Browsing by Person "Reiser, David"

Now showing 1 - 3 of 3

Camera-guided weed hoeing in winter cereals with narrow row distance
(2020) Gerhards, Roland; Kollenda, Benjamin; Machleb, Jannis; Möller, Kurt; Butz, Andreas; Reiser, David; Griegentrog, Hans-Werner
Farmers are facing severe problems with weed competition in cereal crops. Grass-weeds and perennial weed species became more abundant in Europe mainly due to high percentages of cereal crops in cropping systems and reduced tillage practices combined with continuous applications of herbicides with the same mode of action. Several weed populations have evolved resistance to herbicides. Precision weed hoeing may help to overcome these problems. So far, weed hoeing in cereals was restricted to cropping practices with row distances of more than 200 mm. Hoeing in cereals with conventional row distances of 125–170 mm requires the development of automatic steering systems. The objective of this project was to develop a new automatic guidance system for inter-row hoeing using camera-based row detection and automatic side-shift control. Six field studies were conducted in winter wheat to investigate accuracy, weed control efficacy and crop yields of this new hoeing technology. A three-meter prototype and a 6-meter segmented hoe were built and tested at three different speeds in 150 mm seeded winter wheat. The maximum lateral offset from the row center was 22.53 mm for the 3 m wide hoe and 18.42 mm for the 6 m wide hoe. Camera-guided hoeing resulted in 72–96% inter-row and 21–91% intra-row weed control efficacy (WCE). Weed control was 7–15% higher at 8 km h−1 compared to 4 km h−1. WCE could be increased by 14–22% when hoeing was combined with weed harrowing. Grain yields after camera-guided hoeing at 8 km h−1 were 15–76% higher than the untreated control plots and amounted the same level as the weed-free herbicide plots. The study characterizes camera-guided hoeing in cereals as a robust and effective method of weed control.
Development and experimental validation of an agricultural robotic platform with high traction and low compaction
(2023) Reiser, David; Sharipov, Galibjon M.; Hubel, Gero; Nannen, Volker; Griepentrog, Hans W.
Some researchers expect that future agriculture will be automated by swarms of small machines. However, small and light robots have some disadvantages. They have problems generating interaction forces high enough to modify the environment (lift a stone, cultivate the soil, or transport high loads). Additionally, they have limited range and terrain mobility. One option to change this paradigm is to use spikes instead of wheels, which enter the soil to create traction. This allows high interaction forces with the soil, and the process is not limited by the weight of the vehicle. We designed a prototype for mechanical soil cultivation and weeding in agricultural fields and evaluated its efficiency. A static and dynamic test was performed to compare the energy input of the electrical motor with precise measurements of the forces on the attached tool. The results indicate that the prototype can create interaction forces of up to 2082 N with a robot weight of 90 kg. A net traction ratio of 2.31 was reached. The dynamic performance experiment generated pull forces of up to 1335 N for a sustained net traction ratio of 1.48. The overall energy efficiency ratio for the machine reached values of up to 0.54 based on the created draft force and the measured input energy consumption.
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.