Functional Road Map Generation for Navigation Without HD Maps

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing autonomous vehicle navigation systems rely on high-definition mapping that requires costly and time-consuming manual updates, and there is a need for systems that can navigate without pre-existing maps or GPS connections.

Innovation Solution

Generate functional road maps in real-time using visual input from vehicle sensors, employing an Artificial Neural Network (ANN) with an encoder-decoder architecture to transform front-view images into top-down maps, incorporating self-attention modules and coordinate-augmented convolutions for accurate navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high-definition mapping with manual updates is used, then navigation accuracy is improved, but cost and time consumption increase

Engineering Contradiction:
Improvenavigation accuracyVSAvoidtime consumption for map updates
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system enables autonomous vehicles to generate their own functional maps in real-time using onboard sensors and neural networks, eliminating the need for manual map updates. The vehicle independently perceives road structures, lane markings, and navigation-relevant features, serving its own mapping needs without external intervention

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent transitions from static pre-defined HD maps to dynamic real-time map generation. The functional map is continuously updated as the vehicle moves, with the neural network processing current sensor data to generate up-to-date navigation information adapted to changing road conditions

Inventive Principle:
Principle #15Dynamics

2Reliability

If pre-mapped areas are required for navigation, then route planning reliability is improved, but adaptability to new locations deteriorates

Engineering Contradiction:
Improveroute planning reliabilityVSAvoidadaptability to new locations
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary perception and mapping actions in real-time as the vehicle encounters new areas. The neural network continuously processes sensor data to pre-identify road structures, lane configurations, and navigation features before they are needed for route planning, enabling immediate adaptation to new locations

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent transforms the navigation approach from relying on pre-existing 2D map data to generating 3D functional spatial understanding in real-time. The system creates a functional map that includes elevation, lane geometry, and road structure information directly from sensor data, enabling navigation in unmapped areas with the same reliability as mapped areas

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

3Manufacturing precision

If manual HD map maintenance is performed, then map accuracy is improved, but operational cost increases

Engineering Contradiction:
Improvemap accuracyVSAvoidoperational cost
Core Design Contradiction:
Manufacturing precisionVSEase of manufacture

Solution Approach 1:

The patent replaces the mechanical process of manual map creation and maintenance with an automated neural network-based perception system. The neural network processes sensor data to automatically generate and update functional maps, eliminating the need for human surveyors, data processors, and map maintainers while preserving map accuracy

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

Solution Approach 2:

The system creates functional copies of road structures and navigation features directly from sensor perception rather than manual surveying. The neural network generates simplified functional representations of complex road geometries, capturing essential navigation information at a fraction of the cost of traditional HD map production

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3832260B1Real-time generation of functional road maps
Publication Date: 2025.08.27 IMAGRY ISRAEL LTD
  • EP3832260B1 patent drawingFigure 1
  • EP3832260B1 patent drawingFigure 2
  • EP3832260B1 patent drawingFigure 3A~3B

AI summary

A method, an apparatus and a computer program for real-time generation of functional road maps. The method comprises obtaining a real-time input from a sensor mounted on a vehicle, that captures a front view of a road ahead of the vehicle and processing thereof by a neural network to generate a functional map of the road ahead of the vehicle. Each pixel in the functional map is associated with a predetermined relative position to the vehicle. A content of each pixel is assigned a set of values, each of which represents a functional feature relating to a location at a corresponding predetermined relative position to the pixel. The processing is performed without relying on a pre-determined precise mapping. The method further comprises providing the functional map to an autonomous navigation system of the vehicle, to autonomously drive the vehicle in accordance with functional features represented by the functional map.