Autonomous agricultural field robot

Abstract

An autonomous agricultural field robot consisting of: a structural chassis made of rigid frame elements that carries components for locomotion, sensors, fluid supply and ground interaction; a multitude of drive wheels coupled to respective drive motors to enable movement on agricultural terrain; a large number of encoder units coupled to at least some of the drive motors to generate motion feedback signals; a LiDAR sensor unit mounted on an elevated support structure and configured to generate spatial field data representing rows of plants and surrounding obstacles; an imaging unit positioned to capture forward-facing visual data from plant surfaces; a processing unit that is connected to the LiDAR sensor unit, the imaging unit and communicates with the encoder units to generate navigation and control signals based on the received data; a microcontroller unit coupled to the processing unit, configured to supply low control signals to motor drivers and fluid supply components; Liquid storage units for holding liquids for agricultural treatment; Pump units connected to the liquid storage units and configured to pressurize the liquids and deliver them to a spray unit directed at the plants; a soil monitoring unit consisting of a moisture sensor and a motor-driven soil sampling element for taking soil samples; and a power supply unit configured to provide electrical energy to drive components and sensor components.

Description

AREA OF INVENTION

[0001] The present disclosure relates to the field of autonomous agriculture, in particular an autonomous agricultural field robot for integrated precision agriculture processes, wherein the robot is configured to navigate autonomously through the rows of plants, detect pests, apply targeted pesticides or fungicides, and monitor soil conditions using a combination of sensor data and machine learning. BACKGROUND OF THE INVENTION

[0002] Agricultural robots automate tasks in fields such as sowing, pest control, soil monitoring, and harvesting—with or without direct human intervention. They have the potential to fundamentally transform agriculture by addressing key challenges such as labor shortages, inefficient resource use, environmental degradation, and the need for sustainable farming methods. They can monitor plant health, detect pests and diseases, measure soil parameters such as moisture and nutrient content, and precisely apply inputs like pesticides and fertilizers. Thanks to these capabilities, agricultural robots optimize crop yields, reduce chemical use, and support data-driven decisions in agriculture. This makes them an indispensable tool for modern agriculture and food security.

[0003] Agricultural robots can generally be divided into two groups: (i) manually controlled agricultural robots, which require human operators for tasks such as spraying or monitoring, and (ii) autonomous agricultural robots, which operate without direct human control. While manually controlled robots are widely used, their reliance on human labor and imprecise application methods lead to inefficiencies, particularly in large-scale agriculture. The increasing complexity of agricultural tasks, such as targeted pest control and real-time soil analysis, demands robots with greater autonomy and precision. Autonomous agricultural robots, such as the invention presented here, meet these requirements by integrating advanced sensor, navigation, and actuator technologies to perform tasks independently and efficiently.

[0004] Traditional farming methods face significant challenges, including excessive pesticide use, labor-intensive soil sampling, and inefficient irrigation. The use of broad-spectrum pesticides often leads to overdosing, resulting in pollution, harm to non-target organisms, and the development of pesticide-resistant pests. Manual soil monitoring is time-consuming and lacks the precision required for optimized resource management. Recent advances in precision agriculture utilize technologies such as computer vision, machine learning, and robot navigation to address these issues.

[0005] Despite these advances, existing systems often focus on isolated functions. Several well-known methods describe an agricultural system that combines LiDAR-based scanning for row navigation and camera-based pest detection, but these technologies are not integrated into a single platform. Some describe an autonomous agricultural robot with navigation and spraying capabilities, but lack a soil monitoring system with active core sampling or a dual-power architecture. While precise application of treatments is addressed, it does not include mechanical soil sampling. The absence of a coherent, cost-effective, and modular platform that integrates navigation, pest detection, targeted spraying, and soil monitoring represents a significant research gap.The present invention, an autonomous precision agriculture system, addresses these challenges by combining LiDAR-based SLAM navigation, camera-based pest detection with machine learning, a dual-pump spraying mechanism, a soil monitoring system with moisture measurement and core sampling, and a dual-power architecture, thus providing a scalable solution for modern agriculture. SUMMARY OF THE INVENTION

