Mobile Robot System for Selective Asparagus Harvesting

Šlajpah, Sebastjan; Munih, Marko; Mihelj, Matjaž

doi:10.3390/agronomy13071766

Cited by 4 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the AMRs have zero to no carbon emissions compared to other techniques and heavy equipment used on construction sites. Therefore, these will help reduce the carbon footprints of construction site layout activities [57]. Similarly, the usage of advanced technologies will help in the smoother integration of construction activities into society in line with modern smart cities and society endeavors [58].…”

Section: Conclusion Limitations and Future Directionsmentioning

confidence: 99%

Integrating BIM–IoT and Autonomous Mobile Robots for Construction Site Layout Printing

Iqbal,

Ahmed,

Amin

et al. 2023

Buildings

View full text Add to dashboard Cite

The traditional methods of marking construction site layouts using manual techniques such as chalk lines are prone to human errors, resulting in discrepancies between blueprints and actual layouts. This has serious implications for project delivery, construction, costs and, eventually, project success. However, this issue can be resolved through autonomous robots and construction automation in line with Industry 4.0 and 5.0 goals. Construction automation enables workers to concentrate on the construction phase and not worry about manual site markups. This leads to an enhancement in their productivity. This study aims to improve the floor layout printing technique by introducing a framework that integrates building information modeling (BIM) and the Internet of Things (IoT), i.e., BIM–IoT and autonomous mobile robots (AMR). The development process focuses on three key components: a marking tool, an IoT-based AMR and BIM. The BIM-based tools extract and store coordinates on the cloud platform. The AMR, developed using ESP32 and connected to the Google Firestore cloud platform, leverages IoT technology to retrieve the data and draw site layout lines accordingly. Further, this research presents a prototype of an automated robot capable of accurately printing construction site layouts. A design science research (DSR) method is employed in this study that includes a comprehensive review of the existing literature and usage of AMRs in construction layout printing. Subsequently building upon the extant literature, an AMR is developed and experiments are conducted to evaluate the system’s performance. The experiment reveals that the system’s precision falls within a range of ±15 mm and its angle accuracy is within ±4 degrees. Integrating robotic automation, IoT and BIM technologies enhances the efficiency and precision of construction layout printing. The findings provide insights into the potential benefits of deploying AMRs in construction projects, reducing site layout errors and improving construction productivity. This study also adds to the body of knowledge around construction automation in line with Industry 4.0 and 5.0 endeavors.

show abstract

Section: Conclusion Limitations and Future Directionsmentioning

confidence: 99%

Integrating BIM–IoT and Autonomous Mobile Robots for Construction Site Layout Printing

Iqbal,

Ahmed,

Amin

et al. 2023

Buildings

View full text Add to dashboard Cite

show abstract

“…To determine the most suitable configuration for the proposed system, a preliminary analysis (type synthesis) was conducted, although the details are beyond the scope of this paper. The analysis revealed the four best configurations, consisting of three parallel manipulator configurations based on 3RUU [19], 3PRRR [75], and 3PUU [76,77] arrangements, and one serial manipulator configuration based on PPP arrangements. Considering space and other constraints, the gantry-type PPP serial manipulator was selected for the proposed system.…”

Section: Kinematic Model Of Proposed Vehicle Manipulatormentioning

confidence: 99%

“…These machines also mitigate the dependence on manual labor, addressing the ongoing challenges of labor shortages faced by the agricultural industry. Notable examples of robotic systems that are used in harvesting include asparagus harvesting [19], sweet pepper harvesting [20,21], tomato harvesting [22,23], cucumber harvesting [24], strawberry harvesting [25][26][27], and apple harvesting [28][29][30]. Post-harvesting operations, often critical for preserving the quality and shelf life of harvested crops, have also benefited from robotic innovations [31].…”

Section: Introductionmentioning

confidence: 99%

Designing and Implementing a Versatile Agricultural Robot: A Vehicle Manipulator System for Efficient Multitasking in Farming Operations

