Field Of Autonomous Robots Research Articles

German sugar beet farmers’ intention to use autonomous field robots for seeding and weeding

Robotic weed control is not yet widely adopted, despite its technological availability and proven economics and sustainability in crop cultivation by replacing seasonal labor and synthetic pesticides. This impedes technologically enabled changes toward more sustainable agricultural systems. Given that adopting robotics for the weeding process requires changing existing systems, farmers' appraisals for the new and the current weeding technology may constitute barriers. However, this dualism has been largely ignored by previous studies. Based on a duality approach, we investigate farmers’ beliefs, and adaptive and maladaptive appraisals of current and new robotic weeding in sugar beets. The main variable of interest is their behavioral intention to adopt weeding robots. For our sample of German farmers, we identify the main enablers perceived efficacy of the robots and social norms. The main barrier are maladaptive rewards from traditional weeding. We recommend policy incentives to promote large-scale uptake of new and more sustainable robotic technologies. To improve efficacy perceptions of such robotic systems public demonstrations/talks are mostly relevant. Maladaptive rewards can be reduced, for instance, by notifying about the dependency of the current practices on future availability of synthetic inputs or seasonal workers.

Enhancing 3D object detection by using neural network with self-adaptive thresholding

Robust 3D object detection remains a pivotal concern in the domain of autonomous field robotics. Despite notable enhancements in detection accuracy across standard datasets, real-world urban environments, characterized by their unstructured and dynamic nature, frequently precipitate an elevated incidence of false positives, thereby undermining the reliability of existing detection paradigms. In this context, our study introduces an advanced post-processing algorithm that modulates detection thresholds dynamically relative to the distance from the ego object. Traditional perception systems typically utilize a uniform threshold, which often leads to decreased efficacy in detecting distant objects. In contrast, our proposed methodology employs a Neural Network with a self-adaptive thresholding mechanism that significantly attenuates false negatives while concurrently diminishing false positives, particularly in complex urban settings. Empirical results substantiate that our algorithm not only augments the performance of 3D object detection models in diverse urban and adverse weather scenarios but also establishes a new benchmark for adaptive thresholding techniques in field robotics.

Enhancing 3D object detection by using neural network with self-adaptive thresholding

Robust 3D object detection remains a pivotal concern in the domain of autonomous field robotics. Despite notable enhancements in detection accuracy across standard datasets, real-world urban environments, characterized by their unstructured and dynamic nature, frequently precipitate an elevated incidence of false positives, thereby undermining the reliability of existing detection paradigms. In this context, our study introduces an advanced post-processing algorithm that modulates detection thresholds dynamically relative to the distance from the ego object. Traditional perception systems typically utilize a uniform threshold, which often leads to decreased efficacy in detecting distant objects. In contrast, our proposed methodology employs a Neural Network with a self-adaptive thresholding mechanism that significantly attenuates false negatives while concurrently diminishing false positives, particularly in complex urban settings. Empirical results substantiate that our algorithm not only augments the performance of 3D object detection models in diverse urban and adverse weather scenarios but also establishes a new benchmark for adaptive thresholding techniques in field robotics.

Evolution of topsoil structure after compaction with a lightweight autonomous field robot

Evolution of topsoil structure after compaction with a lightweight autonomous field robot

A small autonomous field robot for strawberry harvesting

This paper presents the subsystem descriptions and testing of a small robotic platform intended to harvest strawberries that are grown on elevated beds in open field conditions. Agricultural robots can assist in the optimization of farm resources and help solve issues related to increasing farm costs and labor shortages. Monolithic, large size harvesters are already in development; however, they are susceptible to single-point-of-failure and lack the flexibility to adapt to varying field conditions and farm sizes. The proposed robotic harvester covers one row at a time and features a Delta arm configuration manipulator with a five-finger structure as the end-effector to individually pick strawberries. A deep neural network-based vision subsystem using a YOLOv4 model was adopted, which was configured to detect small objects and to locate and classify strawberries into five stages of maturity. During experiments on a commercial farm, the proposed platform, including vision, manipulation, and overbed navigation and control subsystems, achieved an overall success rate of 71.7% for five environment scenarios, with a minimum of 37.5% (the most complicated scenario) and a maximum of 94.0% (the easiest scenario). The average harvesting speed of the system was 7.5 s per strawberry.

