Robot Trajectory Transformation for Non-Expert Task Reprogramming

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional robot programming is laborious and requires significant rework when changes occur in the work environment or task, as users need to re-implement entire tasks, which is time-consuming and costly, especially for non-expert users without programming skills.

Innovation Solution

A system comprising a translator and a transformer that allows users to provide high-level descriptions of modifications to existing robot trajectories, translating these into applicable transformations for updating the trajectories without requiring specialized programming expertise, enabling non-expert users to modify robot tasks intuitively and efficiently.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If conventional robot programming methods are used, then the robot can execute tasks with high precision, but the programming process becomes laborious and time-consuming when changes are required

Engineering Contradiction:
Improvetrajectory accuracyVSAvoidreprogramming time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system records the operator's natural movements and actions as they perform the task manually. This preliminary capture of motion data creates a foundation trajectory that can be later transformed and adapted, eliminating the need to program from scratch when changes are needed.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system allows transformation of the recorded trajectory by changing parameters such as start position, target position, speed, and timing. By modifying these parameters, the same base trajectory can adapt to different task requirements, reducing reprogramming time while maintaining precision.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If expert engineers use specialized programming software to program robots, then the robot trajectory can be precisely controlled, but the process requires significant expertise and cannot be easily performed by non-expert users

Engineering Contradiction:
Improvetrajectory controlVSAvoidprogramming accessibility
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The system enables non-expert users to program the robot themselves by simply demonstrating the desired task through natural movement. The operator's own actions become the program, eliminating the need for specialized programming knowledge while the system handles the complex trajectory generation and control automatically.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system replaces complex programming software and expert knowledge with a motion capture and transformation system. Instead of requiring users to write code or configure parameters in specialized software, the system captures physical movements and automatically translates them into robot trajectories, making the process accessible to anyone regardless of programming expertise.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If the work environment or task changes frequently, then the robot must be reprogrammed each time, but this increases the initial time investment and reduces economic efficiency

Engineering Contradiction:
Improvetask flexibilityVSAvoidreprogramming efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system creates a library of recorded trajectories that serve as reusable templates. When the task changes, the system can select from existing recorded trajectories or combine them, rather than requiring complete reprogramming. This preliminary capture of multiple potential trajectories enables quick adaptation to changing requirements.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically transforms recorded trajectories based on the specific task requirements. Instead of static, fixed programs, the system can adapt existing trajectories through transformation operations, allowing the same base recordings to serve multiple purposes and reducing the need for frequent reprogramming when tasks change.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3960393A1Method and system for programming a robot
Publication Date: 2022.03.02 ABB (SCHWEIZ) AG
  • EP3960393A1 patent drawingFigure 1
  • EP3960393A1 patent drawing
  • EP3960393A1 patent drawing

AI summary

A method and system are provided for programming robots by users without expertise in specialized robot programming languages. In the method, a high-level description is provided by the user to a translator. The translator translates the description into a transformation. A transformer applies the transformation to an existing robot trajectory in order to provide an updated robot trajectory. The updated robot trajectory is then used to operate the robot.