Agricultural Vehicle Weeding Tool Control with 3D Trunk Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Mechanical weeding in extensive crops is challenging due to the risk of damaging plants with existing tools, and existing autonomous systems lack effective collision avoidance mechanisms, particularly in areas where herbicide use is limited.

Innovation Solution

A 3D sensor (RADAR, LiDAR, stereo camera) combined with GPS to create a map of obstacles, georeference their positions, and control the weeding tool's extension and retraction based on predetermined distance thresholds, using vehicle trajectory and speed to avoid collisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If a contact sensor is used to detect plant trunks, then the tool can be retracted automatically, but the plant trunk is still damaged due to vehicle inertia and retraction speed

Engineering Contradiction:
Improveautomatic retraction controlVSAvoidplant trunk damage
Core Design Contradiction:
Extent of automationVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary detection of plant trunks using a 3D sensor (RADAR, LiDAR, or stereo camera) before the vehicle reaches collision distance. The processed image identifies trunk positions and calculates distances, enabling the control unit to initiate retraction in advance. This preliminary action allows the tool to be retracted before contact occurs, preventing damage despite vehicle inertia and retraction speed limitations.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If a human operator manually controls the weeding tool, then collision avoidance can be monitored, but the time required for weeding increases significantly

Engineering Contradiction:
Improvecollision avoidanceVSAvoidweeding time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system replaces the human operator's mechanical monitoring and control actions with an automated system comprising a 3D sensor for detection, an image processing unit for analysis, and a control unit for actuation. This substitution maintains reliable collision avoidance through continuous automated monitoring while eliminating the time loss associated with manual operation, enabling the vehicle to proceed at optimal speeds without human intervention delays.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If the weeding tool is extended to cover more ground, then weeding productivity increases, but the risk of colliding with plants increases

Engineering Contradiction:
Improveweeding coverageVSAvoidcollision risk
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system implements continuous feedback by using the 3D sensor to detect plant trunks in real-time, processing the images to determine distances, and feeding this information back to the control unit. The control unit adjusts the tool's position based on this feedback, extending it when safe to maximize productivity and retracting it when collision risk is detected. This closed-loop feedback enables the tool to operate at maximum safe extension, optimizing both productivity and collision avoidance.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4482288B1Autonomous control system of a weeding tool connected to an agricultural vehicle
Publication Date: 2025.10.15 CNH IND ITALIA SPA
  • EP4482288B1 patent drawingFigure 1~2
  • EP4482288B1 patent drawingFigure 3
  • EP4482288B1 patent drawingFigure 4

AI summary

Autonomous control system of a weeding tool connected to an agricultural vehicle (AV), wherein the weeding tool is able to assume a weeding condition and a retracted condition, wherein said weeding condition includes a distension of the tool according to a direction perpendicular to a longitudinal development (L) of the vehicle; the system comprising a 3D sensor (3DS) associated with a front part of the agricultural vehicle to acquire a pointcloud corresponding to a scenario in front of the vehicle (AV), and processing means (ECU) configured cyclically to generate a map of poles and/or trunks detected by means of said pointcloud, and command a weeding condition of the implement when the distance between the implement and a pole and/or trunk is greater than a predetermined threshold and command a retraction condition of the implement when said distance is less than or equal at said predetermined threshold.