[0006] This disclosure relates to a cost-effective autonomous precision agriculture robot called Krishibot. This robot is equipped with a LiDAR-based SLAM system, a machine-learning camera for pest detection, a dual-pump spraying system, a soil monitoring system with moisture measurement and core drilling, and a dual power supply. It is designed for navigation in agricultural fields, pest detection and control, soil health monitoring, and resource optimization in the areas of sustainable agriculture, research, and precision agriculture. The robot autonomously navigates through crop rows, detects pests, applies pesticides or fungicides in a targeted manner, and monitors soil conditions using a combination of sensor data and machine learning algorithms.

[0007] The present disclosure relates to an autonomous field robot for agriculture. The robot comprises: a chassis formed from rigid frame elements, which carries components for locomotion, sensors, fluid supply, and ground interaction; several traction wheels coupled to respective drive motors to enable movement on agricultural terrain; several encoder units coupled to at least some of the drive motors to generate motion feedback signals; a LiDAR sensor unit mounted on an elevated support structure, which acquires spatial field data representing rows of plants and surrounding obstacles; and an imaging unit positioned to acquire forward-facing visual data of plant surfaces.A processing unit that communicates with the LiDAR sensor unit, the imaging unit, and the encoder units to generate navigation and control signals based on the received data; a microcontroller unit coupled to the processing unit, configured to provide low-level control signals to the motor drivers and the fluid supply components; fluid storage units for holding agricultural treatment fluids; pump units connected to the fluid storage units, configured to pressurize the fluids and deliver them to a spray unit directed at the plants; a soil monitoring unit consisting of a moisture sensor and a motor-driven soil core drill for taking soil samples;and a power supply unit configured to provide electrical energy for drive components and sensor components;

[0008] The purpose of the present disclosure is to provide an autonomous precision agricultural robot capable of performing navigation, pest detection, targeted spraying and soil monitoring in an integrated manner, in order to overcome the limitations of existing single-function agricultural systems.

[0009] Another objective of the present disclosure is to provide an agricultural robot that uses LiDAR-based SLAM for robust autonomous navigation in row fields and uneven terrain, thereby reducing dependence on manual guidance and improving the accuracy of field coverage.

[0010] Another objective of the present disclosure is to provide an agricultural robot equipped with a camera-based pest detection system that uses machine learning models to identify pests and diseases in real time and to enable local treatment instead of large-scale pesticide spraying, thereby reducing the use of chemicals and environmental impact.

[0011] Another objective of the present disclosure is to provide an agricultural robot equipped with a double-pump spraying mechanism configured to selectively deliver various agrochemical formulations or variable dosages to target regions based on the detected pest pressure or the condition of the crops, thereby improving input efficiency and treatment accuracy.

[0012] Another objective of the present disclosure is to provide an agricultural robot equipped with a soil monitoring system that includes moisture sensors and an active core drilling mechanism for on-site soil sampling, enabling spatially resolved measurement of soil moisture and nutrient-related parameters for data-driven irrigation and fertilization decisions.

[0013] Another objective of the present disclosure is to provide a dual-power architecture for the autonomous precision agricultural robot, in which traction and high-power actuator subsystems as well as low-energy sensor and processing subsystems are controlled separately to improve energy efficiency, operational reliability and runtime under field conditions.

[0014] Another objective of the present disclosure is to provide a scalable and modular platform architecture that enables the addition, removal or upgrade of sensor, actuator and processing modules based on specific plant species, field conditions and task requirements, thereby enabling cost-effective use in various agricultural scenarios.

[0015] However, another objective of the present disclosure is to enable the acquisition, logging and wireless transmission of georeferenced agronomic data, including pest infestation, plant health indices and soil parameters, for integration into agricultural management and decision support systems to support long-term precision agriculture practices.

