Robot Supplemental Learning for Unforeseen Work Interruptions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robot systems cannot continue operations when encountering unforeseen situations or when the learned environment changes, leading to interruptions in work processes.

Innovation Solution

A robot system equipped with a state detection sensor, timekeeping unit, learning control unit, determination unit, operation device, switching device, and additional learning unit that allows for autonomous additional learning to update the model based on operator inputs and sensor data, enabling the robot to adapt and continue operations even when initial conditions are not met.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If the robot operates based on a pre-learned model, then the robot can perform work autonomously, but the robot cannot continue work when encountering unforeseen situations or when the learned environment changes

Engineering Contradiction:
Improveautonomous work capabilityVSAvoidadaptability to unforeseen situations
Core Design Contradiction:
Extent of automationVSAdaptability or versatility

Solution Approach 1:

The robot system performs additional learning autonomously without operator intervention when work cannot be continued. The additional learning unit automatically acquires new data from sensor readings and timer signals, updates the model, and restores autonomous operation, making the system self-repairing and self-adapting

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The determination unit continuously monitors whether the robot can continue work based on current state values. When work cannot be continued, this feedback triggers the additional learning process. The system uses feedback from the environment (sensor data) to adapt and improve its model, creating a closed-loop adaptive system

Inventive Principle:
Principle #23Feedback

2Reliability

If the robot stops work when encountering unknown situations, then operational safety is maintained, but productivity is reduced due to work interruptions

Engineering Contradiction:
Improveoperational safetyVSAvoidwork continuity
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs additional learning during periods when work cannot continue, preparing the updated model in advance. The timekeeping unit tracks learning duration, and once learning is complete, the robot resumes work with the updated knowledge, transforming downtime into productive learning time

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes the operational parameter from 'work execution mode' to 'additional learning mode' when encountering unknown situations. This parameter switching allows the robot to adapt its behavior dynamically, learning from new situations and then returning to work with improved capabilities

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If the robot arm is caught or the situation is not learned in advance, then the robot cannot continue work, but with additional learning the robot can adapt and continue operations

Engineering Contradiction:
Improveability to handle new situationsVSAvoidsystem structure complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The additional learning unit serves multiple functions: it detects when work cannot continue, acquires new training data from sensors, updates the machine learning model, and manages the transition between work and learning modes. This multi-functional component handles diverse tasks without requiring separate specialized systems for each function

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent combines the determination unit, additional learning unit, and model updating functionality into an integrated system. The switching device merges operator operation force with calculation operation force to generate unified operation commands, consolidating multiple control inputs into a single coordinated output

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS11858140B2Robot system and supplemental learning method
Publication Date: 2024.01.02 KAWASAKI JUKOGYO KK
  • US11858140B2 patent drawing
  • US11858140B2 patent drawing
  • US11858140B2 patent drawing

AI summary

A robot system includes a robot, state detection sensors to, a timekeeping unit, a learning control unit, a determination unit, an operation device, and an input unit, and an additional learning unit. The determination unit determines whether or not the work of the robot can be continued under the control of the learning control unit based on the state values detected by the state detection sensors to and outputs determination result. The additional learning unit performs additional learning of the determination result indicating that the work of the robot cannot be continued, the operator operation force, work state output by the operation device and the input unit, and timer signal output by the timekeeping unit.