In-Vehicle Marker Detection for Autonomous Occupancy Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous vehicles lack an efficient and reliable method to determine their internal state, such as occupancy and passenger characteristics, especially in situations where remote human oversight is unavailable or latency is high.

Innovation Solution

Implementing cameras and machine learning models within the vehicle to identify visible markers and determine the internal state, using markers on seats and seatbelts for improved visibility and processing images to identify occupancy and passenger conditions, with responsive actions defined by action data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If remote human oversight is used to determine internal state, then reliability is improved, but loss of time increases due to high latency

Engineering Contradiction:

Improveinternal state determination reliabilityVSAvoidlatency

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The autonomous vehicle performs self-monitoring of its internal state using onboard cameras and machine learning models, eliminating the need for remote human oversight. The vehicle independently detects occupancy, passenger characteristics, and safety conditions, thereby resolving the latency issue while maintaining reliability through automated real-time analysis.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical/communication-based remote monitoring system with an automated optical detection system using cameras and machine learning algorithms. This substitution enables real-time internal state determination without the time delays inherent in remote human oversight, while maintaining or improving reliability through continuous automated monitoring.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If markers are placed on vehicle elements, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improvemarker detection precisionVSAvoidvehicle interior complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses markers with distinct visual characteristics (such as color, reflectivity, or pattern) that can be easily differentiated by the camera system. These markers are positioned on vehicle elements like seats and seatbelts to indicate occupancy status, providing high measurement precision for internal state detection while maintaining relatively simple implementation through visual differentiation rather than complex sensor integration.

Inventive Principle:

Principle #32Color changes

Data Source

PatentEP3755594B1Determining and responding to an internal status of a vehicle

Publication Date: 2026.01.28 WAYMO LLC

Figure 1
Figure 2
Figure 3

AI summary

Aspects of the disclosure relate to determining and responding to an internal state of a self-driving vehicle 100. For instance, an image of an interior of the vehicle captured by a camera 530, 532, and 534 mounted in the vehicle is received. The image is processed in order to identify one or more visible markers 950, 956, 960, 966 at predetermined locations within the vehicle. The internal state of the vehicle is determined based on the identified one or more visible markers. A responsive action is identified action using the determined internal state, and the vehicle is controlled in order to perform the responsive action.