Umeå University's logo

umu.sePublications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 28) Show all publications
Kurtser, P., Lowry, S. & Ringdahl, O. (2024). Advances in machine learning for agricultural robots. In: Eldert van Henten; Yael Edan (Ed.), Advances in agri-food robotics: (pp. 103-134). Cambridge: Burleigh Dodds Science Publishing
Open this publication in new window or tab >>Advances in machine learning for agricultural robots
2024 (English)In: Advances in agri-food robotics / [ed] Eldert van Henten; Yael Edan, Cambridge: Burleigh Dodds Science Publishing , 2024, p. 103-134Chapter in book (Refereed)
Abstract [en]

This chapter presents a survey of the advances in using machine learning algorithms for agricultural robotics. The development of machine learning algorithms in the last decade has been astounding, and there has therefore been a rapid increase in the widespread deployment of machine learning algorithms in many domains, such as agricultural robotics. However, there are also major challenges to be overcome in ML for agri-robotics, due to the unavoidable complexity and variability of the operating environments, and the difficulties in accessing the required quantities of relevant training data. This chapter presents an overview of the usage of ML for agri-robotics and discusses the use of ML for data analysis and decision-making for perception and navigation. It outlines the main trends of the last decade in employed algorithms and available data. We then discuss the challenges the field is facing and ways to overcome these challenges.

Place, publisher, year, edition, pages
Cambridge: Burleigh Dodds Science Publishing, 2024
Series
Burleigh dodds series in agricultural science, ISSN 2059-6936, E-ISSN 2059-6944 ; 139
National Category
Computer Sciences Computer Vision and Robotics (Autonomous Systems)
Research subject
computer and systems sciences
Identifiers
urn:nbn:se:umu:diva-223680 (URN)10.19103/AS.2023.0124.04 (DOI)9781801462778 (ISBN)9781801462792 (ISBN)9781801462785 (ISBN)
Available from: 2024-04-23 Created: 2024-04-23 Last updated: 2024-05-14Bibliographically approved
Seeburger, P., Herdenstam, A. P. F., Kurtser, P., Arunachalam, A., Castro Alves, V., Hyötyläinen, T. & Andreasson, H. (2023). Controlled mechanical stimuli reveal novel associations between basil metabolism and sensory quality. Food Chemistry, 404(Part A), Article ID 134545.
Open this publication in new window or tab >>Controlled mechanical stimuli reveal novel associations between basil metabolism and sensory quality
Show others...
2023 (English)In: Food Chemistry, ISSN 0308-8146, E-ISSN 1873-7072, Vol. 404, no Part A, article id 134545Article in journal (Refereed) Published
Abstract [en]

There is an increasing interest in the use of automation in plant production settings. Here, we employed a robotic platform to induce controlled mechanical stimuli (CMS) aiming to improve basil quality. Semi-targeted UHPLC-qToF-MS analysis of organic acids, amino acids, phenolic acids, and phenylpropanoids revealed changes in basil secondary metabolism under CMS, which appear to be associated with changes in taste, as revealed by different means of sensory evaluation (overall liking, check-all-that-apply, and just-about-right analysis). Further network analysis combining metabolomics and sensory data revealed novel links between plant metabolism and sensory quality. Amino acids and organic acids including maleic acid were negatively associated with basil quality, while increased levels of secondary metabolites, particularly linalool glucoside, were associated with improved basil taste. In summary, by combining metabolomics and sensory analysis we reveal the potential of automated CMS on crop production, while also providing new associations between plant metabolism and sensory quality.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Agricultural robotics, Linalool glucoside, Network analysis, Plant metabolomics, Sensomics, Sensory analysis
National Category
Robotics
Identifiers
urn:nbn:se:umu:diva-200354 (URN)10.1016/j.foodchem.2022.134545 (DOI)000873921900006 ()36252376 (PubMedID)2-s2.0-85139833699 (Scopus ID)
Available from: 2022-10-18 Created: 2022-10-18 Last updated: 2022-12-22Bibliographically approved
Gupta, H., Lilienthal, A. J., Andreasson, H. & Kurtser, P. (2023). NDT-6D for color registration in agri-robotic applications. Journal of Field Robotics, 40(6), 1603-1619
Open this publication in new window or tab >>NDT-6D for color registration in agri-robotic applications
2023 (English)In: Journal of Field Robotics, ISSN 1556-4959, E-ISSN 1556-4967, Vol. 40, no 6, p. 1603-1619Article in journal (Refereed) Published
Abstract [en]

