Robot Pose Validation Using Digital Twin Sensor Comparison

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current validation methods for robot pose and sensor data are inadequate, particularly in ensuring safety standards for human-robot collaboration, as they lack secure interfaces and reliable validation processes, leading to potential safety risks in industrial environments.

Innovation Solution

A method and system that utilize simulated robot and sensor data to validate the pose and sensor data through cross-comparisons, creating digital twins of the robot and sensor to ensure accurate alignment with real-world conditions, using a computing unit connected to the robot and sensor, allowing for adaptable and high-quality validation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If complex safety measures such as redundant electronics and function monitoring are implemented to meet safety standards, then the reliability of safety monitoring is improved, but the device complexity increases

Engineering Contradiction:
Improvesafety monitoring reliabilityVSAvoidsafety system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a digital twin (virtual model) of the robot and its sensor system that replicates the physical system's behavior. This virtual model is used to validate sensor data and robot pose without requiring additional physical safety components. By copying the system's functionality in a virtual environment, the patent achieves validation capabilities while avoiding the complexity of redundant physical safety systems.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces complex mechanical and electronic safety validation systems with a computational approach using digital twins and simulated sensor data. Instead of using redundant physical sensors and electronics to validate safety, the system uses virtual simulations to compare against real sensor data, substituting mechanical complexity with information processing.

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

2Reliability

If traditional safety validation methods are used, then safety standards are met, but the ease of operation and adaptability to different robots deteriorates

Engineering Contradiction:
Improvesafety standard complianceVSAvoidvalidation implementation ease
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The digital twin validation system is designed to be universally applicable to different robot types and sensor configurations. The virtual model can be adapted to represent various robot geometries, kinematics, and sensor setups, allowing the same validation methodology to be used across different platforms without requiring robot-specific safety validation procedures.

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

Solution Approach 2:

The system validates safety by comparing parameters from the digital twin (simulated sensor data) with parameters from the physical system (real sensor data). By changing and adjusting these parameters in the virtual model to match the physical system, the patent achieves adaptable validation that works across different robot configurations while maintaining safety standard compliance.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If sporadic tests to known reference positions are performed, then some validation is achieved, but measurement precision and continuous validation capability are insufficient

Engineering Contradiction:
Improvevalidation capabilityVSAvoidpose validation precision
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent implements continuous validation by constantly comparing real sensor data with simulated sensor data from the digital twin throughout the robot's operation. Instead of performing intermittent tests at reference positions, the validation process runs continuously during normal operation, providing ongoing assurance of sensor accuracy and robot pose without interrupting workflow.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system uses feedback from the comparison between real and simulated sensor data to continuously validate the robot's pose and sensor measurements. The digital twin provides expected sensor readings based on the robot's reported pose, and any discrepancies trigger validation alerts. This feedback mechanism enables precise, continuous validation without requiring external reference measurements.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4385676B1Validation of a pose of a robot and of sensor data of a sensor moving along with the robot
Publication Date: 2024.11.13 SICK AG
  • EP4385676B1 patent drawingFigure 1~2
  • EP4385676B1 patent drawingFigure 3~4
  • EP4385676B1 patent drawingFigure 5~6

AI summary

A method for validating the pose of a robot (10) and/or sensor data of a sensor (12) moving with the robot (10) is described, wherein a robot controller (28) determines the actual pose of the robot (10) and the sensor (12) measures actual sensor data. A robot simulation (24) determines a simulated pose of the robot (10) by means of a simulated movement of the robot (10), and a sensor simulation (26) determines simulated sensor data of the sensor (12) by means of a simulated sensor measurement. Validation is performed by at least one comparison of the actual pose and the simulated pose of the robot (10), of actual sensor data and simulated sensor data, and/or of simulated sensor data among themselves.