Autonomous Field Path Planning for Variable Working Widths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for generating path plans for autonomous agricultural vehicles are cumbersome, requiring manual operator input and relying on historical data that may not be applicable to different implements, leading to inaccurate or unsuccessful path generation, especially when the working width changes.
Innovation Solution
The system generates a path plan based on real-time coverage data, independent of the implement's working width, by using sensors to determine the vehicle's geographical location, speed, and direction, and adjusts the path to ensure complete field coverage, including turns within the field boundary, while calculating the cost of the path plan to select the most efficient route.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual operator input and historical data are used to generate path plans, then the system is simpler to implement, but the path generation accuracy deteriorates when working width changes or different implements are used
Solution Approach 1:
The system automatically generates path plans using real-time sensor data from the vehicle's own operation, eliminating the need for manual operator input and historical data storage. The vehicle self-monitors its geographical location, speed, and direction to create accurate path plans adapted to current working conditions and implement specifications.
Solution Approach 2:
The system dynamically adjusts path plan parameters based on real-time sensor measurements of the vehicle's actual performance and environmental conditions. This allows the path generation algorithm to adapt to different implements and working widths by using current operational data rather than fixed historical parameters.
2Measurement precision
If real-time sensor data is used to generate path plans, then path generation accuracy improves, but the amount of data processing and computational requirements increase
Solution Approach 1:
The system extracts only the essential real-time parameters needed for path planning (geographical location, speed, direction) from the vehicle's sensor suite, processing only the critical data required for accurate path generation while filtering out unnecessary information to minimize computational overhead.
Solution Approach 2:
The system pre-processes sensor data streams to identify and prioritize critical path-related parameters before feeding them into the path planning algorithm, reducing the computational burden by preparing only the necessary data elements in advance.
3Ease of operation
If conventional methods relying on historical data are used, then the system is more adaptable to different implements, but the path generation becomes cumbersome and requires manual intervention
Solution Approach 1:
The system automatically adapts to different implements by using real-time sensor data from the vehicle's own operation, eliminating the need for manual reconfiguration or historical data updates. The vehicle self-adjusts its path planning based on current implement specifications and working conditions.
Solution Approach 2:
The system continuously monitors real-time vehicle performance and environmental conditions through sensors, using this feedback to dynamically adjust path plans for different implements. This closed-loop approach ensures the system remains adaptable without requiring manual intervention or historical data.
4Productivity
If manual operator input is required for path planning, then less computational resources are needed, but operator fatigue increases and productivity decreases
Solution Approach 1:
The vehicle autonomously generates and follows path plans using its own sensor data, completely eliminating the need for manual operator input for path planning. This self-service capability increases productivity by allowing continuous operation without operator fatigue while managing automation complexity through efficient use of onboard sensors and processors.
Data Source
AI summary
Methods, apparatus, systems and articles of manufacture are disclosed to generate a path plan. An example method includes generating guidance lines for a next path of a vehicle based on an edge of a current path, generating a first path plan of a field within a field boundary, the first path plan generated using a first degree heading, generating a second path plan of the field within the field boundary, the second path plan generated using a second degree heading, and when the first path plan includes a first cost lower than a second cost of the second path plan, transmitting the first path plan to a vehicle to control the vehicle.