Camera-Based Vehicle Navigation Using Warped Road Feature Views

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in navigating due to the vast amounts of data they need to process and store, particularly with traditional mapping technologies, which can limit their efficiency and accuracy in interpreting visual information and making decisions for safe navigation.

Innovation Solution

The system uses cameras to capture images, generates warped images from a simulated viewpoint, identifies road features, predicts edge points, clusters them to determine aggregated positions, and implements navigational actions through actuator systems, allowing for efficient data processing and navigation without extensive data storage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional mapping technology is used to navigate, then the vehicle can access comprehensive map data, but the volume of data needed to store and update the map becomes excessively large

Engineering Contradiction:
Improvenavigation accuracyVSAvoiddata storage volume
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential geometric features of the environment (road boundaries, lane markings, obstacles) and represents them as simplified 2D planar surfaces rather than storing complete 3D maps or raw sensor data. This extraction of critical information reduces data storage requirements while maintaining navigation reliability.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of storing comprehensive map data and matching it with sensor inputs, the patent inverts the approach by directly constructing simplified geometric representations from sensor data in real-time. This inversion eliminates the need for large-scale map storage and updating.

Inventive Principle:
Principle #13The other way round (Inversion)

2Reliability

If vast volumes of data are collected and analyzed, then the vehicle can make informed navigation decisions, but the processing time and computational complexity increase significantly

Engineering Contradiction:
Improvenavigation decision accuracyVSAvoiddata processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts only the critical geometric features needed for navigation decisions from sensor data, ignoring redundant information. By focusing on essential elements like road boundaries and obstacles, the system reduces processing time while maintaining decision accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms complex 3D sensor data into simplified 2D geometric parameters representing planar surfaces. This parameter transformation reduces computational complexity by working with fewer, more manageable variables that capture the essential navigation information.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If detailed environmental information is processed, then the vehicle can identify navigation features accurately, but the complexity of the processing system increases

Engineering Contradiction:
Improvefeature identification accuracyVSAvoidprocessing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent changes the parameter representation from complex 3D point clouds to simplified 2D planar surface parameters. This parameter transformation maintains feature identification accuracy by preserving essential geometric relationships while reducing system complexity.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent replaces complex mechanical processing of raw sensor data with mathematical transformations that directly compute geometric parameters. This substitution of computational methods reduces system complexity while maintaining measurement precision.

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

Data Source

PatentEP3818339B1Systems and methods for vehicle navigation
Publication Date: 2024.02.21 MOBILEYE VISION TECH LTD
  • EP3818339B1 patent drawingFigure 1
  • EP3818339B1 patent drawingFigure 2A
  • EP3818339B1 patent drawingFigure 2B

AI summary

Systems and methods are provided for vehicle navigation. In one implementation, at least one processor may be programmed to receive, from a camera, a captured image representative of features in an environment of the vehicle. The processor may generate a warped image based on the received captured image, which may simulate a view of the features in the environment of the vehicle from a simulated viewpoint elevated relative to an actual position of the camera. The processor may further identify a road feature represented in the warped image, which may be transformed in one or more respects relative to a representation of the road feature in the captured image. The processor may then determine a navigational action for the vehicle based on the identified feature represented in the warped image and cause at least one actuator system of the vehicle to implement the determined navigational action.