Registration of point cloud data containing both depth and color information is critical for a variety of applications, including in-field robotic plant manipulation, crop growth modeling, and autonomous navigation. However, current state-of-the-art registration methods often fail in challenging agricultural field conditions due to factors such as occlusions, plant density, and variable illumination. To address these issues, we propose the NDT-6D registration method, which is a color-based variation of the Normal Distribution Transform (NDT) registration approach for point clouds. Our method computes correspondences between pointclouds using both geometric and color information and minimizes the distance between these correspondences using only the three-dimensional (3D) geometric dimensions. We evaluate the method using the GRAPES3D data set collected with a commercial-grade RGB-D sensor mounted on a mobile platform in a vineyard. Results show that registration methods that only rely on depth information fail to provide quality registration for the tested data set. The proposed color-based variation outperforms state-of-the-art methods with a root mean square error (RMSE) of 1.1-1.6 cm for NDT-6D compared with 1.1 - 2.3 cm for other color-information-based methods and 1.2 - 13.7 cm for noncolor-information-based methods. The proposed method is shown to be robust against noises using the TUM RGBD data set by artificially adding noise present in an outdoor scenario. The relative pose error (RPE) increased 14% for our method compared to an increase of 75% for the best-performing registration method. The obtained average accuracy suggests that the NDT-6D registration methods can be used for in-field precision agriculture applications, for example, crop detection, size-based maturity estimation, and growth modeling.

Place, publisher, year, edition, pages
John Wiley & Sons, 2023
Keywords
agricultural robotics, color pointcloud, in‐field sensing, machine perception, RGB‐D registration, stereo IR, vineyardJ
National Category
Robotics Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer Science
Identifiers
urn:nbn:se:umu:diva-208383 (URN)10.1002/rob.22194 (DOI)000991774400001 ()2-s2.0-85159844423 (Scopus ID)
Funder
EU, Horizon 2020
Available from: 2023-05-23 Created: 2023-05-23 Last updated: 2023-11-13Bibliographically approved
Kurtser, P. & Lowry, S. (2023). RGB-D datasets for robotic perception in site-specific agricultural operations: a survey. Computers and Electronics in Agriculture, 212, Article ID 108035.
Open this publication in new window or tab >>RGB-D datasets for robotic perception in site-specific agricultural operations: a survey
2023 (English)In: Computers and Electronics in Agriculture, ISSN 0168-1699, E-ISSN 1872-7107, Vol. 212, article id 108035Article in journal (Refereed) Published
Abstract [en]

Fusing color (RGB) images and range or depth (D) data in the form of RGB-D or multi-sensory setups is a relatively new but rapidly growing modality for many agricultural tasks. RGB-D data have potential to provide valuable information for many agricultural tasks that rely on perception, but collection of appropriate data and suitable ground truth information can be challenging and labor-intensive, and high-quality publicly available datasets are rare. This paper presents a survey of the existing RGB-D datasets available for agricultural robotics, and summarizes key trends and challenges in this research field. It evaluates the relative advantages of the commonly used sensors, and how the hardware can affect the characteristics of the data collected. It also analyzes the role of RGB-D data in the most common vision-based machine learning tasks applied to agricultural robotic operations: visual recognition, object detection, and semantic segmentation, and compares and contrasts methods that utilize 2-D and 3-D perceptual data.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
3D perception, Color point clouds, Datasets, Computer vision, Agricultural robotics
National Category
Computer Vision and Robotics (Autonomous Systems) Robotics
Research subject
Computer Science
Identifiers
urn:nbn:se:umu:diva-213053 (URN)10.1016/j.compag.2023.108035 (DOI)001059437100001 ()2-s2.0-85172469543 (Scopus ID)
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-10-16Bibliographically approved
Gupta, H., Andreasson, H., Lilienthal, A. J. & Kurtser, P. (2023). Robust scan registration for navigation in forest environment using low-resolution LiDAR sensors. Sensors, 23(10), Article ID 4736.
Open this publication in new window or tab >>Robust scan registration for navigation in forest environment using low-resolution LiDAR sensors
2023 (English)In: Sensors, E-ISSN 1424-8220, Vol. 23, no 10, article id 4736Article in journal (Refereed) Published
Abstract [en]

