Visual Following Robot Control for Unpredictable Conveyor Motion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing production lines face challenges in preventing damage to robots, conveying devices, and items due to unpredictable movements of items being conveyed, particularly during operations that involve potential interference.
Innovation Solution
A following robot system equipped with a movable arm, visual sensor, feature-value storage, and control units that utilize feedforward control to adjust movement instructions based on detected position and orientation differences, allowing the robot to accurately follow the item and perform tasks despite vibrations or unpredictable movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the robot moves along the rail at the same velocity as the conveying device, then the robot can perform defect inspection and polishing, but the robot cannot prevent damage when the item behaves unpredictably or vibrates
Solution Approach 1:
The patent implements feedback control by detecting the actual position and orientation of the item using visual sensors, comparing it with the robot's current state, and adjusting the robot's movement instructions in real-time. This closed-loop control system enables the robot to respond to unpredictable item motions and vibrations, preventing damage while maintaining reliable operation during defect inspection and polishing tasks.
Solution Approach 2:
The patent applies feedforward control by pre-calculating and storing movement instructions for the robot based on expected item trajectories and conveying device motions. These preliminary movement instructions are prepared in advance and executed proactively, allowing the robot to anticipate and prepare for item movements before they occur, thereby preventing damage during unpredictable motions.
2Extent of automation
If the robot performs work with potential interference between the robot and the item, then the robot can accomplish complex tasks, but damage prevention becomes difficult due to unpredictable item behavior
Solution Approach 1:
The patent implements dynamic control by continuously adjusting the robot's movement instructions in real-time based on detected item position and orientation. The system transitions from static pre-programmed paths to dynamic adaptive trajectories, enabling the robot to perform complex tasks with potential interference while maintaining reliability through real-time responsiveness to item behavior changes.
Solution Approach 2:
The patent uses feedback control to monitor the actual relative position and orientation between the robot and item during complex tasks, comparing it with desired trajectories, and adjusting movement instructions accordingly. This real-time feedback mechanism enables the robot to safely navigate complex operations with potential interference while preventing damage from unpredictable item motions.
3Reliability
If the robot uses only feedback control to follow the item, then the robot can respond to item position changes, but the robot cannot proactively anticipate and prepare for item movements
Solution Approach 1:
The patent applies preliminary action through feedforward control by pre-calculating movement instructions based on expected item trajectories and conveying device motions. The robot proactively executes these pre-planned movements in anticipation of item positions, eliminating response delays while maintaining accurate tracking. This preliminary preparation allows the robot to be in the correct position before the item arrives, rather than reacting after detection.
Solution Approach 2:
The patent implements continuous useful action by combining feedforward and feedback control mechanisms that operate simultaneously and continuously. The feedforward component provides continuous proactive movement instructions based on expected trajectories, while the feedback component continuously adjusts these instructions based on actual item positions. This continuous dual-mode control ensures both anticipatory response and accurate tracking without interruption or delay.
Data Source
AI summary
A following robot including an arm, at least one visual sensor, a feature-value storage unit that stores, as target data for causing the visual sensor to follow a follow target, first feature values related to at least the position and the orientation of the follow target, a feature-value detecting unit for detecting, by using an image acquired by the visual sensor, second feature values related to at least current position and orientation of the follow target, a movement-amount computing unit computing a movement instruction based on differences between the second feature values and the first feature values and adjusting the movement instruction by using at least feedforward control, a movement instructing unit which moves the arm based on the movement instruction, and an input-value storage unit that stores a signal acquired when a specific motion of the follow target is started and an input value for the feedforward control.