Tilted Camera Layout for Mobile Robot SLAM Depth Precision

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Mobile robots face challenges in accurately mapping and localizing within environments due to limited disparity in images captured by forward-facing cameras, especially when features are directly in front, leading to difficulties in determining 3D structure and precision of relative pose estimation.

Innovation Solution

The use of tilted cameras with a narrow field of view and increased angular resolution, positioned at an acute angle above the forward direction of motion, enhances disparity observation and precision by capturing images with higher angular resolution without the need for computationally expensive rectification processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a forward-facing camera is used to capture images for SLAM, then the robot can navigate in the forward direction, but the disparity in images is limited when features are directly in front, reducing 3D structure determination accuracy

Engineering Contradiction:
Improve3D structure determination accuracyVSAvoiddisparity information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The camera is tilted at an angle (e.g., 30 degrees) relative to the forward direction of motion, introducing a dimensional change in the viewing angle. This angular offset creates parallax disparity for features directly ahead, enabling the robot to capture depth information that would otherwise be lost with a purely forward-facing camera.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

Instead of symmetric forward-facing camera placement, the system uses asymmetric angular offset by tilting the camera axis relative to the direction of motion. This asymmetric configuration ensures that features at various positions in the field of view produce sufficient disparity for accurate 3D reconstruction.

Inventive Principle:
Principle #4Asymmetry

2Measurement precision

If a tilted camera with narrow field of view is used, then angular resolution is increased and disparity observation is enhanced, but the area covered by each image is reduced

Engineering Contradiction:
Improveangular resolutionVSAvoidimage coverage area
Core Design Contradiction:
Measurement precisionVSArea of stationary object

Solution Approach 1:

The system changes the camera's field of view parameters by using a narrow field of view combined with a tilted angle. This parameter adjustment increases angular resolution for features within the narrowed view, providing more detailed disparity information while the tilt ensures relevant features remain in frame during motion.

Inventive Principle:
Principle #35Parameter changes

3Manufacturing precision

If rectification processes are applied to tilted camera images, then geometric distortion is corrected, but computational complexity and processing time increase

Engineering Contradiction:
Improvegeometric accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent extracts and removes the computationally expensive rectification step from the image processing pipeline. By capturing images at a tilted angle without applying rectification transformations, the system maintains geometric accuracy sufficient for SLAM while significantly reducing computational complexity and processing time.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3224649B1Systems and methods for performing simultaneous localization and mapping using machine vision systems
Publication Date: 2023.04.05 IROBOT CORP
  • EP3224649B1 patent drawingFigure 1A
  • EP3224649B1 patent drawingFigure 1B
  • EP3224649B1 patent drawingFigure 1C

AI summary

The present invention provides a mobile robot configured to navigate an operating environment, that includes a controller circuit that directs a drive of the mobile robot to navigate the mobile robot through an environment using camera-based navigation system and a camera including optics defining a camera field of view and a camera optical axis, where the camera is positioned within the recessed structure and is tilted so that the camera optical axis is aligned at an acute angle of above a horizontal plane in line with the top surface and is aimed in a forward drive direction of the robot body, and the camera is configured to capture images of the operating environment of the mobile robot.