Robot Force Control Parameter Adjustment Using Learning Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In force control of robots, manually setting control parameters such as pressing force, traveling speed, and direction is challenging, especially when parameter adjustments fail, making it difficult to determine which parameters to change to resolve issues.
Innovation Solution
An adjustment support device is developed that constructs a learning model using machine learning to analyze past control parameters and their outcomes, enabling the determination of appropriate adjustments for improving force control success, even for inexperienced operators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual adjustment of control parameters is performed, then the operator can set pressing force, traveling speed, and direction, but it becomes difficult to determine which parameters to change when adjustment fails
Solution Approach 1:
The system collects determination data indicating whether force control results are success or failure, feeds this information back through the learning model, and generates adjustment method recommendations. This closed-loop feedback mechanism enables the system to learn from past outcomes and provide targeted guidance for parameter adjustments, resolving the information loss problem.
Solution Approach 2:
The learning model automatically analyzes past control parameter data and determination results to generate adjustment method recommendations without requiring external expert intervention. The system serves itself by using its own accumulated data to improve future adjustments, eliminating the need for operators to have deep expertise in parameter tuning.
2Adaptability or versatility
If control parameters are manually adjusted without guidance, then operators have flexibility in adjustment, but inexperienced operators cannot perform appropriate adjustments when force control fails
Solution Approach 1:
The patent replaces the mechanical expertise-based adjustment process with an information-processing system. The learning model processes control parameter data and determination results to generate adjustment recommendations, substituting human expert judgment with automated data-driven analysis. This enables inexperienced operators to achieve reliable adjustments without manual expertise.
3Extent of automation
If a learning model is constructed using machine learning, then automated adjustment support is provided, but the system requires processing and storing historical control data
Solution Approach 1:
The learning model serves multiple functions: it stores control parameter data, analyzes determination results, generates adjustment recommendations, and continuously learns from new data. This multi-functional component consolidates what could be separate complex systems into a single versatile module, reducing overall system complexity while maintaining high automation.
Data Source
AI summary
An adjustment support device includes: a storage unit for storing, with force state data and position data in an operation when performing force control of the industrial robot as a state variable and with data indicating a result of determining whether a result of the force control is success or failure based on predetermined criteria as determination data, a learning model generated by machine learning; an analysis unit for analyzing the learning model to analyze, for a control parameter used when the force control of the industrial robot has failed, an adjustment method of the control parameter for improving a degree of success of the force control; and an adjustment determination unit for determining, based on a result of the analysis by the analysis unit, an adjustment method of the control parameter in the force control used when the force control has failed and outputting the adjustment method.