Robot Motion Program Generation Using Selective Human Imitation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing techniques for generating motion control programs for robots struggle to accurately replicate desired motions, especially when the robot's environment, workpiece details, or human motion variability are considered.

Innovation Solution

A method is introduced that displays various parameters related to human motion, allows users to select specific imitation parameters for the robot, and generates a motion control program based on the selected parameters and initial information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If the robot is controlled to uniformly imitate all motions of the human, then the motion control program can be generated by simple imitation, but the robot's motions may be unsuitable for specific work situations and environments

Engineering Contradiction:

Improveease of motion control program generationVSAvoidadaptability to work situations

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent segments human motion into multiple independent parameters (position, posture, speed, acceleration, jerk) that can be selectively imitated. This allows the system to divide the complex motion imitation task into manageable components, enabling easy program generation while adapting specific parameters to match work requirements.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts which motion parameters to imitate based on the specific work situation. By making the imitation parameters configurable rather than fixed, the system can adapt its behavior to different work environments and requirements while maintaining ease of program generation through the selective parameter approach.

Inventive Principle:

Principle #15Dynamics

2Loss of time

If the robot imitates all motion parameters of the human, then the motion control program can be generated quickly, but the complexity of the motion control program increases

Engineering Contradiction:

Improvetime for motion control program generationVSAvoidcomplexity of motion control program

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The patent extracts only the necessary motion parameters from human motion for program generation. By selecting and imitating only relevant parameters (position, posture, speed, acceleration, or jerk) rather than all possible parameters, the system reduces program complexity while maintaining quick generation capability.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Different motion parameters are imitated with different levels of detail based on local requirements. The system applies selective imitation quality to each parameter, imitating some parameters in full detail while using simplified models for others, thereby reducing overall program complexity while maintaining accuracy where needed.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12311541B2Generation method, computer program, and generation system

Publication Date: 2025.05.27 SEIKO EPSON CORP

AI summary

A generation method of generating a motion control program for a robot includes displaying a plurality of parameters relating to a motion of a human, receiving a selection of an imitation parameter as the parameter to be imitated by the robot from the displayed plurality of parameters, and generating the motion control program with reference to the motion of the human corresponding to the received imitation parameter.