Inter seasonal validation of non-contact NIR spectroscopy for measurement of total soluble solids in high tunnel strawberries

Autonomous field robots are being developed for picking of fruit, where each fruit needs to be individually graded and handled. There is therefore a need for rapid and non-destructive sensing to measure critical fruit quality parameters. In this article we report how total soluble solids (TSS), a measure for total sugar content, can be measured in strawberries in the field by non-contact near-infrared (NIR) interaction spectroscopy. A specially designed prototype system working in the wavelength range 760–1080 nm was tested for this purpose. This novel instrument was compared with a commercial handheld NIR reflection instrument working in the range 900–1600 nm. The instruments were calibrated in the lab using data collected from 200 strawberries of two varieties and tested in a strawberry field on 50 berries in 2022 and 100 berries in 2023. Both systems performed well during calibration with root mean square errors of cross validation for TSS around 0.49 % and 0.57 %, for interaction and reflection, respectively. For prediction of TSS in new berries in 2023, the interaction system was superior, with a prediction error of 1.0 % versus 8.1 % for the reflection system, most likely because interaction probes deeper into the berries. The results suggest that interaction measurements of average TSS are more robust and would most likely require less calibration maintenance compared to reflection measurements. The non-contact feature is important since it reduces the spread of diseases and physical damage to the berries.

Positioning System of Working Bodies in Differential Spraying of Plants

The paper highlights that the escalation in the use of pesticides and agrochemicals poses a significant risk to human health, environmental integrity, and food safety. The predominant method of pesticide application is crop spraying. Improved efficiency and quality of spraying, coupled with a reduction in drug costs, can be achieved by transitioning to differential treatment of agricultural land and precision dose regulation. The incorporation of robotic devices offers a promising solution to facilitate the process of plant protection. (Research purpose) The research aims to develop a positioning system for a robotic differential spraying device. (Materials and methods) were subjected to chemical treatment by an autonomous field robot, and the quality of spraying was assessed using a nozzle. (Results and discussion) The research established a relationship between calculating the nozzle capture angle of an individual plant and the angle of lever lift. Subsequently, a computerized spraying model was developed, enabling the adjustment of various parameters and benchmarking the proposed differential spraying method against the traditional one. The variation coefficient, reflecting the uniformity of droplet distribution on the plant surface, was calculated. The results indicate that the variation coefficient is dependent on the speed and distance of spraying in different operating modes, including individual plant spraying and row spraying. (Conclusions) The variation coefficient for the traditional spray method was 46 percent. With the adoption of differential spraying methods, this variation coefficient decreased to 25-28 percent for individual plant spraying and 33-40 percent for row spraying. Field studies further demonstrated a variation coefficient of 19-24 percent for individual plant spraying in contrast to 30-35 percent for row-spray treatments.

Vertical and horizontal stresses from a lightweight autonomous field robot during repeated wheeling

