Sensor fusion-based approach for the field robot localization on Rovitis 4.0 vineyard robot

This study proposed an approach for robot localization using data from multiple low-cost sensors with two goals in mind,to produce accurate localization data and to keep the computation as simple as possible.The approach used data from wheel odometry,inertial-motion data from the Inertial Motion Unit(IMU),and a location fix from a Real-Time Kinematics Global Positioning System(RTK GPS).Each of the sensors is prone to errors in some situations,resulting in inaccurate localization.The odometry is affected by errors caused by slipping when turning the robot or putting it on slippery ground.The IMU produces drifts due to vibrations,and RTK GPS does not return to an accurate fix in(semi-)occluded areas.None of these sensors is accurate enough to produce a precise reading for a sound localization of the robot in an outdoor environment.To solve this challenge,sensor fusion was implemented on the robot to prevent possible localization errors.It worked by selecting the most accurate readings in a given moment to produce a precise pose estimation.To evaluate the approach,two different tests were performed,one with robot localization from the robot operating system(ROS)repository and the other with the presented Field Robot Localization.The first did not perform well,while the second did and was evaluated by comparing the location and orientation estimate with ground truth,captured by a hovering drone above the testing ground,which revealed an average error of 0.005 m±0.220 m in estimating the position,and 0.6°±3.5°when estimating orientation.The tests proved that the developed field robot localization is accurate and robust enough to be used on a ROVITIS 4.0 vineyard robot.

Reduction of environmental pollution by using RTK-navigation in soil cultivation

The concept of precision farming is wide,and it represents the efficiency which is achieved with the help of precision.For the navigation of field machines,the RTK(Real Time Kinematic)navigation is needed.In order to verify the positive effects in practice,RTK navigation system equipped with Fentd 828 was applied to test the width of overlap,and fuel and time that could be saved compared with manual driving.The experiment was conducted on two areas of land size of 172 m×58 m with two working machines width 3 m and 6 m.Results indicated that 15.7%of the time and 8.66%of the fuel were saved on a working machine of 3 meters width,and 12.6%of the time and 8.28%of the fuel were saved on a working machine of 6 m width.The width of the overlap represent 10%of the working width of the machine,and with the method of turning,which RTK navigation allows,additional time was saved.Ecological footprint,CO2 emissions and global warming potential(GWP)was estimated under different guiding systems.The largest footprint was related to manual tillage with 3 m width working machine,while estimation on CO2(kg)emissions and GWP obtained the same result.The use of precision agriculture technologies allows better planning and analyzing of working procedures.The air,water and soil pollution are less intensive.

Possibilities and concerns of implementing precision agriculture technologies on small farms in Slovenia

Precision agriculture(PA)through the use and utilization of innovative technologies is a concept in agricultural management that enables long-term efficiency gains,control of unforeseen changes,and a reduction of negative impacts on the environment.However,there are even more reasons and benefits to using precision agriculture technologies(PATs)on farms,but the actual use on small farms is often questionable.The main objective of this research was to evaluate and analyze the current state of PA and its potential on a set of small farms.In addition,a comparison was made between small farms located in less favored areas(LFAs)and more favored areas(MFAs)to find if specific characteristics of the surrounding environment affect the(non-)implementation of these technologies by farm owners,with respect to the given regional possibilities.The result shows that 57.5%of respondents on these farms have never implemented PATs before and 20%are beginners in their respective fields.It was found that there were no statistically significant differences in the integration between fewer LFAs and MFAs technologies and their use in this study.The majority of respondents believe that the main changes need to occur on the level of politics.The results show that the level of cost or initial investment is the main reason and the main obstacle in the implementation of PATs on the surveyed farms.