope the community will benefit from. The work developed in this thesis has been done following the operating scenario proposed by the Flourish project, in which Sapienza, University of Rome, participated as a consortium partner
An Effective Multi-Cue Positioning System for Agricultural Robotics
Full text linkThe self-localization capability is a crucial component for Unmanned Ground Vehicles (UGV) in farming applications. Approaches based solely on visual cues or on low-cost GPS are easily prone to fail in such scenarios. In this paper, we present a robust and accurate 3D global pose estimation framework, designed to take full advantage of heterogeneous sensory data. By modeling the pose estimation problem as a pose graph optimization, our approach simultaneously mitigates the cumulative drift introduced by motion estimation systems (wheel odometry, visual odometry, ...), and the noise introduced by raw GPS readings. Along with a suitable motion model, our system also integrates two additional types of constraints: (i) a Digital Elevation Model and (ii) a Markov Random Field assumption. We demonstrate how using these additional cues substantially reduces the error along the altitude axis and, moreover, how this benefit spreads to the other components of the state. We report exhaustive experiments combining several sensor setups, showing accuracy improvements ranging from 37% to 76% with respect to the exclusive use of a GPS sensor. We show that our approach provides accurate results even if the GPS unexpectedly changes positioning mode. The code of our system along with the acquired datasets are released with this paper
Augmentation of Sunflower-Weed Segmentation Classification with Unity Generated Imagery Including Near Infrared Sensor Data
Full text linkThis paper presents a solution to create synthetic datasets for deep learning training of convolutional neural networks (CNNs) for plant-weed classification. We use the Unity game engine to create simulated procedural fields of sunflowers and weeds images. The visual imagery is generated by the photo realistic real time rendering engine in Unity. Moreover, we include the regular red, green, and blue (RGB) channels, plus the near infrared (NIR) channel data. This is done by including the aligned textures from both the RGB and the NIR channel separately, since Unity does not simulate NIR illumination.
Our main contribution is the simulation of the sunflower plant including both the RGB and the NIR data, based of a real image dataset with low quality and quantity. This generates improved datasets that can reliably train CNNs for plant-weed segmentation classification. The results obtained achieve high intersection over union (IoU) performance when we build a dataset with a small subset of hand-picked synthetic images. The selected images included high amount of plant and weed pixel data plus the available real images for training.
Our best results show an IoU performance of 76.4%, training the CNN only with sunflower synthetic images. This is close to the results from our previous research where the available real dataset, for sugar beets, had ideal conditions of quality and quantity. Therefore, we conclude that using synthetic imagery including both RGB and NIR data can greatly improve plant-weed segmentation classification IoU performance, when the real images available have limited quality and quantity
Joint Vision-Based Navigation, Control and Obstacle Avoidance for UAVs in Dynamic Environments
Full text linkThis work addresses the problem of coupling vision-based navigation systems for Unmanned Aerial Vehicles (UAVs) with robust obstacle avoidance capabilities. The former problem is solved by maximizing the visibility of the points of interest, while the latter is modeled by means of ellipsoidal repulsive areas. The whole problem is transcribed into an Optimal Control Problem (OCP), and solved in a few milliseconds by leveraging state-of-the-art numerical optimization. The resulting trajectories are well suited for reaching the specified goal location while avoiding obstacles with a safety margin and minimizing the probability of losing the route with the target of interest. Combining this technique with a proper ellipsoid shaping (i.e., by augmenting the shape proportionally with the obstacle velocity or with the obstacle detection uncertainties) results in a robust obstacle avoidance behavior. We validate our approach within extensive simulated experiments that show effective capabilities to satisfy all the constraints even in challenging conditions. We release with this paper the open source implementation
Effective target aware visual navigation for UAVs
No full textIn this paper we propose an effective vision-based navigation method that allows a multirotor vehicle to simultaneously reach a desired goal pose in the environment while constantly facing a target object or landmark. Standard techniques such as Position-Based Visual Servoing (PBVS) and Image-Based Visual Servoing (IBVS) in some cases (e.g., while the multirotor is performing fast maneuvers) do not allow to constantly maintain the line of sight with a target of interest. Instead, we compute the optimal trajectory by solving a non-linear optimization problem that minimizes the target reprojection error while meeting the UAV's dynamic constraints. The desired trajectory is then tracked by means of a real-time Non-linear Model Predictive Controller (NMPC): this implicitly allows the multirotor to satisfy both the required constraints. We successfully evaluate the proposed approach in many real and simulated experiments, making an exhaustive comparison with a standard approach
AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming
Full text linkThe combination of aerial survey capabilities of Unmanned Aerial Vehicles with targeted intervention abilities of agricultural Unmanned Ground Vehicles can significantly improve the effectiveness of robotic systems applied to precision agriculture. In this context, building and updating a common map of the field is an essential but challenging task. The maps built using robots of different types show differences in size, resolution and scale, the associated geolocation data may be inaccurate and biased, while the repetitiveness of both visual appearance and geometric structures found within agricultural contexts render classical map merging techniques ineffective. In this paper we propose AgriColMap, a novel map registration pipeline for that leverages a grid-based multi-modal environment representation which includes a vegetation index map and a Digital Surface Model. We cast the data association problem between maps built from UAVs and UGVs as a multimodal, large displacement dense optical flow estimation. The dominant, coherent flows, selected using a voting scheme, are used as point-to-point correspondences to infer a preliminary non-rigid alignment between the maps. A final refinement is then performed, by exploiting only meaningful parts of the registered maps. We evaluate our system using real world data for 3 fields with different crop species. The results show that our method outperforms several state of the art map registration and matching techniques by a large margin, and has a higher tolerance to large initial misalignments. We release an implementation of the proposed approach along with the acquired datasets with this paper
Non-linear model predictive control with adaptive time-mesh refinement
No full textIn this paper, we present a novel solution for real-time, Non-Linear Model Predictive Control (NMPC) exploiting a time-mesh refinement strategy. The proposed controller formulates the Optimal Control Problem (OCP) in terms of flat outputs over an adaptive lattice. In common approximated OCP solutions, the number of discretization points composing the lattice represents a critical upper bound for real-time applications. The proposed NMPC-based technique refines the initially uniform time horizon by adding time steps with a sampling criterion that aims to reduce the discretization error. This enables a higher accuracy in the initial part of the receding horizon, which is more relevant to NMPC, while keeping bounded the number of discretization points. By combining this feature with an efficient Least Square formulation, our solver is also extremely time-efficient, generating trajectories of multiple seconds within only a few milliseconds. The performance of the proposed approach has been validated in a high fidelity simulation environment, by using an UAV platform. We also released our implementation as open source C++ code
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