Some agricultural robots differ in design from traditional tractors which can affect load distribution among the wheels and the resulting soil stresses, especially when moving and carrying implements. Accurate measurements of soil stresses from these machines are needed to estimate their potential to reduce risk of compaction. The aim of this experiment was to study the vertical and horizontal stresses during repeated wheeling from a lightweight autonomous robot and to compare the measurements with calculations using the model Terranimo. We installed stress transducers at 10 cm depth in a loamy sand soil with water content close to field capacity. As an example of an agricultural field robot, we used a 55 kW 4WD robot (model ROBOTTI 150 D equipped with 320/65 R16 tyres) in two configurations: unloaded (33.6 kN) and loaded with a sprayer (37.2 kN). We conducted ten passes with the robot on the same wheel tracks over the transducers and measured the contact area, dynamic wheel load, mean ground pressure and maximum vertical and horizontal stresses during each wheel pass. We observed a significant increase in mean ground pressure with repeated wheeling. Measured values of maximum vertical stresses were 32% larger than the ones predicted by the model. On the same wheel and for different numbers of passes, we found differences between maximum and minimum dynamic wheel loads of up to 9.3 kN. Our results suggest that using static loads from this machine as inputs in models can result in inaccurate predictions of soil-tyre interface parameters due to the high variability and unknown redistribution of the load under dynamic conditions. The differences between static and dynamic loads also impede the correct on-field adjustment of tyre inflation pressures. These issues can result in an underestimation of the risk of soil compaction of this type of vehicle, especially in the topsoil. This work can help design new robots that aim to minimize soil compaction.

Impacts of load and repeated wheeling from a lightweight autonomous field robot on the physical properties of a loamy sand soil

The increasing size of agricultural machinery has intensified the risk of soil compaction. Fleets of lightweight autonomous robots have been proposed as a solution. However, because of their lower capacity and narrower working widths, they are likely to increase the area affected by traffic and repeated wheeling in the fields. The aim of this study was to evaluate the effects of load and repeated wheeling from a lightweight autonomous robot on soil physical properties. We conducted ten passes on the same wheel track with a 55 kW 4WD robot (model ROBOTTI 150 D with 320/65 R16 tyres) in two configurations: unloaded (total weight 33.6 kN) and carrying a filled sprayer (total weight 37.2 kN). After the first, fifth and tenth passes, we measured rut depth, apparent cohesion and penetration resistance. We took minimally disturbed 100-cm3 soil cores at 10 cm depth to measure air permeability and effective air-filled porosity in the laboratory. The results show that load configuration was significant for rut depth and apparent cohesion, whereas the number of robot passes was significant for all parameters. We found significant differences in penetration resistance for the different numbers of passes down to 0.26 m depth. Penetration resistance maximum values were 1.5 and 2 MPa for five and ten passes. Effective air-filled porosity and air permeability were negatively affected between, respectively, the second to fifth and sixth to tenth pass, reaching 0.15 cm3 cm−3 and 8 µm2, which are close to but above what is considered critical for crop growth. The pore organisation index showed blocking of the large conductive pores, especially after ten passes. Our results show that even though critical limits were not exceeded, topsoil functionality was affected by repeated wheeling, especially after six to ten passes. Thus, despite the relatively light wheel loads (< 10 kN), the recommendation is to limit the number of wheel passes to reduce the risk of compaction.

A Multi-MAV System for the Autonomous Elimination of Multiple Targets in the MBZIRC 2020 Competition

The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) is a prestigious, biennial competition aimed at furthering the state of the art in the field of autonomous robotics. In this paper, we present our solution to one of the tasks in the MBZIRC 2020 competition, which design won second place in Challenge 1 and first place in the Grand Challenge of the competition. This paper focuses specifically on the popping task of multiple balloons by multiple Micro Aerial Vehicles (MAVs). This task required a rapid and robust performance to compete with systems from other expert robotic teams from around the world. In this task, a team of autonomous MAV’s had to seek and attack several balloons positioned throughout the competition arena. The novel fast autonomous searching for multiple targets in 3D, their reliable detection, precise relative state estimation, and agile motion planning algorithms are presented in this paper, together with an application for general tasks of 3D target capturing. With a primary focus on reliability, the methods reported in this paper and the entire, complex multi-agent system were successfully verified in both extreme conditions of the desert and the MBZIRC competition. An evaluation of the proposed methods using data from the competition and additional separate datasets is presented. The relevant code of our implementation has been made publicly available for the robotics community.

