Traffic Light to Lane Assignment via Swarm Data Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies face challenges in accurately assigning traffic lights to lanes, especially in complex intersection situations, leading to high incorrect rates.

Innovation Solution

A procedure where vehicles equipped with front cameras recognize traffic lights and their states, and transmit this data to a backend calculator. The calculator processes the data to determine the traffic light system's position on a map, vehicle movement, and traffic light states, creating an assignment table that correlates traffic lights with lanes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a single vehicle's camera detects traffic lights and lanes at intersections, then the system can identify traffic light positions and orientations, but the assignment accuracy of traffic lights to lanes deteriorates due to complex intersection situations

Engineering Contradiction:
Improvetraffic light detection accuracyVSAvoidtraffic light to lane assignment accuracy
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent merges data from multiple vehicles (swarm) to create a comprehensive view of the intersection. Each vehicle's camera detects traffic lights and lanes independently, but the backend combines all these observations to determine the correct traffic light-to-lane assignments, resolving ambiguities that single-vehicle detection cannot solve

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system uses feedback loops where detected traffic light states and lane information are continuously transmitted to the backend, which refines the assignment table based on accumulated data from multiple vehicles. This feedback mechanism allows the system to learn and improve assignment accuracy over time

Inventive Principle:
Principle #23Feedback

2Device complexity

If traffic light assignment is determined solely by single-vehicle camera detection, then the system complexity remains low, but the assignment correctness deteriorates in diverse intersection scenarios

Engineering Contradiction:
Improvedetection system complexityVSAvoidassignment correctness
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The backend server acts as an intermediary that receives raw detection data from multiple vehicles, processes this information centrally, and generates the final traffic light-to-lane assignment table. This intermediary approach allows complex processing to be distributed rather than embedded in each vehicle, maintaining individual vehicle simplicity while achieving high overall reliability

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The assignment table generated by the backend serves multiple functions: it provides traffic light-to-lane mapping, predicts traffic light states, and guides vehicle navigation decisions. This universal data structure handles diverse intersection scenarios without requiring vehicle-specific customization

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

3Reliability

If the system collects and processes data from multiple vehicles in a swarm, then the traffic light assignment accuracy improves, but the data transmission and processing requirements increase

Engineering Contradiction:
Improvetraffic light assignment accuracyVSAvoiddata volume
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The system extracts only the essential data elements needed for assignment determination from each vehicle's detection output - specifically traffic light positions, orientations, states, and lane information. By filtering out redundant data before transmission to the backend, the system reduces data volume while preserving the information necessary for accurate assignment

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3588464B1Allocation of traffic light to associated lanes
Publication Date: 2025.04.16 VOLKSWAGEN AG
  • EP3588464B1 patent drawingFigure 1
  • EP3588464B1 patent drawingFigure 2

AI summary

A method for assigning traffic lights of a traffic light system of a roadway section controlled by that traffic light system to the lanes of the roadway section, wherein the roadway section has at least one lane, the lanes of the roadway section have a common direction of travel, and a plurality of vehicles travel on the roadway section, comprises the steps of: - detection of an upcoming traffic light system by each vehicle traveling on the roadway section and moving towards the traffic light system, - continuous acquisition of the traffic light states of the traffic light system, the lane being traveled, the vehicle speed, and the vehicle position by each vehicle, wherein the acquisition begins at a predetermined distance from the traffic light system and continues until the traffic light system is passed, - transmission of the data recorded by each vehicle (traffic light states, lane, and speed) in the form of a data set to a backend computer.- The backend computer performs the following evaluations for each vehicle-specific data record: - Determining the identified traffic light system on a map, - Detecting the vehicle's movement through the road segment, - Determining the traffic light states as the vehicle passes the traffic light system, and - Creating an assignment table for the identified traffic light system from the evaluated data records, whereby the assignment table assigns the traffic lights of the traffic light system to the lanes of the road segment.