A Hybrid Cable-Driven Robot for Non-Destructive Leafy Plant Monitoring and Mass Estimation using Structure from Motion

Chen, Gerry; Harsh, Muriki,; Sharkey, Andrew; Pradalier, Cédric; Chen, Yongsheng; Dellaert, Frank

doi:10.1109/icra48891.2023.10161045

Cited by 8 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tomato, as a significant vegetable crop, relies on an accurate assessment of fruit ripeness, which is crucial for determining tomato quality and optimizing harvest yields [1][2][3][4][5] . This research indicates that non-destructive methods for evaluating fruit ripeness have become a prominent area of study in precision agriculture within controlled environments.…”

Section: Introductionmentioning

confidence: 99%

Method for the real-time detection of tomato ripeness using a phenotype robot and RP-YolactEdge

Yuanqiao,

Wenbo,

Chuanyu

et al. 2024

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

In order to address the challenge of non-destructive detection of tomato fruit ripeness in controlled environments, this study proposed a real-time instance segmentation method based on the edge device. This method combined the principles of phenotype robots and machine vision based on deep learning. A compact and remotely controllable phenotype detection robot was employed to acquire precise data on tomato ripeness. The video data were then processed by using an efficient backbone and the FeatFlowNet structure for feature extraction and analysis of key-frame to non-key-frame mapping from video data. To enhance the diversity of training datasets and the generalization of the model, an innovative approach was chosen by using random enhancement techniques. Besides, the PolyLoss optimization technique was applied to further improve the accuracy of the ripeness multi-class detection tasks. Through validation, the method of this study achieved real-time processing speeds of 90.1 fps (RTX 3070Ti) and 65.5 fps (RTX 2060 S), with an average detection accuracy of 97% compared to manually measured results. This is more accurate and efficient than other instance segmentation models according to actual testing in a greenhouse. Therefore, the results of this research can be deployed in edge devices and provide technical support for unmanned greenhouse monitoring devices or fruit-picking robots in facility environments.

show abstract

Section: Introductionmentioning

confidence: 99%

Method for the real-time detection of tomato ripeness using a phenotype robot and RP-YolactEdge

Yuanqiao,

Wenbo,

Chuanyu

et al. 2024

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

show abstract

“…As mentioned, each of these folds is evaluated by using two separate performance indexes-coefficient of determination R 2 and mean absolute percentage error MAPE. These values were selected because they are commonly used in the evaluation of regression models, with R 2 evaluating how well the predicted data follow the trends of the original data across different outputs [38,39], and MAPE defines the absolute difference between the predicted data and the real data across different inputs [40,41]. These two values are utilized because individually they may not provide a good picture of model performance-e.g., a model that has a good variance prediction but a large error will have a good R 2 and a poor MAPE, while the model which follows the data closely, but without taking the trends across inputs into account will demonstrate the opposite.…”

mentioning

confidence: 99%

Regression Model for the Prediction of Total Motor Power Used by an Industrial Robot Manipulator during Operation

Baressi Šegota,

Anđelić,

Štifanić

et al. 2024

Machines

View full text Add to dashboard Cite

Motor power models are a key tool in robotics for modeling and simulations related to control and optimization. The authors collect the dataset of motor power using the ABB IRB 120 industrial robot. This paper applies a multilayer perceptron (MLP) model to the collected dataset. Before the training of MLP models, each of the variables in the dataset is evaluated using the random forest (RF) model, observing two metrics-mean decrease in impurity (MDI) and feature permutation score difference (FP). Pearson’s correlation coefficient was also applied Based on the scores of these values, a total of 15 variables, mainly static variables connected with the position and orientation of the robot, are eliminated from the dataset. The scores demonstrate that while both MLPs achieve good scores, the model trained on the pruned dataset performs better. With the model trained on the pruned dataset achieving R¯2=0.99924,σ=0.00007 and MA¯PE=0.33589,σ=0.00955, the model trained on the original, non-pruned, data achieves R¯2=0.98796,σ=0.00081 and MA¯PE=0.46895,σ=0.05636. These scores show that by eliminating the variables with a low influence from the dataset, a higher scoring model is achieved, and the created model achieves a better generalization performance across five folds used for evaluation.

show abstract

Evaluation of Two Tension Sensors for Cable‐Driven Parallel Manipulators

Gonzalez‐Rodriguez,

Ottaviano,

Rea

2024

Journal of Field Robotics

View full text Add to dashboard Cite

Cable‐driven parallel manipulators (CDPMs) constitute a class of parallel robots in which the frame is connected to the end‐effector through a set of cables. The weight reduction achieved by replacing rigid links with cables, along with their exceptionally large workspace, makes CDPMs suitable for applications such as positioning devices, large surface inspection, motion support systems, and automated storage systems. For effective use in these applications, accurate positioning capabilities are essential, which in turn require accurate measurements of the tension on each cable, and at a sampling rate that is less than or equal to the time constant of the actuator response. This paper first analyses the dynamics of the actuator for an over‐constrained robot and provides concrete values of this constant considering the cable elasticity. Then, it proposes two tension sensors, presents the calibration procedures, and the methodologies to evaluate them in CDPMs so that they can be replicated and subsequently included in another CDPM configuration. They also serve as critical safety devices, continuously monitoring cable tension to detect any operations or situations that are out of range. Ensuring the safe and reliable condition of cables is crucial not only for CDPMs but also for lifting systems, transmission systems, and other mechanical or mechatronic systems that rely on cables.

show abstract

A Hybrid Cable-Driven Robot for Non-Destructive Leafy Plant Monitoring and Mass Estimation using Structure from Motion

Cited by 8 publications

References 32 publications

Method for the real-time detection of tomato ripeness using a phenotype robot and RP-YolactEdge

Method for the real-time detection of tomato ripeness using a phenotype robot and RP-YolactEdge

Regression Model for the Prediction of Total Motor Power Used by an Industrial Robot Manipulator during Operation

Evaluation of Two Tension Sensors for Cable‐Driven Parallel Manipulators

Contact Info

Product

Resources

About