Automated forest machines are becoming important due to human operators’ complex and dangerous working conditions, leading to a labor shortage. This study proposes a new method for robust SLAM and tree mapping using low-resolution LiDAR sensors in forestry conditions. Our method relies on tree detection to perform scan registration and pose correction using only low-resolution LiDAR sensors (16Ch, 32Ch) or narrow field of view Solid State LiDARs without additional sensory modalities like GPS or IMU. We evaluate our approach on three datasets, including two private and one public dataset, and demonstrate improved navigation accuracy, scan registration, tree localization, and tree diameter estimation compared to current approaches in forestry machine automation. Our results show that the proposed method yields robust scan registration using detected trees, outperforming generalized feature-based registration algorithms like Fast Point Feature Histogram, with an above 3 m reduction in RMSE for the 16Chanel LiDAR sensor. For Solid-State LiDAR the algorithm achieves a similar RMSE of 3.7 m. Additionally, our adaptive pre-processing and heuristic approach to tree detection increased the number of detected trees by 13% compared to the current approach of using fixed radius search parameters for pre-processing. Our automated tree trunk diameter estimation method yields a mean absolute error of 4.3 cm (RSME = 6.5 cm) for the local map and complete trajectory maps.

Place, publisher, year, edition, pages
MDPI, 2023
Keywords
tree segmentation, LiDAR mapping, forest inventory, SLAM, forestry robotics, scan registration
National Category
Robotics Forest Science
Research subject
Computer Science; English
Identifiers
urn:nbn:se:umu:diva-208254 (URN)10.3390/s23104736 (DOI)000997887900001 ()2-s2.0-85160406537 (Scopus ID)
Funder
EU, Horizon 2020, 858101
Available from: 2023-05-15 Created: 2023-05-15 Last updated: 2023-09-05Bibliographically approved
Herdenstam, A. P. F., Kurtser, P., Swahn, J. & Arunachalam, A. (2022). Nature versus machine: a pilot study using a semi-trained culinary panel to perform sensory evaluation of robot-cultivated basil affected by mechanically induced stress. International Journal of Gastronomy and Food Science, 29, Article ID 100578.
Open this publication in new window or tab >>Nature versus machine: a pilot study using a semi-trained culinary panel to perform sensory evaluation of robot-cultivated basil affected by mechanically induced stress
2022 (English)In: International Journal of Gastronomy and Food Science, ISSN 1878-450X, E-ISSN 1878-4518, Vol. 29, article id 100578Article in journal (Refereed) Published
Abstract [en]

In this paper we present a multidisciplinary approach combining technical practices with sensory data to optimize cultivation practices for production of plants using sensory evaluation and further the how it affects nutritional content. We apply sensory evaluation of plants under mechanical stress, in this case robot cultivated basil. Plant stress is a research field studying plants' reactions to suboptimal conditions leading to effects on growth, crop yield, and resilience to harsh environmental conditions. Some of the effects induced by mechanical stress have been shown to be beneficial, both in futuristic commercial growing paradigms (e.g., vertical farming), as well as in altering the plant's nutritional content. This pilot study uses established sensory methods such as Liking, Just-About-Right (JAR) and Check-All-That-Apply (CATA) to study the sensory effect of mechanical stress on cropped basil induced by a specially developed robotic platform. Three different kinds of cropped basil were evaluated: (a) mechanically stressed-robot cultivated, (b) non-stressed -robot cultivated from the same cropping bed (reference); and (c) a commercially organic produced basil. We investigated liking, critical attributes, sensory profile, and the use of a semi-trained culinary panel to make any presumptions on consumer acceptance. The semi-trained panel consisted of 24 culinary students with experience of daily judging sensory aspects of specific food products and cultivated crops. The underlying goal is to assess potential market aspects related to novel mechanical cultivation systems. Results shows that basil cropped in a controlled robot cultivated platform resulted in significantly better liking compared to commercially organic produced basil. Results also showed that mechanical stress had not negatively affected the sensory aspects, suggesting that eventual health benefits eating stressed plants do not come at the expense of the sensory experience.

