Service Robot Mode Selection Between Rule-Based and Learned Behavior

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Service robots face limitations in adapting their behavior to optimize performance and safety in dynamic situations, as they typically operate in either rule-based or training-based modes, which may not be suitable for all environments and tasks.

Innovation Solution

A service robot system that determines an evaluation index based on sensor data to selectively switch between rule-based and training-based behaviors, allowing it to choose the most appropriate behavior for the current operation mode and improve performance over time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the service robot operates in rule-based mode, then the operation is reliable and predictable, but the adaptability to dynamic situations is limited

Engineering Contradiction:
Improveoperation reliabilityVSAvoidbehavior adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The robot system dynamically switches between rule-based and training-based behaviors based on the determined operation mode. The control system adjusts the behavior type in real-time according to the evaluation index, allowing the robot to transition from static rule-based operations to adaptive training-based operations when needed, thus resolving the contradiction between reliability and adaptability.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the behavioral parameter of the robot by selecting different behavior types (rule-based or training-based) based on the determined operation mode. This parameter change allows the robot to optimize its performance characteristics according to different operational requirements, maintaining reliability when using rules and gaining adaptability when using training-based approaches.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If the service robot uses training-based behavior, then the adaptability to different environments is improved, but the performance consistency may deteriorate

Engineering Contradiction:
Improveenvironmental adaptabilityVSAvoidperformance consistency
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system dynamically selects between training-based and rule-based behaviors based on the operation mode determination. When training-based behavior provides sufficient adaptability, the system uses it; otherwise, it switches to rule-based behavior to ensure performance consistency, thus balancing adaptability and reliability dynamically.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system uses the evaluation index as feedback to determine the operation mode and select appropriate behavior types. This feedback mechanism ensures that the robot monitors its performance and environmental conditions, adjusting its behavior selection to maintain both adaptability and performance consistency based on real-time assessments.

Inventive Principle:
Principle #23Feedback

3Productivity

If the service robot switches between different behavior types, then the performance optimization is improved, but the system complexity increases

Engineering Contradiction:
Improveperformance optimizationVSAvoidcontrol system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The control system is segmented into distinct modules: an evaluation index determination unit, an operation mode determination unit, and a behavior selection unit. This segmentation allows the complex function of adaptive behavior selection to be divided into manageable components, reducing overall system complexity while maintaining performance optimization capabilities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The robot system performs self-assessment through the evaluation index and automatically determines the appropriate operation mode and behavior type without external intervention. This self-service capability simplifies the control architecture by eliminating the need for complex external control mechanisms, achieving performance optimization through autonomous decision-making.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3670109B1Method and apparatus for controlling behavior of service robot
Publication Date: 2021.11.03 SAMSUNG ELECTRONICS CO LTD
  • EP3670109B1 patent drawingFigure 1
  • EP3670109B1 patent drawingFigure 2
  • EP3670109B1 patent drawingFigure 3

AI summary

A method and apparatus for controlling an operation of a service robot is disclosed. The method includes measuring, by processing circuitry, an evaluation index of the service robot based on sensor data in a service mode; determining, by the processing circuitry, an operation mode of the service robot from a set of at least two operation modes based on the measured evaluation index; selecting, by the processing circuitry, a behavior to be applied to the operation of the service robot from a set of at least two behaviors based on the operation mode; and controlling, by the processing circuitry, the operation of the service robot based on the behavior.