Search

A novel motion planning algorithm for robotic bush trimming is presented. The algorithm is based on an optimal route search over a graph. Differently from other works in robotic surface coverage, it entails both accuracy in the surface sweeping task and smoothness in the motion of the robot arm. The proposed method requires the selection of a custom objective function in the joint space for optimal node traversal scheduling, as well as a kinematically constrained time interpolation. The algorithm was tested in simulation using a model of the Jaco arm and three target bush shapes. Analysis of the simulated motions showed how, differently from classical coverage techniques, the proposed algorithm is able to ensure high tool positioning accuracy while avoiding excessive arm motion jerkiness. It was reported that forbidding manipulation posture changes during the cutting phase of the motion is a key element for task accuracy, leading to a decrease of the tool positioning error up to 90%. Furthermore, the algorithm was validated in a real-world trimming scenario with boxwood bushes. A target of 20 mm accuracy was proposed for a trimming result to be considered successful. Results showed that on average 82% of the bush surface was affected by trimming, and 51% of the trimmed surface was cut within the desired level of accuracy. Despite the fact that the trimming accuracy turned out to be lower than the stated requirements, it was found out this was mainly a consequence of the inaccurate, early stage vision system employed to compute the target trimming surface. By contrast, the trimming motion planning algorithm generated trajectories that smoothly followed their input target and allowed effective branch cutting.

Obstacles are densely spaced in a sweet-pepper crop and they limit the free workspace for a robot that can detach the fruit from the plant. Previous harvesting robots mostly attempted to detach a fruit without using any information of obstacles, thereby reducing the harvest success and damaging the fruit and plant. The hypothesis evaluated in this research is that a robot capable of distinguishing between hard and soft obstacles, and capable of employing this knowledge, improves harvest success and decreases plant damages during harvesting. In line with this hypothesis, the main objective was to develop a sweet-pepper harvesting robot capable of distinguishing between hard and soft obstacles, and of employing this knowledge. As a start, the thesis describes the crop environment of a harvesting robot, reviews all harvesting robots developed for high-value crops, and defines challenges for future development. Based on insights from this review, we explored the ability to distinguish five plant parts. A multi-spectral imaging set-up and artificial lighting were developed and pixels were classified using a decision tree classifier and a feature selection algorithm. Classification performance was found insufficient and therefore post-processing methods were employed to enhance performance and detect plant parts on a blob basis. Still, performance was found insufficient and a focussed study was conducted on stem localization. The imaging set-up and algorithm developed for stem localization were used to provide real stem locations for motion planning simulations. To address the motion planning problem, we developed a new method of selecting the grasp pose of the end-effector. The new method and the stem localization algorithm were both integrated in the harvesting robot, and we tested their contribution to performance. This research is the first to report a performance evaluation of a sweet-pepper harvesting robot tested under greenhouse conditions. The robot was

This research initiated a model-based method to analyse labour in crop production systems and to quantify effects of system changes in order to contribute to effective greenhouse crop cultivation systems with efficient use of human labour and technology. This method was gradually given shape in the discrete event simulation model GWorkS, acronym for Greenhouse Work Simulation. Model based evaluation of labour in crop operations is relatively new in greenhouse horticulture and could allow for quantitative evaluation of existing greenhouse crop production systems, analysis of improvements, and identification of bottlenecks in crop operations. The modelling objective was a flexible and generic approach to quantify effects of production system changes. Cut-rose was selected as a case-study representative for many cut-flowers and fruit vegetables. The first focus was a queueing network model of the actions of a worker harvesting roses in a mobile cultivation system. Data and observations from a state-of-art mobile rose production system were used to validate and test the harvesting model. Model experiments addressed target values of operational parameters for best system performance. The model exposed effects of internal parameters not visible in acquired data. This was illustrated for operator and gutter speed as a function of crop yield. The structure and setup of the GWorkS model was generic where possible and system specific where inevitable. The generic concept was tested by transferring GWorkS to harvesting a greenhouse section in a static growing system for cut-roses and extending it with navigation in the greenhouse, product handling, and multiple operator activity (up to 3 workers). Also for rose harvesting in a static growing system, the model reproduced harvesting accurately. A seven workday validation for an average skilled harvester showed a relative root mean squared error (RRMSE) under 5% for both labour time and harvest rate. A validation for 96

different remote and proximal soil sensors are available today that can scan entire fields and give detailed information on various physical, chemical, mechanical and biological soil properties. The first objective of this thesis was to evaluate different proximal soil sensors available today and to identify their capacity of quantifying soil properties. The second objective of this thesis was to enhance the usefulness of a single sensor system by multiple sensor data fusion that can improve the performance of currently available soil sensors when a single sensor does not function optimally due to certain set of soil and environmental constraints., Op dit moment zijn er verscheidene sensoren ontwikkeld en beschikbaar die van grote (remote) of kleine afstand (proximal) veel gedetailleerde informatie kunnen geven van een veld, zowel van fysische en chemische, maar ook mechanische en biologische bodemeigenschappen. Het eerste doel van dit proefschrift is om een evaluatie te geven van de verschillende ‘proximal’ bodemsensors die op dit moment beschikbaar zijn en een indicatie te geven van hun mogelijkheden om bodemeigenschappen te kwantificeren. Het tweede doel is om te onderzoeken of het nut van één enkel sensorsysteem kan worden verbeterd door dit te koppelen aan het gebruik van meerdere systemen die op een ander principe zijn gebaseerd. De hypothese is dat een enkel systeem niet optimaal kan werken door de belemmeringen die aan een meetsysteem ten grondslag liggen.

Doel van dit proefschrift is het ontwikkelen van een methode die kasontwerpen genereert die geschikt zijn voor de locale klimaat en economische condities. Deze methode moet functioneren voor de verschillende condities die men wereldwijd tegen kan komen. De ontwerpmethode die ontwikkeld is maakt gebruik van computermodellen.

High amounts of manual labor are needed to control volunteer potato plants in arable fields. Due to the high costs, this leads to incomplete control of these weed plants, and they spread diseases like Phytophthora infestans to other fields. This results in higher environmental loads by curative spraying of crop protection chemicals, which is in contradiction to the required decreased use of crop protection chemicals to save the environment. Therefore, the main objective of this thesis was “to develop a system for automated detection and control of volunteer potato plants”. A systematic design approach was used to define a program of requirements and to identify and order possible solutions to accomplish the detection and control. The main requirements were a travel speed of up to 2 m s-1, resolution of control at least 10×10 mm, work under variable natural light conditions, control of volunteer plants > 95%, and undesired control of sugar beet plants < 5%. The design strategy resulted in color and near-infrared machine vision as detection method and a micro-sprayer for application of glyphosate as a result. Furthermore, issues were identified that required further investigation to successfully come to a proof of principle machine. The research was then focused on: - Detection of volunteer potato plants, - Control of volunteer potato plants, - Real-time implementation of integrated detection and control on a proof of principle machine. For the purpose of detection of volunteer potato plants, the narrow band spectral reflectance properties of volunteer potato plants and sugar beet plants were analyzed. Narrow band spectral measurements were done in 2006 and 2007 on two different fields. This resulted in 15 datasets on clay and sand soil. Discriminating wavebands were selected and classified with neural networks and statistical discriminant analysis. A neural network with two hidden neurons performed best for classification. Two sensors were used covering the range fro