We present a novel dataset for training and benchmarking semantic SLAM methods. The dataset consists of 200 long sequences, each one containing 3000-5000 data frames. We generate the sequences using realistic home layouts. For that we sample trajectories that simulate motions of a simple home robot, and then render the frames along the trajectories. Each data frame contains a) RGB images generated using physically-based rendering, b) simulated depth measurements, c) simulated IMU readings and d) ground truth occupancy grid of a house. Our dataset serves a wider range of purposes compared to existing datasets and is the first large-scale benchmark focused on the mapping component of SLAM. The dataset is split into train/validation/test parts sampled from different sets of virtual houses. We present benchmarking results for both classical geometry-based [1], [2] and recent learningbased [3] SLAM algorithms, a baseline mapping method [4], semantic segmentation [5] and panoptic segmentation [6]. The dataset and source code for reproducing our experiments will be publicly available at the time of publication.
This article presents the substantiation of application of a robotic platform for express monitoring of the main physical-chemical and agrochemical indicators of soils in field conditions. The concept of the robotic platform provides for its movement in the field along the trajectory given by the IV International Scientific and Practical Conference "Modern S&T Equipments and Problems in Agriculture" 29 program, collection of soil samples and immersion of probes with sensors in them. The main advantage of the proposed method is its high efficiency at low economic costs. Due to the large number of measurements per unit area of the field the estimation accuracy is quite high. At the same time, for one point of the field it is possible to make measurements in different soil horizons. The conceptual scheme of the robotic platform is offered, energy calculations are performed, specific brands of sensors and other devices are selected. The presented materials are the basis for designing, manufacturing and operation of this automated vehicle. The concept of robotic platform operation corresponds to modern digital technologies and precision farming system.
The number of threats to the plants is constantly increasing. The harmful impact of pests and plant diseases costs billions of dollars to the global economics each year. Chemical protection of plants from diseases and insects became an urgent problem in crop production, forestry and parks. The study aimed to develop an effective mobile robot for treating trees and shrubs from insects and diseases by spraying with chemicals. The work used monographic and general scientific research methods. A review of existing designs and technologies, as well as an analysis of publications in leading scientific journals, led to the conclusion that there is no one generally accepted technology for remote diagnosis and spot spraying of single trees and shrubs. Most of the technical means used have significant technical and environmental limitations. Currently, there is no unambiguous decision about which machine and technology to choose for solving the problems of remote diagnostics and spot spraying of single plant objects with a height of 2 to 4 meters. Taking into account the identified requirements, a robotic platform was developed for diagnosing and spot spraying of ornamental and fruit trees and tall shrubs. The developed robot is equipped with the necessary set of equipment for moving around the territory and spraying objects, has an increased cross-country ability, works according to a given program, has a minimal environmental impact, and can record data for diagnosing problems on plants. The proposed universal robot can work in agricultural, forest and urban areas, in warehouses and production facilities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.