Robot Movement Sequence Selection for Faster Pick-and-Place
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot movement sequence planning methods are inefficient, requiring significant skill and difficulty in programming, and often result in suboptimal performance due to the selection of similar movement sequences for each pick and place cycle, leading to reduced pick rates and increased robot movements.
Innovation Solution
A method that predicts values of parameters such as time, speed, and energy consumption for alternative movement sequences, allowing for the selection of optimal sequences and execution by the robot, utilizing neural networks and genetic algorithms for efficient implementation in real-time computer environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional robot movement sequence planning methods are used, then programming is complex and requires significant skill, but the system can still execute basic pick and place operations
Solution Approach 1:
The system performs self-optimization by automatically predicting and selecting optimal movement sequences based on parameter values (time, speed, energy consumption) without requiring complex manual programming. The robot controller autonomously evaluates alternative movement sequences and selects the optimal one, making the system serve itself rather than requiring extensive programmer intervention.
Solution Approach 2:
The system optimizes movement sequences by predicting and adjusting parameter values such as time, speed, and energy consumption. By changing these parameters dynamically based on predicted outcomes, the system achieves optimal performance without complex programming, transforming rigid traditional control into adaptive parameter-based optimization.
2Productivity
If similar movement sequences are selected for each pick and place cycle, then programming is simplified, but pick rate decreases and robot performance is suboptimal
Solution Approach 1:
The system transitions from static, repetitive movement sequences to dynamic optimization where movement sequences are continuously adapted based on predicted parameter values. The controller dynamically selects from alternative movement sequences for each pick and place cycle, optimizing pick rate and reducing cycle time through real-time decision-making rather than fixed patterns.
Solution Approach 2:
The system incorporates feedback mechanisms by predicting parameter values (time, speed, energy consumption) for alternative movement sequences and using this information to select optimal sequences. This feedback loop enables continuous improvement of pick rate and reduction of cycle time, as the system learns from predicted outcomes and adjusts movement sequences accordingly.
3Productivity
If optimal movement sequences are predicted and selected, then robot performance and pick rate improve, but system complexity and computational requirements increase
Solution Approach 1:
The system performs preliminary prediction of parameter values for alternative movement sequences before actual execution. By predicting time, speed, and energy consumption values in advance, the controller can select optimal sequences without real-time computational burden during execution, reducing the impact of added complexity on operational performance.
Solution Approach 2:
The system replaces traditional mechanical control approaches with computational prediction and selection methods. Instead of relying on complex mechanical mechanisms for optimization, the system uses software-based prediction of parameter values and intelligent selection algorithms, substituting mechanical complexity with computational intelligence that achieves optimal performance more efficiently.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Method for controlling movement sequences (58) of a robot (12), the method comprising predicting values of at least one parameter related to the execution of alternative movement sequences (58) by the robot (12), where each movement sequence (58) comprises at least one movement segment (60) associated with a handling location (40); selecting a movement sequence (58) based on the predicted values of the at least one parameter; and executing the selected movement sequence (58) by the robot (12). A control system (50) for controlling movement sequences (58) of a robot (12) is also provided.