Robot Constraint Learning From Task Success and Failure

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Setting constraint conditions manually for robot operation planning is difficult and time-consuming.

Innovation Solution

A constraint condition learning device that converts first time series data into propositional time series data and estimates constraint conditions as logical formulas based on task success or failure, using a conversion unit and constraint condition estimation unit.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If constraint conditions are set manually for robot operation planning, then the accuracy and reliability of constraint conditions can be ensured, but the time consumption and complexity of the setting process increase significantly

Engineering Contradiction:

Improveconstraint condition accuracyVSAvoidconstraint condition setting time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables automatic learning of constraint conditions through machine learning algorithms that process observation data and task outcomes independently, eliminating the need for manual constraint condition setting while maintaining high accuracy through self-improving mechanisms

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system incorporates feedback loops where task execution outcomes are used to refine and update constraint conditions automatically. The machine learning model continuously learns from successful and unsuccessful task executions, adjusting constraint conditions to improve future performance without manual intervention

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If all constraint conditions are set manually, then comprehensive coverage of task requirements can be achieved, but the complexity and difficulty of the setting process increase

Engineering Contradiction:

Improveconstraint condition coverageVSAvoidsetting process complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system automatically discovers and learns constraint conditions from observation data and task outcomes, enabling comprehensive coverage of task requirements without manual configuration. The machine learning process handles the complexity of identifying all necessary constraints across diverse task scenarios

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The constraint condition learning process is divided into distinct phases: data collection, proposition conversion, constraint estimation, and validation. This segmentation allows the system to handle complex constraint discovery systematically through manageable computational steps

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12544918B2Constraint condition learning device, constraint condition learning method, and storage medium

Publication Date: 2026.02.10 NEC CORP

AI summary

A constraint condition learning device 1X mainly includes a conversion means 15X and a constraint condition estimation means 16X. The conversion means 15X converts first time series data regarding a state and an input of a robot system during an execution period of a task executed by the robot system into second time series data represented by propositions. The constraint condition estimation means 16X estimates a constraint condition on the task as a logical formula, based on the second time series data and the information regarding whether or not the task succeeded.