[0016] To further clarify the advantages and features of the present disclosure, the invention is described in more detail with reference to specific embodiments illustrated in the accompanying drawings. It is understood that these drawings merely show typical embodiments of the invention and are therefore not to be understood as limiting its scope of protection. The invention is described and explained in more detail and with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE IMAGES

[0017] These and other features, aspects and advantages of the present disclosure will be better understood when the following detailed description is read with reference to the accompanying drawings, in which identical symbols represent identical parts, wherein: Fig. Figure 1 shows a block diagram of an autonomous agricultural field robot according to an embodiment of the present disclosure; Fig. Figure 2 shows the top view of the autonomous precision farming robot according to an embodiment of the present disclosure; Fig. Figure 3 shows the front view of the autonomous precision farming robot according to an embodiment of the present disclosure; and Fig. Figure 4 shows the isometric view of the autonomous precision farming robot according to an embodiment of the present disclosure.

[0018] Furthermore, those skilled in the art will recognize that the elements in the drawings are simplified and not necessarily drawn to scale. For example, the flowcharts illustrate the process by highlighting the main steps to facilitate understanding of this disclosure. With regard to the construction of the device, one or more components may be represented in the drawings by conventional symbols. The drawings may show only those specific details relevant to understanding the embodiments of this disclosure, so as not to clutter the drawings with details that are already apparent to those skilled in the art from the description contained herein. DETAILED DESCRIPTION:

[0019] To facilitate understanding of the principles of the invention, reference is made below to the embodiment illustrated in the drawings, which is described using specific terms. It is understood, however, that this does not limit the scope of protection of the invention. Rather, modifications and further developments of the illustrated system, as well as further applications of the inventive principles depicted therein, are conceivable, insofar as they would typically occur to a person skilled in the art in the field of the invention.

[0020] It will be clear to those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not to be understood as a limitation thereof.

[0021] References to “an aspect”, “another aspect”, or similar phrases in this description mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, phrases such as “in one embodiment”, “in another embodiment”, and similar expressions in this description may, but do not necessarily, all refer to the same embodiment.

[0022] The terms "includes," "comprehensive," or similar expressions denote non-exclusive inclusion. Thus, a procedure or method containing a list of steps does not only include those steps but may also include further steps not explicitly listed or inherent in the procedure or method. Likewise, the statement "includes..." for one or more devices, subsystems, elements, structures, or components, without further limitations, does not preclude the existence of other devices, subsystems, elements, structures, or components.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meanings generally known to those skilled in the art in the field to which this invention belongs. The systems, methods, and examples described herein serve only for illustration and are not to be understood as limiting.

[0024] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0025] The autonomous agricultural field robot (100) according to Fig. 1 comprises: a structural chassis (102) made of rigid frame elements, which carries components for locomotion, sensors, fluid supply and ground interaction; several traction wheels (104) coupled to respective drive motors (106) to enable locomotion on agricultural terrain; several encoders (108) coupled to at least some of the drive motors (106) to generate motion feedback signals; a LiDAR sensor unit (110) mounted on an elevated support structure, which generates spatial field data representing rows of plants and surrounding obstacles; an imaging unit (112) positioned to capture forward-facing visual data from plant surfaces; a processing unit (114) which communicates with the LiDAR sensor unit (110), the imaging unit (112) and the encoders (108) to generate navigation and control signals based on the received data;A microcontroller unit (116) connected to the processing unit (114) and configured to provide low-level control signals to motor drivers and fluid delivery components; fluid storage units (118) configured to hold agricultural treatment fluids; pump units (120) fluidically connected to the fluid storage units (118) and configured to pressurize the fluids and deliver them to a spray unit (122) directed at the plants; a soil monitoring unit (124) comprising a moisture sensor element (124a) and a motor-driven soil core drill element (124b) for taking soil samples; and a power supply unit (126) configured to provide electrical energy to drive components and sensor components.

[0026] In one embodiment, the chassis (102) is formed from metallic frame elements that provide mechanical strength and internal routing for cables and fluid lines, with the arrangement of the fluid storage units (118) and sensor units ensuring stability when moving over uneven terrain.

