Natural-Language Robot Programming for Fast Task Reconfiguration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional robot programming requires specialized knowledge and expertise, making it difficult and costly for non-experts to reconfigure robots frequently needed in applications like collaborative robots in small workshops, medical labs, and restaurants, where intuitive and accessible programming is essential.

Innovation Solution

A system that enables intuitive robot programming using multiple communication channels such as speech, vision, and touch, translating generic operator inputs into software commands, allowing non-experts to teach robots tasks through natural interaction and providing immediate feedback.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If conventional robot programming using specialized languages is used, then robot programming precision and control capability are improved, but operator skill requirement and programming complexity increase

Engineering Contradiction:
Improverobot programming precisionVSAvoidprogramming complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary system that translates natural language instructions into robot-specific programming commands. This intermediary layer allows operators to communicate with robots using everyday language while the system handles the complex translation to specialized programming languages, thus maintaining programming precision without increasing operator skill requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical approach of directly writing specialized code with a natural language processing system. Instead of operators manually constructing complex programming syntax, the system uses language understanding and translation algorithms to convert simple instructions into precise robot commands, reducing programming complexity while maintaining control capability.

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

2Reliability

If expert engineers program robots, then programming accuracy and task completion reliability are improved, but labor cost and reconfiguration time increase

Engineering Contradiction:
Improvetask completion reliabilityVSAvoidreconfiguration time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent enables robots to be programmed through self-service interfaces where operators can independently configure robot tasks using natural language. The system provides automated translation and validation, allowing non-experts to perform reconfiguration without requiring expert engineers, thus reducing both labor costs and reconfiguration time while maintaining task completion reliability.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent implements preliminary action by pre-configuring translation rules, validation protocols, and error handling mechanisms in advance. This preparation allows the system to quickly and accurately translate natural language instructions into reliable robot commands without requiring expert intervention during the reconfiguration process, reducing both time and cost.

Inventive Principle:
Principle #10Preliminary action

3Ease of operation

If specialized programming languages are used, then robot control precision is improved, but ease of operation and accessibility decrease

Engineering Contradiction:
Improveease of robot programmingVSAvoidtechnical knowledge requirement
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent uses an intermediary natural language processing system that bridges the gap between simple operator instructions and complex robot control requirements. This intermediary translates everyday language into precise technical commands, maintaining control precision while eliminating the need for operators to learn specialized programming languages or technical terminology.

Inventive Principle:
Principle #24Intermediary (Mediator)

4Adaptability or versatility

If frequent robot reconfiguration is performed, then adaptability to different tasks is improved, but cumulative programming cost and time loss increase

Engineering Contradiction:
Improverobot task adaptabilityVSAvoidcumulative reconfiguration time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent enables frequent reconfiguration through self-service programming interfaces that allow operators to quickly adapt robots to different tasks using natural language instructions. The automated translation and validation systems handle the complexity of reconfiguration, allowing rapid task switching without accumulating significant time losses or requiring expert intervention for each change.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3960392A1Method and system for robotic programming
Publication Date: 2022.03.02 ABB (SCHWEIZ) AG
  • EP3960392A1 patent drawingFigure 1
  • EP3960392A1 patent drawingFigure 2
  • EP3960392A1 patent drawingFigure 3

AI summary

A method and system are provided for programming robots by operators without expertise in specialized robot programming languages. In the method, inputs are received from the operator generically describing a desired robot movement. The system then uses the operator inputs to translate the desired robot movement into software commands that direct the robot to perform the desired robot movement. The robot may then be programmed with the software commands and operated to perform the desired robot movement.