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Robot-cultivation, Mechanical stress, Morphology, Liking, Just-about-right (JAR), Check-all-that-apply (CATA)
National Category
Social Sciences Interdisciplinary Computer Vision and Robotics (Autonomous Systems)
Research subject
Culinary Arts and Meal Science
Identifiers
urn:nbn:se:umu:diva-198795 (URN)10.1016/j.ijgfs.2022.100578 (DOI)
Available from: 2022-08-24 Created: 2022-08-24 Last updated: 2022-08-25Bibliographically approved
Herdenstam, A. P. F., Kurtser, P., Swahn, J., Arunachalam, A. & Edberg, K.-M. (2022). Nature versus machine: Sensory evaluation of robot-cultivated basil affected by mechanically induced stress. In: : . Paper presented at EUROSENSE 2022: A Sense of Earth. 10th European Conference on Sensory and Consumer Research, Turku, Finland, September 13-16, 2022. Elsevier, Article ID P2.121.
Open this publication in new window or tab >>Nature versus machine: Sensory evaluation of robot-cultivated basil affected by mechanically induced stress
Show others...
2022 (English)Conference paper, Poster (with or without abstract) (Other academic)
Place, publisher, year, edition, pages
Elsevier, 2022
National Category
Social Sciences Interdisciplinary Biological Systematics Robotics
Research subject
Culinary Arts and Meal Science
Identifiers
urn:nbn:se:umu:diva-200355 (URN)
Conference
EUROSENSE 2022: A Sense of Earth. 10th European Conference on Sensory and Consumer Research, Turku, Finland, September 13-16, 2022
Available from: 2022-10-18 Created: 2022-10-18 Last updated: 2022-10-19Bibliographically approved
Kurtser, P., Castro Alves, V., Arunachalam, A., Sjöberg, V., Hanell, U., Hyötyläinen, T. & Andreasson, H. (2021). Development of novel robotic platforms for mechanical stress induction, and their effects on plant morphology, elements, and metabolism. Scientific Reports, 11(1), Article ID 23876.
Open this publication in new window or tab >>Development of novel robotic platforms for mechanical stress induction, and their effects on plant morphology, elements, and metabolism
Show others...
2021 (English)In: Scientific Reports, E-ISSN 2045-2322, Vol. 11, no 1, article id 23876Article in journal (Refereed) Published
Abstract [en]

This research evaluates the effect on herbal crops of mechanical stress induced by two specially developed robotic platforms. The changes in plant morphology, metabolite profiles, and element content are evaluated in a series of three empirical experiments, conducted in greenhouse and CNC growing bed conditions, for the case of basil plant growth. Results show significant changes in morphological features, including shortening of overall stem length by up to 40% and inter-node distances by up to 80%, for plants treated with a robotic mechanical stress-induction protocol, compared to control groups. Treated plants showed a significant increase in element absorption, by 20-250% compared to controls, and changes in the metabolite profiles suggested an improvement in plants' nutritional profiles. These results suggest that repetitive, robotic, mechanical stimuli could be potentially beneficial for plants' nutritional and taste properties, and could be performed with no human intervention (and therefore labor cost). The changes in morphological aspects of the plant could potentially replace practices involving chemical treatment of the plants, leading to more sustainable crop production.

Place, publisher, year, edition, pages
Springer Nature, 2021
National Category
Botany
Identifiers
urn:nbn:se:umu:diva-198831 (URN)10.1038/s41598-021-02581-9 (DOI)000729935300061 ()34903776 (PubMedID)2-s2.0-85121055500 (Scopus ID)
Note

Funding agency:

Örebro University

Available from: 2022-08-25 Created: 2022-08-25 Last updated: 2022-09-15Bibliographically approved
van Herck, L., Kurtser, P., Wittemans, L. & Edan, Y. (2020). Crop design for improved robotic harvesting: a case study of sweet pepper harvesting. Biosystems Engineering, 192, 294-308
Open this publication in new window or tab >>Crop design for improved robotic harvesting: a case study of sweet pepper harvesting
2020 (English)In: Biosystems Engineering, ISSN 1537-5110, E-ISSN 1537-5129, Vol. 192, p. 294-308Article in journal (Refereed) Published
Abstract [en]

Current harvesting robots have limited performance, due to the unstructured and dynamic nature of both the target crops and their environment. Efforts to date focus on improving sensing and robotic systems. This paper presents a parallel approach, to "design" the crop and its environment to best fit the robot, similar to robotic integration in industrial robot deployments.