[0027] In one embodiment, the drive wheels (104) are driven by geared motors (106) which enable a sliding steering movement, wherein the encoder units (108) provide rotation position signals to correct the direction of travel and to maintain alignment with the rows of plants.

[0028] In one embodiment, the LiDAR sensor unit (110) generates spatial data which is used by the processing unit (114) to determine the relative position of the robot, detect obstacles and assist in path guidance during field traversal.

[0029] In one embodiment, the imaging unit (112) acquires visual data from plant surfaces, and the processing unit (114) identifies areas infested by pests from the visual data and generates signals for the selective activation of the pump units to enable localized treatment.

[0030] In one embodiment, the pump units (120) are mounted on a vertical support structure and connected to the liquid storage units (118) via special inlet and outlet lines, which prevent the stored liquids from mixing. The spray unit (122) comprises a nozzle (122a) which is connected to the pump units (120) via a pressure hose directed towards the plant foliage.

[0031] In one embodiment, the soil monitoring unit (124) further comprises a moisture sensor element (124a) positioned to make contact with the soil during movement in order to generate real-time soil moisture signals, and the motor-driven soil core drilling element (124b) is configured to penetrate the soil and collect physical samples while the robot is stationary.

[0032] In one embodiment, the power supply unit (126) comprises electrical distribution components for supplying power to drive elements and sensor elements, as well as electrical protection components for suppressing voltage fluctuations associated with motor-driven inductive loads.

[0033] In one embodiment, the raised support structure supports the LiDAR sensor unit (110) at an upper position, the imaging unit (112) at a middle position, and the pump units (120) below the imaging unit (112) to allow unimpeded detection and fluid supply.

[0034] In one embodiment, the microcontroller unit (116) is arranged in a closed electronics housing and connected to motor drivers, relay units and sensor interfaces to control drive, fluid supply and ground monitoring functions in coordination with the processing unit (114).

[0035] The present invention relates to a cost-effective autonomous precision agricultural robot for automated navigation, pest control, and soil monitoring on agricultural land. The robot integrates a LiDAR-based SLAM system, camera-based pest detection with machine learning, a dual-pump spraying mechanism, a soil monitoring system, and a dual power supply architecture with planetary geared DC motors, robust wheels, an extruded aluminum chassis, motor encoders, a power distribution board, and an Nvidia Jetson graphics card for optimizing crop yield and resource utilization.

[0036] In one embodiment, the chassis of the autonomous precision farming robot is made of extruded aluminum, ensuring durability and stability during navigation within crop rows. The system is equipped with four robust wheels with grippy rubber treads, which, thanks to skid steering, enable maneuverability on uneven terrain. Four planetary geared DC motors drive the wheels and are controlled by H-bridge drivers. Motor encoders on the front motors provide position feedback for precise navigation. The robot incorporates a Jetson System Nano controller, configured to process data and coordinate motor control via a microcontroller to ensure accurate field traversal.

[0037] In one embodiment, the autonomous precision farming robot includes a LiDAR sensor whose data is processed by the LeGO-LOAM algorithm on the Jetson Nano controller. This enables SLAM-based navigation for real-time mapping and obstacle avoidance. A camera with OpenCV and a CNN pest dataset detects pests and activates two 12V diaphragm pumps (for pesticide and fungicide) via a microcontroller-controlled relay. Blue inlet and red outlet hoses prevent the liquids from mixing, ensuring targeted spraying of infested areas.

[0038] In one embodiment, the autonomous precision agricultural robot additionally includes a soil monitoring system with a capacitive moisture sensor for real-time water content measurement and a motor-driven soil sampling probe. Both are controlled by the microcontroller. The robot also features a dual power supply architecture with one battery that powers motors and actuators via a power distribution board (PDB) with a buck converter, and a battery for constant-current components (LiDAR, camera, sensors). Fused connections and a freewheeling diode ensure safety and isolation.

