ROV Position Estimation Using 2D Registration in Noisy Telemetry

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

ROVs operating in underwater environments face challenges with noisy positional telemetry, leading to misalignment between virtual and real elements, which hinders accurate navigation and operation.

Innovation Solution

A system and method that includes a position estimation module to remove outlier estimations, a full registration process for specific structures, and an efficiency module to enhance the alignment of virtual and real elements, using a combination of modules such as 2D projection, registration, and efficiency modules to improve position estimation accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If ROV positional telemetry is used directly for AR rendering, then the system is simple and fast, but the alignment between virtual and real elements becomes inaccurate due to noisy position data

Engineering Contradiction:
Improveposition estimation accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary position estimation module that processes the noisy ROV positional telemetry before using it for AR rendering. This module acts as a mediator between the raw sensor data and the rendering system, applying filtering algorithms (such as Kalman filtering or complementary filtering) to reduce noise and improve position accuracy without requiring hardware changes

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback by continuously comparing the estimated ROV position with visual feedback from the camera feed and 3D model alignment. The position estimation module uses this feedback to continuously refine and correct the ROV position estimates, creating a closed-loop system that improves accuracy over time

Inventive Principle:
Principle #23Feedback

2Measurement precision

If full registration process is performed for all structures, then alignment accuracy is maximized, but computational efficiency and real-time performance deteriorate

Engineering Contradiction:
Improvealignment accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent applies partial registration by performing full registration processes only for selected key structures or when significant alignment errors are detected, rather than continuously registering all structures. This selective approach maintains alignment accuracy for critical elements while reducing overall computational burden and improving real-time performance

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The registration process is segmented into different levels: a fast approximate registration for continuous operation and a more accurate full registration performed selectively. This segmentation allows the system to maintain real-time performance while periodically improving alignment accuracy when needed

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3834175B1System and method of operation for remotely operated vehicles with improved position estimation
Publication Date: 2025.12.17 OCEAN INFINITY (PORTUGAL) SA
  • EP3834175B1 patent drawingFigure 1A~1B
  • EP3834175B1 patent drawingFigure 2A~2B
  • EP3834175B1 patent drawingFigure 3A

AI summary

The present invention provides a system and method of position estimation for remotely operated vehicles, even in noisy environments. In some embodiments, a position estimation engine includes a 2D projection module, a registration module, a position estimation module, and an efficiency module. The improved position estimation starts with a real frame from a video and a virtual image that is the projection of the 3D elements given the ROV's noisy position. The position estimate begins by projecting each of the visible structures individually and then registers them with the real image. Then the 2D transformation resulting from the registration process is used to estimate the 3D ROV's position. Then, the ROV's position estimates are robustly combined. Because this position estimation needs to run in real-time or near real-time, an efficiency module improves the efficiency of the position estimation.