Traffic Light Identification Data for Autonomous Driving

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing techniques for associating lanes with traffic lights in autonomous driving systems are not accurate, leading to potential errors in identifying the correct traffic light to obey, especially in intersections with multiple lights, which can compromise safety.

Innovation Solution

A data generation and storage system that generates and stores traffic light identification data including lane information, traffic light information, and confidence levels for each light, allowing the vehicle to identify the most trustworthy traffic light based on the lane it is traveling on, using a data structure that compares confidence levels across multiple traffic lights.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If multiple traffic lights are associated with a single lane in the map data, then the system can provide comprehensive traffic light information, but the vehicle cannot determine which specific traffic light to obey, reducing reliability

Engineering Contradiction:
Improvenumber of traffic light associationsVSAvoidaccuracy of traffic light identification
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent segments the undifferentiated set of traffic light associations by introducing lane connection relationships. Each traffic light is associated with specific lanes through which vehicles must pass to reach the traffic light, creating a segmented and structured data model that enables precise identification of the relevant traffic light for a given lane and vehicle position.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If simple lane-traffic light association is used, then the data structure is simple, but the system cannot accurately identify the correct traffic light in intersections with multiple lights

Engineering Contradiction:
Improvedata structure complexityVSAvoidtraffic light identification accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent adds a spatial dimension to the lane-traffic light association by introducing lane connection relationships. Instead of a simple one-to-one or one-to-many association, the system creates a multi-dimensional relationship where traffic lights are connected to lanes through defined paths, enabling accurate identification while maintaining manageable data structure complexity.

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

Data Source

PatentUS20240426631A1Data generation device and data storage device
Publication Date: 2024.12.26 DENSO CORP
  • US20240426631A1 patent drawing
  • US20240426631A1 patent drawing
  • US20240426631A1 patent drawing

AI summary

A data generation device includes a data generation unit configured to generate data. The data generation unit is further configured to generate, as the data, traffic light identification data including lane information for identifying a lane in which a vehicle is traveling, traffic light information for identifying a plurality of traffic lights installed at an intersection to which the lane is connected, and confidence information indicating a degree of confidence set for each of the plurality of traffic lights. The traffic light identification data has a data structure that allows the traffic light that should be trusted to be identified based on the degrees of confidence set for the plurality of traffic lights depending on the lane in which the vehicle is traveling.