[0039] In one embodiment, the autonomous agricultural field robot comprises a central processing unit that executes Python scripts within a Robot Operating System (ROS) for real-time fusion of LiDAR, camera, and soil sensor data; a microcontroller for low-level actuators; and a Unified Robot Description Format model for RViz and Gazebo simulation, with ROS enabling modular node communication, SLAM via the LeGO-LOAM algorithm, visualization in RViz, and path planning via the navigation stack, thereby integrating obstacle avoidance, pest detection, soil analysis, and coordinated fieldwork.

[0040] In one embodiment, the autonomous agricultural field robot comprises a LiDAR sensor coupled with a system for simultaneous localization and mapping, generating a three-dimensional topological map of the field, and an artificial intelligence module comprising a convolutional neural network trained on agricultural terrain data, which identifies uneven surfaces and generates a waterlogging risk map, the waterlogging risk map being integrated into the irrigation control to dynamically adjust water flow and prevent waterlogging in the plants.

[0041] The Fig. 2 and Fig. Figure 3 shows the orthographic projections from above and front of the proposed autonomous precision agricultural robot, designed for agricultural tasks requiring precision, such as targeted application of pesticides and environmental assessment.

[0042] Fig. Figure 2 shows a top view of the vehicle's square base frame (450 mm × 450 mm), which is made of extruded aluminum profiles. These profiles are lightweight yet high-strength, allowing the vehicle to operate efficiently even on uneven terrain, minimizing weight, and increasing corrosion resistance. Two pesticide tanks are symmetrically positioned on the chassis to ensure a balanced center of gravity. A spray unit with nozzles is located at the front and is connected to the tanks via pressure lines to enable the controlled release of liquid pesticides.

[0043] Fig. Figure 3 shows the front view of the vertical aluminum structure extending from the center of the chassis, serving as the main support for the component tower. This tower houses two vertically arranged diaphragm pumps, each responsible for pressurizing liquids from separate tanks. The lower plate, where the lower pump is mounted, contains an electronics enclosure with a microcontroller, motor drivers, power supply, and interface circuitry. The upper plate, where the upper pump sits, houses an integrated camera module that provides visual data for image-based navigation. A 360° LiDAR sensor is positioned at the top of the tower, generating environmental point cloud data for real-time obstacle detection and route planning. The chassis features four independent wheels, each driven by a 12V DC planetary geared motor, enabling skid steering.This steering technique allows turning maneuvers to zero and is therefore ideally suited for narrow rows of plants and precise movements.

[0044] Fig.Figure 4 shows an isometric view of an autonomous precision agricultural robot, illustrating the mechanical configuration and spatial arrangement of its components. The isometric view highlights the modular extruded aluminum frame, which allows for easy adaptation, maintenance, and expansion. The wheels are located at the corners of the square base, with the motor units directly connected to the wheel hubs. The two cylindrical pesticide reservoirs are prominently mounted on either side of the vertical structure, ensuring even weight distribution. Flexible hoses carry the pesticide fluid from these reservoirs to the two pumps and then to the front sprayer. The vertical frame serves as a mounting structure for the pumps, electronics, camera, and LiDAR system.The camera provides a forward view, while the LiDAR system enables 360° environmental scanning for autonomous navigation in the field. Wiring harnesses, hoses, and engine cables are neatly routed in internal channels within the aluminum profiles, reducing external clutter and increasing durability in field use. The design promotes a low center of gravity, improving stability when traversing uneven terrain.

[0045] The drawings and the preceding description illustrate embodiments. Those skilled in the art will recognize that one or more of the described elements can be combined to form a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment can be added to another. For example, the process flows described here can be modified and are not limited to the manner described herein. Furthermore, the actions of a flowchart need not be performed in the sequence shown; nor do all actions necessarily need to be carried out. Actions that do not depend on other actions can be performed in parallel with the other actions. The scope of protection of the embodiments is in no way limited by these specific examples. Numerous variations, whether explicitly stated in the description or not, such as...Differences in structure, dimensions, and materials are possible. The scope of protection of the embodiments is at least as comprehensive as described by the following claims.