2023

View full text Add to dashboard Cite

This paper presents a detailed design of a skid-steering mobile platform with four wheels, along with a Cartesian serial (PPP) manipulator. The aim of this design is to enable the platform to perform various tasks in the agricultural process. The parallel manipulator designed can handle heavy materials in the agricultural field. An experimental robotic harvesting scenario was conducted using parallel manipulator-based end-effectors to handle heavy fruits such as watermelon or muskmelon. The conceptual and component design of the different models was carried out using the Solidworks modeling package. Design specifications and parametric values were utilized during the manufacturing stage. The mobile manipulator was simulated on undulating terrain profiles using ADAMS software. The simulation was analyzed for a duration of 15 s, and graphs depicting the distance, velocity, and acceleration were evaluated over time. Proportional derivative control and proportional derivative-like conventional sliding surface control were applied to the model, and the results were analyzed to assess the error in relation to the input and desired variables. Additionally, a structural analysis was performed to ensure minimal deformation and the highest safety factor for the wheel shaft and L bracket thickness. Throughout the fabrication and prototype development, calibration tests were conducted at various X-, Y-, and Z-axis frame mounting stages. The objective was to minimize the lateral and longitudinal deviation between the parallel linear motion (LM) rails. Once the fabrication and prototype construction was completed, field testing was carried out. All mechanical movements in the lateral and longitudinal directions functioned according to the desired commands given by the Arduino Mega, controlled via a six-channel radio frequency (RF) controller. In the context of agriculture, the grippers utilizing parallel mechanisms were also subjected to testing, demonstrating their ability to handle sizable cylindrical and spherical fruits or vegetables, as well as other relevant objects.

show abstract

A vision transformer‐based robotic perception for early tea chrysanthemum flower counting in field environments

Qi,

Chen,

Gao

2024

Journal of Field Robotics

View full text Add to dashboard Cite

The current mainstream approaches for plant organ counting are based on convolutional neural networks (CNNs), which have a solid local feature extraction capability. However, CNNs inherently have difficulties for robust global feature extraction due to limited receptive fields. Visual transformer (ViT) provides a new opportunity to complement CNNs' capability, and it can easily model global context. In this context, we propose a deep learning network based on a convolution‐free ViT backbone (tea chrysanthemum‐visual transformer [TC‐ViT]) to achieve the accurate and real‐time counting of TCs at their early flowering stage under unstructured environments. First, all cropped fixed‐size original image patches are linearly projected into a one‐dimensional vector sequence and fed into a progressive multiscale ViT backbone to capture multiple scaled feature sequences. Subsequently, the obtained feature sequences are reshaped into two‐dimensional image features and using a multiscale perceptual field module as a regression head to detect the overall scale and density variance. The resulting model was tested on 400 field images in the collected TC test data set, showing that the proposed TC‐ViT achieved the mean absolute error and mean square error of 12.32 and 15.06, with the inference speed of 27.36 FPS (512 × 512 image size) under the NVIDIA Tesla V100 GPU environment. It is also shown that light variation had the greatest effect on TC counting, whereas blurring had the least effect. This proposed method enables accurate counting for high‐density and occlusion objects in field environments and this perception system could be deployed in a robotic platform for selective harvesting and flower phenotyping.

show abstract

Mobile Robot System for Selective Asparagus Harvesting

Cited by 4 publications

References 33 publications

Integrating BIM–IoT and Autonomous Mobile Robots for Construction Site Layout Printing

Integrating BIM–IoT and Autonomous Mobile Robots for Construction Site Layout Printing

Designing and Implementing a Versatile Agricultural Robot: A Vehicle Manipulator System for Efficient Multitasking in Farming Operations

A vision transformer‐based robotic perception for early tea chrysanthemum flower counting in field environments

Contact Info

Product

Resources

About