A systematic methodology to select and modify the crop "design" (crop and environment) to improve robotic harvesting is presented. We define crop-dependent robotic features for successful harvesting (e.g., visibility, reachability), from which associated crop features are identified (e.g., crop density, internode length). Methods to influence the crop features are derived (e.g., cultivation practices, climate control) along with a methodological approach to evaluate the proposed designs. A case study of crop "design" for robotic sweet pepper harvesting is presented, with statistical analyses of influential parameters. Since comparison of the multitude of existing crops and possible modifications is impossible due to complexity and time limitations, a sequential field experimental setup is planned. Experiments over three years, 10 cultivars, two climate control conditions, two cultivation techniques and two artificial illumination types were performed. Results showed how modifying the crop effects the crops characteristics influencing robotic harvesting by increased visibility and reachability. The systematic crop "design" approach also led to robot design recommendations. The presented "engineering" the crop "design" framework highlights the importance of close synergy between crop and robot design achieved by strong collaboration between robotic and agronomy experts resulting in improved robotic harvesting performance.

Place, publisher, year, edition, pages
Elsevier, 2020
Keywords
Crop design, Harvesting robot, Sweet pepper, Agricultural robotics, Crop engineering, Robot design
National Category
Agricultural Science, Forestry and Fisheries Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer Science
Identifiers
urn:nbn:se:umu:diva-198794 (URN)10.1016/j.biosystemseng.2020.01.021 (DOI)000526112100021 ()2-s2.0-85079874831 (Scopus ID)
Note

This research was supported by the European Commission (SWEEPER GA nr. 644313), and by Ben-Gurion University of the Negev through the Helmsley Charitable Trust, the Agricultural, Biological and Cognitive Robotics Initiative, the Marcus Endowment Fund, and the Rabbi W. Gunther Plaut Chair in Manufacturing Engineering. We acknowledge the SWEEPER partners who contributed general technical support for data collection.

Available from: 2022-08-24 Created: 2022-08-24 Last updated: 2022-08-25Bibliographically approved
Arad, B., Balendonck, J., Barth, R., Ben-Shahar, O., Edan, Y., Hellström, T., . . . van Tuijl, B. (2020). Development of a sweet pepper harvesting robot. Journal of Field Robotics, 37(6), 1027-1039
Open this publication in new window or tab >>Development of a sweet pepper harvesting robot
Show others...
2020 (English)In: Journal of Field Robotics, ISSN 1556-4959, E-ISSN 1556-4967, Vol. 37, no 6, p. 1027-1039Article in journal (Refereed) Published
Abstract [en]

This paper presents the development, testing and validation of SWEEPER, a robot for harvesting sweet pepper fruit in greenhouses. The robotic system includes a six degrees of freedom industrial arm equipped with a specially designed end effector, RGB-D camera, high-end computer with graphics processing unit, programmable logic controllers, other electronic equipment, and a small container to store harvested fruit. All is mounted on a cart that autonomously drives on pipe rails and concrete floor in the end-user environment. The overall operation of the harvesting robot is described along with details of the algorithms for fruit detection and localization, grasp pose estimation, and motion control. The main contributions of this paper are the integrated system design and its validation and extensive field testing in a commercial greenhouse for different varieties and growing conditions. A total of 262 fruits were involved in a 4-week long testing period. The average cycle time to harvest a fruit was 24 s. Logistics took approximately 50% of this time (7.8 s for discharge of fruit and 4.7 s for platform movements). Laboratory experiments have proven that the cycle time can be reduced to 15 s by running the robot manipulator at a higher speed. The harvest success rates were 61% for the best fit crop conditions and 18% in current crop conditions. This reveals the importance of finding the best fit crop conditions and crop varieties for successful robotic harvesting. The SWEEPER robot is the first sweet pepper harvesting robot to demonstrate this kind of performance in a commercial greenhouse.

Place, publisher, year, edition, pages
John Wiley & Sons, 2020
Keywords
agriculture, computer vision, field test, motion control, real-world conditions, robotics
National Category
Robotics
Research subject
Computer Science; Mechanical Engineering
Identifiers
urn:nbn:se:umu:diva-167658 (URN)10.1002/rob.21937 (DOI)000509488400001 ()2-s2.0-85078783496 (Scopus ID)
Funder
EU, Horizon 2020, 644313
Available from: 2020-01-31 Created: 2020-01-31 Last updated: 2023-03-24Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4685-379X

Search in DiVA

Show all publications