[0046] The advantages, other benefits, and problem solutions have been described above with reference to specific embodiments. However, the advantages, benefits, problem solutions, and any components that can effect or enhance an advantage, benefit, or solution are not to be construed as critical, necessary, or essential features or components of the claims. REFERENCES 100 Block diagram of an autonomous agricultural field robot. 102 structural chassis 104 Multiple drive wheels 106 drive motors 108 Multiple encoder units 110 Lidar sensor unit 112 Imaging Unit 114 processing units 116 Microcontroller unit 118 liquid storage units 120 pump units 122 Spray unit 122a nozzle 124 Ground monitoring unit 124a Humidity sensor element 124b Motor-driven soil drilling element 126 Power supply 202 pesticide storage tanks 302 Lidar 304 Camera 306 Electronics 308 Pump 310 battery 202 pesticide storage tanks

Claims

[1] An autonomous agricultural field robot consisting of: a structural chassis made of rigid frame elements that carries components for locomotion, sensors, fluid supply and ground interaction; a multitude of drive wheels coupled to respective drive motors to enable movement on agricultural terrain; a large number of encoder units coupled to at least some of the drive motors to generate motion feedback signals; a LiDAR sensor unit mounted on an elevated support structure and configured to generate spatial field data representing rows of plants and surrounding obstacles; an imaging unit positioned to capture forward-facing visual data from plant surfaces; a processing unit that is connected to the LiDAR sensor unit, the imaging unit and communicates with the encoder units to generate navigation and control signals based on the received data; a microcontroller unit coupled to the processing unit, configured to supply low control signals to motor drivers and fluid supply components; Liquid storage units for holding liquids for agricultural treatment; Pump units connected to the liquid storage units and configured to pressurize the liquids and deliver them to a spray unit directed at the plants; a soil monitoring unit consisting of a moisture sensor and a motor-driven soil sampling element for taking soil samples; and a power supply unit configured to provide electrical energy to drive components and sensor components. [2] The autonomous agricultural field robot according to claim 1, wherein the chassis consists of metallic frame elements that provide mechanical strength and internal routing for cables and fluid lines, and wherein the arrangement of the fluid storage units and sensor units ensures stability when moving on uneven terrain. [3] The autonomous agricultural field robot according to claim 1, wherein the drive wheels are driven by geared motors enabling a skid-steering movement, and wherein the encoder units provide rotation position signals to correct the direction of travel and to maintain alignment with the rows of plants. [4] The autonomous agricultural field robot according to claim 1, wherein the LiDAR sensor unit generates spatial data which is used by the processing unit to determine the relative position of the robot, detect obstacles and assist in path guidance during field crossing. [5] The autonomous agricultural field robot according to claim 1, wherein the imaging unit captures visual data from plant surfaces and the processing unit identifies pest-infested areas from the visual data and generates signals for selective activation of the pump units to enable localized treatment. [6] The autonomous agricultural field robot according to claim 1, wherein the pump units are mounted on a vertical support structure and are connected to the liquid storage units via special inlet and outlet lines which prevent the stored liquids from mixing, and wherein the spray unit comprises a nozzle which is connected to the pump units via a pressure hose and is directed towards the plant foliage. [7] The autonomous agricultural field robot according to claim 1, wherein the soil monitoring unit further comprises a moisture sensor element positioned to make contact with the soil during movement in order to generate real-time soil moisture signals, and the motor-driven soil core sampling element configured to penetrate the soil and collect physical samples while the robot is stationary. [8] The autonomous agricultural field robot according to claim 1, wherein the power supply unit comprises electrical distribution components for supplying power to drive elements and sensor elements and electrical protection components for suppressing voltage fluctuations connected to motor-driven inductive loads. [9] The autonomous agricultural field robot according to claim 1, wherein the raised support structure carries the LiDAR sensor unit at an upper position, the imaging unit at a middle position and the pump units below the imaging unit to allow unimpeded detection and fluid supply. [10] The autonomous agricultural field robot according to claim 1, wherein the microcontroller unit is arranged in a closed electronics housing and is connected to motor drivers, relay units and sensor interfaces to control drive, fluid supply and soil monitoring functions in coordination with the processing unit.

Images