Robot Learning Control via Motor Encoder and Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing learning control techniques for robot systems face challenges such as measurement position errors due to obstructions, high estimation errors with acceleration, gyro, and inertial sensors, and the need for repeated sensor attachment for modified learning processes, leading to inefficiencies and inaccuracies in vibration control.
Innovation Solution
A robot system incorporating a motor encoder and sensors for position detection, with a learning control unit that estimates position errors using both low-frequency components from the motor encoder and high-frequency components from sensors, allowing for accurate correction and reduced man-hours by determining if learning is possible solely with the motor encoder.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a vision sensor is used for position measurement, then measurement capability is improved, but measurement reliability deteriorates due to obstructions
Solution Approach 1:
The patent introduces motor encoder data as an intermediary for estimating the low-frequency position error component. This intermediary provides a reliable backup measurement source that operates independently of visual line-of-sight requirements, ensuring continuous and reliable position estimation even when vision sensors are obstructed.
2Measurement precision
If sensor attachment is required for learning control, then measurement accuracy is improved, but operation time increases due to repeated attachment and detachment
Solution Approach 1:
The patent enables the robot system to perform learning control using its own built-in motor encoder data for the low-frequency position error component. This self-service capability eliminates the mandatory requirement for external sensor attachment, allowing the system to maintain learning control functionality while reducing setup time and operational complexity.
Data Source
AI summary
A robot system includes a robot mechanism unit provided with a sensor and a motor encoder for detecting a position of a control target, and a robot control device which controls an operation of the robot mechanism unit in accordance with an operation program, in which a learning control unit includes a position error estimating section which estimates low-frequency components in a position error, based on information from the motor encoder and estimates high-frequency components in the position error, based on information from the sensor.