Field robots development in the aspect of achieving the goals of sustainable agriculture

The article deals with the issues related to the use of field robots in agricultural production in the aspect of the use of a sustainable farming system. At the beginning, the very essence of sustainable agriculture is presented and the problems that remain to be solved are identified, thus determining the market demand for autonomous field robots. The next part of the article presents the main division of agricultural robots and an overview of the most interesting solutions from the last few years that have been implemented by private companies and research centres from around the world. The review of available solutions makes it possible to identify the main challenges related to the implementation of robotic projects into working in difficult field conditions that are faced by the engineers who design them. The projects of autonomous robots used for work in agriculture, implemented by the Łukasiewicz Research Network - Industrial Institute of Agricultural Engineering in cooperation with consortium members, are also presented. At the end of the article, there is a summary and conclusions, which in a general sense define the need for further research on field robots, so as to achieve their fully autonomous work in the near future.

Overcoming the Sim-to-Real Gap in Autonomous Robots

When designing and planning an autonomous, adaptive system utilizing the benefits of Artificial Intelligence (AI), both the specific field of AI and the desired use case must be addressed to achieve a reliable system. In the field of autonomous robotics, the authors focus on the aspect of training a robot not in reality, where training is reliant on real-time and the amount of hardware systems performing the training, but in a virtual environment, which can be parallelized and customized individually. In this paper, a functional simulation of a real robot was developed and trained using reinforcement learning in a virtual environment to successfully complete a specified task. The trained model was then transferred to the physical robot, which itself was able to complete the specified task in the real world, without the need of previous real-world training. Due to extensive observation and analysis of the physical system’s characteristics, the presented direct transfer approach does not rely on domain randomization, which is usually applied in this field.

RESEARCH OF THE SPRAYING SYSTEM WITH THE METHOD OF DIFFERENTIATED APPLICATION

Processing of valuable crops by applying various agrotechnical means is one of the most important factors that affects the volume and quality of the crop. When processing crops, it is necessary to ensure the accuracy of the actuators of the robotic device and analyse the optimal modes to improve the efficiency of the performed agrotechnical operation. (Research Purpose) The research purpose is studying the dependence of factors affecting the processing of plants on the quality indicators of this operation and comparing the main parameters of the robot during equivalent tests taking out of account secondary factors. (Materials and methods) For the study was uses an autonomous field robot of differentiated application of agrochemical agents by spraying. According to GOST 34630-2019 «Machines for plant protection. Sprayers. Test methods», laboratory studies of the positioning system of an autonomous device for differentiated application of agrochemical agents were conducted. The working documentation has been designed. A laboratory installation, a program and methodology for laboratory research were made. (Results and discussion) The article presents optimal settings of an autonomous field robot for differentiated application of agrochemicals, designed to ensure the effectiveness of applied plant protection products and improve the quality of its application. The features of all working organs and their influence on the uniformity of spraying plants were taken into account. (Conclusions) An autonomous field robot for differentiated application of agrochemical agents ensures uniformity of spraying by hovering the working organ over the plant, thereby reducing the risk of spreading of the working fluid. This is confirmed by a smaller relative spread of drops caught by cards. The data on the considered agrotechnical process comply with GOST 34630-2019 «Machines for plant protection. Sprayers. Test methods».

PROFITABILITY OF THE SPRAYING SYSTEM USING THE METHOD OF DIFFERENTIATED APPLICATION

Most of the agrochemicals used are dispersing in the environment, which negatively affects the environment and health. One of the ways to solve this problem is to use a differentiated method of applying plant protection products. In addition to reducing environmental pollution, this method allows you to save on the consumption of plant protection products. The economic efficiency of agricultural machinery is assessed by the final indicators of agricultural production, profit growth due to increased crop yields, improved product quality and reduced production costs. The article presents the technical and economic efficiency of using a robotic device for precise application of agrochemical agents. (Research purpose) The research purpose is analyzing the economic effectiveness of the differentiated method of applying agro-chemical agents. (Materials and methods) GOST 34630-2019 «Agricultural machinery. Machines for plant protection. Sprayers. Test methods» has been analyzed. The economic efficiency analysis was carried out on the basis of field tests. A robotic device has been tested on the territory of the Agrofirm «POISK» (Ramenskoye city district, Moscow region). (Results and discussion) The consumption of insecticide by the technology of differentiated application decreased by 38 percent. The cost of an autonomous field robot is 25.04 percent lower than the cost of the basic technology. The operational cost reduction in the treatment of cabbage with insecticides by means of differentiated application is 61 percent in comparison with the basic low-volume spraying. (Conclusions) On the basis of the calculation of the economic efficiency of an autonomous field robot for differentiated application of agrochemical agents it was revealed that the payback of additional investments is less than one year; the robot has high maintainability, interchangeability of elements, adaptability of structural parameters; the total economic effect is 1,662,979.63 rubles.

