Occupancy Grid Road Branch Detection Without Lane Markings

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver assistance systems rely on traffic signs and lane markings, which may be absent, damaged, or incorrect, making it difficult to reliably detect locations where roads diverge or converge.

Innovation Solution

An occupancy grid-based method and apparatus that detects road boundaries to identify locations where branches of an area converge or diverge, using chains of region of interest windows to efficiently and accurately determine the number of boundaries.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If lane markings and traffic signs are used to detect road branches, then detection accuracy is improved, but reliability deteriorates when markings are absent, damaged, or unclear

Engineering Contradiction:
Improvedetection accuracyVSAvoidreliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent introduces occupancy grids as an intermediary representation layer between raw sensor data and road branch detection. The occupancy grid converts complex visual information from lane markings and signs into simplified probability maps of free space, enabling reliable detection of road branches through geometric analysis of occupancy patterns rather than direct reliance on potentially degraded markings or signs.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical/visual system of detecting road branches through lane markings and traffic signs with a computational system based on occupancy probability analysis. Instead of relying on physical road infrastructure (markings, signs), the system uses sensor data to construct probabilistic occupancy models and detects road branches through mathematical analysis of boundary convergence and divergence in the occupancy grid.

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

2Reliability

If multiple sensors and complex processing are used to detect road branches without relying on markings, then reliability is improved, but device complexity increases

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The occupancy grid system serves multiple functions simultaneously: it represents free space for navigation, enables road boundary detection, facilitates road branch identification, and provides a unified framework for integrating data from different sensor types. This multi-functionality reduces the need for separate specialized systems while maintaining high reliability in detecting road branches without relying on markings or signs.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3582135B1Method and apparatus for detecting, in an environment of an object, the presence of a location where road branches of an area within the environment converge or diverge
Publication Date: 2026.05.13 AUMOVIO AUTONOMOUS MOBILITY GERMANY GMBH
  • EP3582135B1 patent drawingFigure 1~2
  • EP3582135B1 patent drawingFigure 3~4
  • EP3582135B1 patent drawingFigure 5

AI summary

The invention provides for a detection, in an environment of an object, of the presence of a location where road branches of an area within the environment converge or diverge. The detection is based on an occupancy grid which provides information about the probability of occupancy in the environment of the object. Boundaries of the area are detected based on values of grid cells of the occupancy grid. The number of boundaries is identified. Depending on the number of boundaries identified, the presence of a location where branches of the area converge or diverge is signalled.