Industrial Robot Control Using Finite-State Execution Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Predicting and optimizing the execution quality of industrial robot programs is challenging due to varying outcomes and multiple solution paths, leading to inefficient control and delayed error detection in industrial systems.
Innovation Solution
A method representing industrial systems as finite state machines with associated execution values, allowing for the modification of these values based on action outcomes, which enables improved control, optimization, and error detection by tracking performance and adjusting programs accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If robot programs are created without considering actual performance, then program development is simpler and faster, but the industrial robot does not produce at its best and execution quality is poor
Solution Approach 1:
The patent implements feedback by continuously monitoring actual execution quality metrics (cycle time, success rate) and using this information to dynamically adjust and optimize robot programs. The system compares predicted vs. actual outcomes and refines programs based on real performance data, ensuring the robot produces at its best while maintaining manageable complexity through automated optimization.
Solution Approach 2:
The system optimizes robot program parameters such as speed, acceleration, and positioning based on actual performance measurements. By dynamically adjusting these parameters according to real execution data, the system improves productivity without requiring overly complex program structures, as the optimization is achieved through parameter tuning rather than program redesign.
2Reliability
If error tracking is performed ad-hoc, then implementation is simpler, but errors are detected too late or never detected
Solution Approach 1:
The patent implements preliminary action by establishing comprehensive execution quality monitoring and error tracking systems before problems occur. The system continuously collects and analyzes performance data, enabling early detection of potential issues before they lead to failures. This proactive approach improves reliability while keeping the monitoring system manageable through automated data collection and analysis.
Solution Approach 2:
The system introduces an intermediary monitoring layer that sits between the robot program execution and the control system. This intermediary continuously tracks execution quality metrics and provides structured feedback, enabling reliable error detection without requiring direct complex integration into the core control system. The intermediary acts as a buffer that simplifies the overall system architecture while enhancing reliability.
3Adaptability or versatility
If multiple solution paths are available for robot tasks, then flexibility and adaptability improve, but it becomes difficult to predict which path will be fastest and/or least error prone
Solution Approach 1:
The patent implements self-service by enabling the system to automatically evaluate and select the optimal solution path based on real-time performance data. The monitoring system collects execution quality metrics for different paths and automatically determines which path is fastest and least error-prone, eliminating the need for manual prediction. This self-service approach maintains flexibility while solving the prediction difficulty through automated data-driven decision-making.
Solution Approach 2:
The system replaces manual or heuristic-based path selection with automated, data-driven optimization. By using computational methods to analyze execution quality metrics and predict optimal paths, the system substitutes intuitive or trial-and-error approaches with precise, measurable algorithms. This substitution maintains solution path flexibility while dramatically improving prediction accuracy through quantitative analysis.
4Productivity
If robot programs are deployed without performance optimization, then deployment is faster and simpler, but execution times are extended and success rates decrease
Solution Approach 1:
The patent implements dynamics by making robot programs adaptive rather than static. The system continuously monitors execution quality and automatically adjusts program parameters and sequences based on real performance data. This dynamic optimization improves execution efficiency without requiring extensive upfront development time, as the programs self-optimize during operation based on actual conditions and performance measurements.
Data Source
Figure 1
Figure 2
AI summary
A method of controlling an industrial system (10) comprising at least one agent (14, 16), the method comprising providing a representation of the industrial system (10) as a finite state machine (36), the state machine (36) comprising a plurality of nodes (38) and a plurality of edges (40), where each node (38) represents a discrete system state of the industrial system (10), each edge (40) represents an action for a state transition between system states represented by two of the nodes (38), and at least one execution value (42) is associated with at least one of the edges (40); executing at least one action by the at least one agent (14, 16), the at least one action being represented by at least one of the edges (40); and modifying at least one execution value (42) associated with at least one of the edges (40) representing the at least one executed action, based on an outcome of the at least one executed action.