Navigation Data Fusion With Constraint-Based Object Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in navigating due to the vast amount of data they need to process and store, which can limit navigation accuracy and safety, and traditional mapping technologies pose significant data management and update challenges.

Innovation Solution

The system uses cameras to provide autonomous vehicle navigation features, constructs and navigates with a crowdsourced sparse map, and fuses data from multiple sources including GPS, sensors, and maps, optimizing navigation while ensuring safety and comfort.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple data sources are used for navigation, then navigation reliability is improved, but computational complexity increases

Engineering Contradiction:
Improvenavigation reliabilityVSAvoidcomputational complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the navigation problem into distinct processing stages: generating candidate hypotheses from sensor data, evaluating each hypothesis against navigational constraints, and verifying results. This segmentation allows complex multi-source data to be processed systematically through modular steps, reducing computational complexity while maintaining reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary filtering by evaluating navigational constraints before final verification. By pre-assessing whether candidate interpretations satisfy known navigational rules and constraints, the system eliminates invalid hypotheses early in the process, reducing the computational burden of full verification while maintaining high reliability.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If navigation constraints are applied, then navigation safety is improved, but processing time increases

Engineering Contradiction:
Improvenavigation safetyVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system evaluates navigational constraints as a preliminary step before final hypothesis verification. By checking whether candidate interpretations satisfy navigational rules in advance, the system quickly eliminates unsafe options without requiring full verification of all hypotheses, thus maintaining safety while reducing processing time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies partial verification by focusing constraint evaluation on the most critical navigational safety aspects rather than exhaustive verification of all possible scenarios. This partial action approach maintains adequate safety levels while significantly reducing processing time compared to complete verification.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4478305B1Fusion framework of navigation information for autonomous navigation
Publication Date: 2026.04.08 MOBILEYE VISION TECH LTD
  • EP4478305B1 patent drawingFigure 1
  • EP4478305B1 patent drawingFigure 2A
  • EP4478305B1 patent drawingFigure 2B

AI summary

The present disclosure relates to apparatuses, systems and methods for navigating vehicles. In one implementation, at least one processing device receive a first output from a first data source and a second output from a second data source; identify a representation of a target object in the first output; determine whether a characteristic of the target object triggers at least one navigational constraint; if the at least one navigational constraint is not triggered by the characteristic of the target object, verify the identification of the representation of the target object based on a combination of the first output and the second output; if the at least one navigational constraint is triggered by the characteristic of the target object, verify the identification of the representation of the target object based on the first output; and in response to the verification, cause at least one navigational change to the vehicle.