Design of an Autonomous Field Robot for Differentiated Application of Agrochemical Agents

The introduction of robotic devices into agricultural production processes makes it possible to increase the efficiency of work and the quality of the products and to ensure a new level of environmental safety. The need to develop this device is due to the economic inexpediency of using foreign analogues due to the low level of maintainability for domestic production, high maintenance costs, a narrow list of operations, and the lack of adaptation systems for a wide range of crops. (Research Purpose) The research purpose is in developing an autonomous robotic device for differentiated application of agrochemical agents in order to minimize their consumption, increase economic efficiency and environmental safety. (Materials and methods) The article presents the analyse of existing studies on monitoring of agricultural crops and fertilization and the requirements for the design of an autonomous robotic installation being created. There were conducted laboratory tests of a field robot model. (Results and discussion) The article describes a design of an autonomous field robot for differentiated application of agrochemicals designed for farms engaged in the crop sector. This device will allow performing a wide range of work, ranging from plant condition diagnostics to yield forecasting, reducing the proportion of human labour costs, improving environmental cleanliness and economic efficiency. It has been taken into account the features of the operation of the robotic vehicle in the field, the possibility of quick replacement of batteries, autonomy. During the design, the scope of robot application was expanded by installing additional actuators without replacing the control unit of the working body. (Conclusions) The system of guidance and differentiated application of agrochemical agents is applicable in the field.

Empowerment of mosque communities to increase body immune with aroma therapy robots

Treatment of patients suffering from infection with the novel corona virus by means of therapy because there is no one drug to cure patients affected by Covid-19. Patients with COVID-19 are undergoing therapy to boost their immune system. One of the therapies to increase the body's immunity is by using aromatherapy. This community empowerment program applies aromatherapy robots to increase the immunity of the congregation who are carrying out worship activities at the mosque. The purpose of this community empowerment is to create and implement an aromatherapy robot that has an aromatherapy liquid level indicator and can refill aromatherapy with liquids from plants. The method of implementing the community empowerment program is as follows. The robot was made by UMY community service staff consisting of nine people who are experts in their respective fields, chaired by Dr., Ir., Iswanto., S.T., M.Eng., IPM who is an expert in robotics. There are members from the University of Muhammadiyah Yogyakarta, University of UIN Sunan Kalijaga Yogyakarta, Ahmad Dahlan University and the University of Tlaxcala, Mexico. There are five members from the University of Muhammadiyah Yogyakarta, namely Dr., Adhianty Nurjanah, S.Sos., M.Sc. expert in disaster communication, Dr. Ir. Gatot Supangkat who is an expert in the field of plants and Dhiya Uddin Rijalussalam., S.T who is an expert in the field of robot assembly. Members from outside UMY are Nia Maharani Raharja., S.T., M.Eng. from the University of UIN Sunan Kalijaga Yogyakarta, an expert in instrumentation, Alfian Maarif., S.T., M.Eng. from Ahmad Dahlan University, an expert in control and Professor Ph.D. Carlos Sánchez-López is an expert in the field of autonomous robots from the University of Tlaxcala, Mexico. With this aromatherapy robot, mosque congregations can increase their immunity by inhaling the aromatherapy in the robot.

