Traffic Light Status Estimation From Vehicle and Pedestrian Cues

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in accurately determining traffic light status information when conventional methods like front camera recognition or V2X communication fail, leading to difficulties in controlling autonomous driving at intersections.

Innovation Solution

A traffic light determining apparatus that estimates traffic light status based on surrounding vehicle and pedestrian information when direct information is unavailable, using a processor to determine vehicle behavior and communicate with infrastructure to ensure accurate traffic light information is obtained.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If front camera or V2X communication is used to obtain traffic light information, then traffic light status can be recognized in advance, but traffic light information cannot be obtained when vehicle stops past stop line or when V2X communication fails

Engineering Contradiction:
Improvetraffic light information acquisition reliabilityVSAvoidadaptability to different driving situations
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary actions by detecting surrounding vehicles and pedestrians before the autonomous vehicle reaches the intersection stop line. By analyzing the movement states of these surrounding objects in advance, the system predicts traffic light status before the vehicle stops, ensuring continuous traffic light information availability even when conventional methods fail at the intersection.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses surrounding vehicles and pedestrians as intermediary objects to indirectly determine traffic light status. When direct detection of traffic lights fails or V2X communication is unavailable, the movement patterns of these intermediary objects serve as proxies to infer the current traffic light state, enabling the autonomous vehicle to maintain accurate traffic light information through indirect observation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If traffic light information is not available when entering intersection, then autonomous driving control becomes difficult, but adding more sensing devices increases system complexity

Engineering Contradiction:
Improveautonomous driving control reliabilityVSAvoidsensing and processing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system uses the autonomous vehicle's existing sensing capabilities to detect surrounding vehicles and pedestrians, then processes this data through algorithms that leverage the vehicle's own motion state and position information. This self-service approach allows the system to derive traffic light status from readily available data without requiring additional dedicated sensing hardware, maintaining reliability while avoiding increased system complexity.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The existing sensing devices on the autonomous vehicle are made multi-functional by using them not only for their primary purposes but also for detecting surrounding vehicles and pedestrians to infer traffic light status. This universal use of existing components enables the system to obtain traffic light information without adding specialized sensing equipment, thereby avoiding increased device complexity while improving reliability.

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

Data Source

PatentUS12491914B2Apparatus for determining a traffic light, system having the same and method thereof
Publication Date: 2025.12.09 HYUNDAI MOTOR CO LTD
  • US12491914B2 patent drawing
  • US12491914B2 patent drawing
  • US12491914B2 patent drawing

AI summary

A traffic light determining apparatus, a system including the same, and a method thereof, includes: a processor configured to obtain traffic light status information of an intersection while a vehicle is driven, and when obtaining the traffic light status information is not possible, configured to estimate the traffic light status information according to surrounding vehicle information or pedestrian information; and a storage configured to store data and algorithms driven by the processor.