Browsing by Subject "Agricultural robots"

Now showing 1 - 2 of 2

Crop plant reconstruction and feature extraction based on 3-D vision
(2019) Vázquez Arellano, Manuel; Griepentrog, Hans
3-D imaging is increasingly affordable and offers new possibilities for a more efficient agricul-tural practice with the use of highly advances technological devices. Some reasons contrib-uting to this possibility include the continuous increase in computer processing power, the de-crease in cost and size of electronics, the increase in solid state illumination efficiency and the need for greater knowledge and care of the individual crops. The implementation of 3-D im-aging systems in agriculture is impeded by the economic justification of using expensive de-vices for producing relative low-cost seasonal products. However, this may no longer be true since low-cost 3-D sensors, such as the one used in this work, with advance technical capabili-ties are already available. The aim of this cumulative dissertation was to develop new methodologies to reconstruct the 3-D shape of agricultural environment in order to recognized and quantitatively describe struc-tures, in this case: maize plants, for agricultural applications such as plant breeding and preci-sion farming. To fulfil this aim a comprehensive review of the 3-D imaging systems in agricul-tural applications was done to select a sensor that was affordable and has not been fully inves-tigated in agricultural environments. A low-cost TOF sensor was selected to obtain 3-D data of maize plants and a new adaptive methodology was proposed for point cloud rigid registra-tion and stitching. The resulting maize 3-D point clouds were highly dense and generated in a cost-effective manner. The validation of the methodology showed that the plants were recon-structed with high accuracies and the qualitative analysis showed the visual variability of the plants depending on the 3-D perspective view. The generated point cloud was used to obtain information about the plant parameters (stem position and plant height) in order to quantita-tively describe the plant. The resulting plant stem positions were estimated with an average mean error and standard deviation of 27 mm and 14 mm, respectively. Additionally, meaning-ful information about the plant height profile was also provided, with an average overall mean error of 8.7 mm. Since the maize plants considered in this research were highly heterogeneous in height, some of them had folded leaves and were planted with standard deviations that emulate the real performance of a seeder; it can be said that the experimental maize setup was a difficult scenario. Therefore, a better performance, for both, plant stem position and height estimation could be expected for a maize field in better conditions. Finally, having a 3-D re-construction of the maize plants using a cost-effective sensor, mounted on a small electric-motor-driven robotic platform, means that the cost (either economic, energetic or time) of gen-erating every point in the point cloud is greatly reduced compared with previous researches.
Perception for context awareness of agricultural robots
(2018) Reiser, David; Griepentrog, Hans
Context awareness is one key point for the realisation of robust autonomous systems in unstructured environments like agriculture. Robots need a precise description of their environment so that tasks could be planned and executed correctly. When using a robot system in a controlled, not changing environment, the programmer maybe could model all possible circumstances to get the system reliable. However, the situation gets more complex when the environment and the objects are changing their shape, position or behaviour. Perception for context awareness in agriculture means to detect and classify objects of interest in the environment correctly and react to them. The aim of this cumulative dissertation was to apply different strategies to increase context awareness with perception in mobile robots in agriculture. The objectives of this thesis were to address five aspects of environment perception: (I) test static local sensor communication with a mobile vehicle, (II) detect unstructured objects in a controlled environment, (III) describe the influence of growth stage to algorithm outcomes, (IV) use the gained sensor information to detect single plants and (V) improve the robustness of algorithms under noisy conditions. First, the communication between a static Wireless Sensor Network and a mobile robot was investigated. The wireless sensor nodes were able to send local data from sensors attached to the systems. The sensors were placed in a vineyard and the robot followed automatically the row structure to receive the data. It was possible to localize the single nodes just with the exact robot position and the attenuation model of the received signal strength with triangulation. The precision was 0.6 m and more precise than a provided differential global navigation satellite system signal. The second research area focused on the detection of unstructured objects in point clouds. Therefore, a low-cost sonar sensor was attached to a 3D-frame with millimetre level accuracy to exactly localize the sensor position. With the sensor position and the sensor reading, a 3D point cloud was created. In the workspace, 10 individual plant species were placed. They could be detected automatically with an accuracy of 2.7 cm. An attached valve was able to spray these specific plant positions, which resulted in a liquid saving of 72%, compared to a conventional spraying method, covering the whole crop row area. As plants are dynamic objects, the third objective of describing the plant growth with adequate sensor data, was important to characterise the unstructured agriculture domain. For revering and testing algorithms to the same data, maize rows were planted in a greenhouse. The exact positions of all plants were measured with a total station. Then a robot vehicle was guided through the crop rows and the data of attached sensors were recorded. With the help of the total station, it was possible to track down the vehicle position and to refer all data to the same coordinate frame. The data recording was performed over 7 times over a period of 6 weeks. This created datasets could afterwards be used to assess different algorithms and to test them against different growth changes of the plants. It could be shown that a basic RANSAC line following algorithm could not perform correctly under all growth stages without additional filtering. The fourth paper used this created datasets to search for single plants with a sensor normally used for obstacle avoidance. One tilted laser scanner was used with the exact robot position to create 3D point clouds, where two different methods for single plant detection were applied. Both methods used the spacing to detect single plants. The second method used the fixed plant spacing and row beginning, to resolve the plant positions iteratively. The first method reached detection rates of 73.7% and a root mean square error of 3.6 cm. The iterative second method reached a detection rate of 100% with an accuracy of 2.6 - 3.0 cm. For assessing the robustness of the plant detection, an algorithm was used to detect the plant positions in six different growth stages of the given datasets. A graph-cut based algorithm was used, what improved the results for single plant detection. As the algorithm was not sensitive against overlaying and noisy point clouds, a detection rate of 100% was realised, with an accuracy for the estimated height of the plants with 1.55 cm. The stem position was resolved with an accuracy of 2.05 cm. This thesis showed up different methods of perception for context awareness, which could help to improve the robustness of robots in agriculture. When the objects in the environment are known, it could be possible to react and interact smarter with the environment as it is the case in agricultural robotics. Especially the detection of single plants before the robot reaches them could help to improve the navigation and interaction of agricultural robots.