Algorithms for joint operation of service robotic platform and set of UAVs in agriculture tasks

Vu, Quyen; Nguyen, Vinh; Solеnaya, Oksana; Ronzhin, Andrey; Mehmet, Hancer

doi:10.1109/aieee.2017.8270525

Cited by 5 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stitching of anorthophotomap of 120 images of 470 3 425 px each requires less than 6 s even on a laptop with moderate computing resources; hence, it is possible to employ this algorithm in field on commodity hardware. Therefore, the developed system lays necessary foundation for implementation of robotic vehicles systems to use in agricultural areas (Vu et al, 2017b;Ngo et al, 2019).Further research will be aimed to development of efficient robotic vehicles motion algorithms and establishing robot-to-robot communication along the whole path for better interoperability in collective problem solving (Ronzhin et al, 2018;Vu et al, 2017a;Zakharov et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

Automated terrain mapping based on mask R-CNN neural network

Saveliev

Aksamentov

Karasev

2020

IJIUS

View full text Add to dashboard Cite

PurposeThe purpose of this paper is to analyze the development of a novel approach for automated terrain mapping a robotic vehicles path tracing.Design/methodology/approachThe approach includes stitching of images, obtained from unmanned aerial vehicle, based on ORB descriptors, into an orthomosaic image and the GPS-coordinates are binded to the corresponding pixels of the map. The obtained image is fed to a neural network MASK R-CNN for detection and classification regions, which are potentially dangerous for robotic vehicles motion. To visualize the obtained map and obstacles on it, the authors propose their own application architecture. Users can any time edit the present areas or add new ones, which are not intended for robotic vehicles traffic. Then the GPS-coordinates of these areas are passed to robotic vehicles and the optimal route is traced based on this dataFindingsThe developed approach allows revealing impassable regions on terrain map and associating them with GPS-coordinates, whereas these regions can be edited by the user.Practical implicationsThe total duration of the algorithm, including the step with Mask R-CNN network on the same dataset of 120 items was 7.5 s.Originality/valueCreating an orthophotomap from 120 images with image resolution of 470 × 425 px requires less than 6 s on a laptop with moderate computing power, what justifies using such algorithms in the field without any powerful and expensive hardware.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated terrain mapping based on mask R-CNN neural network

Saveliev

Aksamentov

Karasev

2020

IJIUS

View full text Add to dashboard Cite

show abstract

“…This is facilitated by having specialized functions distributed among a larger number of robots, which can then be deployed as and when needed with coordinated communication (Emmi et al, 2014). Of particular interest are swarms composed of aerial and ground robots, which could integrate airborne sensing capabilities with ground-based application tasks, allowing real-time, closed-loop precision irrigation control (Grassi et al, 2017;Vu et al, 2017;Potena et al, 2019).…”

Section: Agricultural Robotsmentioning

confidence: 99%

How much is enough in watering plants? State-of-the-art in irrigation control: Advances, challenges, and opportunities with respect to precision irrigation

Owino

Söffker²

2022

Front. Control Eng.

View full text Add to dashboard Cite

With a rapidly expanding global population placing an ever growing demand on freshwater resources, an increased focus on irrigation techniques tailored to the specific needs of plant appears as one solution to minimize overall freshwater consumption. Precision irrigation methods seek to realize an acceptable compromise between yield and irrigation water consumption through control of the timing and quantity of water supplied to plants. The goal is to maintain the water content of the soil, achieve specific water use efficiency with regard to yield or maintain the physiological response of the plant to water stress within predetermined limits. Reliance on soil moisture measurements to establish irrigation water demand inadequately addresses heterogenous distribution of water in soil. Growing research interest is observed detailing the determination of plant water status directly from physiological responses. This paper reviews irrigation control approaches based on different plant water status assessment techniques. A distinct focus is made on application scale of the discussed control approaches, an aspect that has not been considered intensively enough in previous discussions of irrigation control approaches. A discussion of the observed strengths and shortcomings and technological advances supporting the various methods used to quantify plant water status extends the review. Emerging trends that are likely to have an impact on plant water status determination and optimal timing and quantification of irrigation water requirements are integrated to show latest results. A peek into the future of precision irrigation foresees greater reliance on plant-based signals, both in characterization of the control variable, namely the plant water status, and in generation of controller outputs in terms of quantity and timing.

show abstract

“…Simultaneous localization and mapping (SLAM) is a well-known problem in mobile robotics, which is is considered for a variety of different applications [1,2] and platforms [3,4], with unmanned aerial or ground vehicles being the most widespread robots to use SLAM as part of the navigation loop [5,6,7]. There exists no universal SLAM method suitable for all robotic platforms and applications due to limitations these platforms/applications impose.…”

Section: Introductionmentioning

confidence: 99%

Sparse 3D Point-Cloud Map Upsampling and Noise Removal as a vSLAM Post-Processing Step: Experimental Evaluation

Bokovoy

Yakovlev

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The monocular vision-based simultaneous localization and mapping (vSLAM) is one of the most challenging problem in mobile robotics and computer vision. In this work we study the post-processing techniques applied to sparse 3D point-cloud maps, obtained by featurebased vSLAM algorithms. Map post-processing is split into 2 major steps: 1) noise and outlier removal and 2) upsampling. We evaluate different combinations of known algorithms for outlier removing and upsampling on datasets of real indoor and outdoor environments and identify the most promising combination. We further use it to convert a pointcloud map, obtained by the real UAV performing indoor flight to 3D voxel grid (octo-map) potentially suitable for path planning.Keywords: 3D · point-cloud · outlier removal · upsampling · vSLAM · 3D path planning · sparse map · feature-based vSLAM

show abstract

Algorithms for joint operation of service robotic platform and set of UAVs in agriculture tasks

Cited by 5 publications

References 15 publications

Automated terrain mapping based on mask R-CNN neural network

Automated terrain mapping based on mask R-CNN neural network

How much is enough in watering plants? State-of-the-art in irrigation control: Advances, challenges, and opportunities with respect to precision irrigation

Sparse 3D Point-Cloud Map Upsampling and Noise Removal as a vSLAM Post-Processing Step: Experimental Evaluation

Contact Info

Product

Resources

About