Mobile Machine Re-Routing Using Deep Learning Field Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing route planning systems for mobile machines, such as agricultural, construction, and forestry machines, do not adequately consider complex interactions between terrain, ground conditions, soil type, weather, and machinery capabilities, leading to suboptimal paths and increased operational costs.
Innovation Solution
The use of machine learning, specifically deep learning models based on Recurrent Neural Networks (RNNs) or Long Short-Term Memory (LSTM) networks, to update and re-route mobile machines in real-time, taking into account various factors such as terrain, weather, and machine capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If manual planning or simple heuristic algorithms are used for route planning, then the system complexity is low and ease of operation is maintained, but the route planning quality is subpar and fuel consumption increases
Solution Approach 1:
The patent replaces manual planning and simple heuristic algorithms with a machine learning-based computing system that processes terrain, ground conditions, soil type, weather, and machinery capabilities data. This substitution of computational complexity for operational simplicity resolves the contradiction by achieving superior route optimization through automated ML models while maintaining ease of use via automated decision-making.
Solution Approach 2:
The system enables self-service route planning by automatically analyzing multiple factors (terrain, soil, weather, machine capabilities) and generating optimized routes without requiring expert knowledge or manual intervention. The ML model independently processes data and produces route recommendations, eliminating the need for operators to manually consider complex interactions between various factors.
2Adaptability or versatility
If manual planning by operators is used, then the system is easy to operate, but the route planning does not consider complex interactions between terrain, ground conditions, soil type, weather, and machinery capabilities
Solution Approach 1:
The computing system performs multiple functions simultaneously: analyzing terrain, ground conditions, soil type, weather conditions, and machinery capabilities to generate comprehensive route plans. This multi-functional approach allows the system to consider all complex interactions in a unified process, achieving high adaptability while maintaining operational simplicity through automation.
Solution Approach 2:
The machine learning model acts as an intermediary between the operator and the complex environmental factors. Instead of requiring the operator to directly analyze and balance multiple interacting factors, the ML model processes these complexities and presents simplified route recommendations, maintaining ease of operation while achieving comprehensive adaptability.
3Productivity
If traditional route planning methods are used, then operational procedures are simple, but productivity is reduced and operational costs increase
Solution Approach 1:
The system performs preliminary analysis of terrain, ground conditions, soil type, weather, and machinery capabilities before generating route plans. By pre-processing this complex data through ML models, the system optimizes routes in advance, enabling higher productivity through better-planned operations while managing complexity through automated preliminary computations.
Solution Approach 2:
The computing system continuously processes data from multiple sources and adjusts route recommendations based on the analyzed interactions between environmental factors and machinery capabilities. This feedback-driven approach improves productivity by adapting routes to actual conditions while managing system complexity through automated data processing and ML-based decision-making.
Data Source
AI summary
Embodiments include technologies that use machine learning to update a route plan to re-route a mobile machine in a field. In some examples, a method includes using a mobile machine to perform work in a field and recording travelled path information. The recorded path information includes information about one or more paths followed by the machine when performing the work in the field. The method also includes using one or more computing devices on the machine to input the path information into a trained deep learning model and to receive new machine travel paths from the trained model. Also, the method includes using the computing device(s) on the mobile machine to control the machine to follow the new travel paths generated by the trained model.