Sensor Pose Calibration for Marker-Based Robot Localization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for mapping and localization in warehouse environments using autonomous robots rely on manual surveys and fixed sensor-to-robot transforms, which are time-consuming and prone to errors, delaying deployment and affecting navigation accuracy.

Innovation Solution

Implementing a graph-based system that calibrates sensor poses relative to the robot using marker detection data, optimizing a cost function to determine sensor pose transforms and motion model parameters, enabling real-time mapping and localization with reduced errors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If manual surveys and fixed sensor-to-robot transforms are used for mapping and localization, then deployment process is simplified, but mapping time is excessive and navigation accuracy deteriorates

Engineering Contradiction:
Improvedeployment simplicityVSAvoidmapping time
Core Design Contradiction:
Ease of manufactureVSLoss of time

Solution Approach 1:

The system performs self-calibration and self-localization by having the robot autonomously navigate through the environment, detect markers, and compute its own pose and sensor transforms without requiring manual surveying or external intervention. The robot serves itself by collecting sensor data and solving the localization and calibration problems independently.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system changes the approach from fixed, pre-determined transforms to dynamically computed transforms based on actual sensor measurements and marker detections. By optimizing transform parameters through cost function minimization using real-world data, the system achieves both speed and accuracy simultaneously.

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If manual surveys are used for sensor calibration, then calibration process is straightforward, but navigation accuracy deteriorates and deployment is delayed

Engineering Contradiction:
Improvecalibration simplicityVSAvoidnavigation accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system uses feedback from actual sensor measurements of markers in the environment to continuously refine and optimize the sensor-to-robot transforms. The cost function incorporates measurement residuals that guide the optimization process, allowing the system to achieve high precision by learning from real-world data rather than relying on manual calibration.

Inventive Principle:
Principle #23Feedback

3Device complexity

If fixed sensor-to-robot transforms are assumed, then system complexity is reduced, but localization accuracy and real-time performance deteriorate

Engineering Contradiction:
Improvesystem complexityVSAvoidlocalization accuracy
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system transitions from static, fixed transforms to dynamic, adaptive transforms that are continuously optimized based on real-time sensor measurements. The transforms are not predetermined but are computed and refined as the robot navigates, allowing the system to maintain high reliability and accuracy while adapting to actual environmental conditions.

Inventive Principle:
Principle #15Dynamics

4Ease of manufacture

If traditional mapping methods are used, then deployment process is simpler, but productivity and real-time feedback capability deteriorate

Engineering Contradiction:
Improvedeployment process simplicityVSAvoidmapping speed
Core Design Contradiction:
Ease of manufactureVSProductivity

Solution Approach 1:

The system performs mapping and localization continuously as the robot navigates through the environment, rather than requiring separate pre-mapping and calibration phases. The useful action of data collection and computation occurs continuously during normal operation, enabling real-time feedback and significantly improving productivity without complicating the deployment process.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP3590016B1Method and system for simultaneous localization and sensor calibration
Publication Date: 2021.12.22 X DEVELOPMENT LLC
  • EP3590016B1 patent drawingFigure 1
  • EP3590016B1 patent drawingFigure 2
  • EP3590016B1 patent drawingFigure 3

AI summary

Simultaneous localization and calibration may involve receiving sensor data indicative of markers detected by a sensor on a vehicle located at vehicle poses within an environment, and determining a pose graph representing the vehicle poses and the markers. For instance, the pose graph may include edges associated with a cost function representing a distance measurement between matching marker detections at different vehicle poses. The distance measurement may incorporate the different vehicle poses and a sensor pose on the vehicle. The implementation further involves determining a sensor pose transform representing the sensor pose on the vehicle that optimizes the cost function associated with the edges in the pose graph, and providing the sensor pose transform.