Agricultural Obstacle Map Updating for Dynamic Field Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing agricultural machinery faces challenges in accurately detecting and avoiding dynamic obstacles due to inaccuracies in obstacle maps, which can lead to collisions, especially with changeable or incorrectly recorded obstacles such as well shafts and growing trees, and there is a need for improved environmental perception in automated or autonomous scenarios.
Innovation Solution
An agricultural machine equipped with sensors dynamically updates an obstacle map during field operations, allowing real-time sharing and classification of obstacles, with driver involvement and pattern recognition, and integrates with a network of machines to enhance obstacle detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If an obstacle map is used for navigation, then collision avoidance is improved, but the map becomes inaccurate due to changeable obstacles such as well shafts, drain covers, and growing trees
Solution Approach 1:
The obstacle map is transformed from a static pre-recorded representation to a dynamic structure that is continuously updated during field operations. Sensors mounted on agricultural machines detect new obstacles in real-time, and the map is automatically revised to reflect current field conditions, including newly appeared obstacles like well shafts and growing trees.
Solution Approach 2:
A feedback loop is established where sensor data from agricultural machines is continuously fed back to update the obstacle map. The system compares detected obstacles with the existing map, identifies discrepancies, and automatically corrects the map information, creating a self-improving navigation system.
2Productivity
If multiple agricultural machines operate simultaneously, then productivity is improved, but the risk of collisions increases due to incomplete obstacle information
Solution Approach 1:
Multiple agricultural machines are merged into a collaborative network where each machine contributes sensor data to a shared obstacle map. The individual detection capabilities of multiple machines are combined to create a comprehensive view of obstacles, allowing all machines to operate safely simultaneously with updated navigation routes.
3Measurement precision
If sensor-based obstacle detection is used, then real-time obstacle detection is improved, but false warnings and incorrect reactions occur due to sensor inaccuracies
Solution Approach 1:
Sensor detections are subjected to a feedback-based verification process where detected obstacles are cross-checked against the obstacle map and other sensor data. The system continuously refines obstacle classifications through feedback loops, reducing false warnings while maintaining real-time detection capabilities.
Solution Approach 2:
The obstacle map serves as an intermediary that mediates between raw sensor data and navigation decisions. Instead of reacting directly to individual sensor detections, the system uses the obstacle map as a filtering and verification layer to confirm obstacles before triggering warnings or route changes.
4Measurement precision
If the obstacle map is updated in real-time, then obstacle detection accuracy is improved, but the system complexity increases due to multiple sensors and data processing
Solution Approach 1:
The system performs self-service by automatically updating the obstacle map using data from the agricultural machines' existing sensors. The update process is autonomous, requiring minimal human intervention, and the system self-corrects map inaccuracies using its own operational data without external assistance.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach reduces false warnings and collisions by providing a more accurate and shared obstacle map, enabling safer operation of multiple agricultural machines by reducing inaccuracies and allowing for real-time updates and collaborative obstacle management.
Implementation Method 1
The sensor (4) can, for example, be a radar sensor
Implementation Method 2
or a lidar sensor
Data Source
Figure 1
Figure 2
AI summary
The invention relates to a method for cultivating a field (3) using an agricultural machine (1), wherein the agricultural machine (1) has a sensor (4) arranged on the agricultural machine (1), and wherein the agricultural machine (1) has a driver assistance system (5) which includes an obstacle map (6). It is proposed that the driver assistance system (5) updates the obstacle map (6) by means of the sensor (4) during cultivation of the field (3).