German farmers\u2019 intention to use autonomous field robots: a PLS-analysis

Autonomous field robots are a promising technology for solving several problems in agriculture, as they are electrical driven, can control weeds single-plant based mechanically or with microdoses of pesticides and exert less ground pressure on the field. Whether such robots will be applied on a large scale in German agriculture depends on various parameters. Therefore, the factors influencing the behavioural intention of farmers with respect to their future adoption of autonomous field robots were investigated. The analysis applies a structural equation model based on an extended version of the Unified Theory of Acceptance and Use of Technology. The dataset, collected in 2019, consists of 500 German farmers. The results reveal significantly positive effects of farmers’ expected performance, social influence and trust as well as significantly negative effects of farmers’ effort expectancy and anxiety on the behavioural intention to use autonomous field robots. Additionally, moderating effects of age on the relationship of individual constructs to the behavioural intent to use robots could be confirmed. The results provide important information for various stakeholders. Robot suppliers should better inform farmers about the performance of their products, for instance by involving farmers in the development process of the robots. The ecological benefits attributed to field robots could meet public expectations and should be better communicated to address farmers’ social influence on the behavioural intention to use the robots. Policymakers could try to create better framework conditions, for example by establishing a stable legal situation for autonomous systems or promote its use.

Evaluation of Grain Quality-Based Simulated Selective Harvest Performed by an Autonomous Agricultural Robot

Grain price differences due to protein content can have economic effects on the farm as well as environmental effects when alternative protein sources are imported. Grain protein variability can vary from year to year due to environmental factors and can be addressed by site-specific management practices. Alternatively, it can be addressed at harvest time by selective harvest. Agricultural autonomous robots can accurately follow alternative harvesting routes that are subject to grain quality maps, making them suitable choices for selective harvest. This study addresses therefore the potential revenue of selective harvest performed by the route planner of an autonomous field robot. The harvest capacity and potential economic revenues of selective harvest in a Danish context were studied for a set of 20 winter wheat fields with four hypothetical scenarios. The results showed significant differences in harvest capacity between conventional and selective harvest. Even though in some scenarios selective harvest did not require notable additional harvest times, the cost–benefit analysis showed small economic returns of up to 46 DKK ha−1 for the best scenarios, and for most cases losses up to 464 DKK ha−1. Additionally, the location of the high protein content areas has great influence on the profitability of selective harvest.

Using a Reconfigurable Holonomic Drive Robot in Robotic education

In industry it is not uncommon for machines to outlive the purpose for which they were commissioned; at times these perfectly serviceable devices are simply decommissioned and left neglected in storage to slowly decay. Motors, actuators, and structural mechanics are still operational, while control system and their design purpose may have passed into obsolescence. In applied educational fields students are often reluctant to consider working with seemingly obsolete systems. Reconfigurable systems may offer a solution to this challenge for education and training in the field of autonomous robotics. Often custom-built devices are beyond the expenditure budget constraints of a college department for one course. Mecanum wheeled robots with tractive forces at each wheel offer the opportunity to explore translation controllable in a degree of freedom that is equal to total degrees of freedom of the robot. They are also excellent platform to demonstrate and study holonomic drive theories. In this proposed study we seek to explore the viability of reconfigurable robots in delivering an applied robotic control perception and design educational program. &nbsp;

자율주행로봇의 주행안정성 예측을 위한 실시간 디지털 트원 모델 개발

This study aimed to develop a real-time digital twin model for an autonomous field robot. Autonomous control involves controlling vehicle stability parameters such as angular and translational velocities. However, stability is lost when a vehicle run over rough terrain. Therefore, it is necessary to accurately predict vehicle stability in real time using a digital twin model. In this study, we developed the digital twin model for an autonomous driving robot using real-time multibody dynamics. To verify the accuracy, we carried out real road tests on a flat road, and roads with symmetric and asymmetric bumps. We regulated the dynamic parameters such as the position of the center of gravity and coefficients of force elements in the built digital twin model and evaluated its efficiency as well.