Assertive Vehicle Detection at Stop-Controlled Intersections

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous vehicles struggle to reliably identify when other vehicles will proceed out of order at stop indicators, leading to inadequate route adjustments and potential collisions.

Innovation Solution

A data-driven model is generated using sensor data from autonomous vehicles to identify characteristics of vehicles at intersections, allowing for the prediction of assertive vehicles that disregard traffic rules, facilitating timely route adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If autonomous vehicles use traditional detection methods to identify vehicles at intersections, then the system complexity remains low, but the reliability of identifying assertive vehicles deteriorates

Engineering Contradiction:

Improvereliability of identifying assertive vehiclesVSAvoidcomplexity of detection model

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary data collection and model training offline before deployment. Historical sensor data from multiple autonomous vehicles is collected, processed, and used to train the detection model in advance. This preliminary action allows the complex model to be ready for real-time use without adding complexity to the operational vehicle systems.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

A remote system acts as an intermediary between data collection and model deployment. The remote system collects sensor data from multiple autonomous vehicles, processes this data to identify assertive vehicle patterns, trains the detection model, and then deploys it to the vehicles. This intermediary handles the complex processing work centrally, keeping individual vehicle systems relatively simple.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If autonomous vehicles collect and process more sensor data to improve detection accuracy, then the measurement precision of vehicle characteristics improves, but the loss of time for data processing increases

Engineering Contradiction:

Improveprecision of vehicle characteristic detectionVSAvoidtime for data collection and processing

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs comprehensive data collection and model training in advance during offline phases. Historical sensor data is gathered and processed beforehand to build the detection model, so that during real-time operation, the vehicle can quickly apply the pre-trained model without extensive processing delays.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The data processing task is segmented into offline and online phases. Complex data collection, processing, and model training are performed offline in segments, while the online phase only requires applying the pre-trained model for real-time detection. This segmentation reduces real-time processing time while maintaining high measurement precision.

Inventive Principle:

Principle #1Segmentation

3Productivity

If autonomous vehicles use simple detection models, then the device complexity remains low, but the productivity of navigating intersections safely deteriorates

Engineering Contradiction:

Improveefficiency of safe intersection navigationVSAvoidcomplexity of detection system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

A remote system serves as an intermediary that handles the complex model training and optimization work. The remote system processes data from multiple vehicles, trains sophisticated detection models, and deploys them to individual vehicles. This allows each vehicle to have access to high-performance models without bearing the full complexity burden, improving intersection navigation efficiency.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The detection model is designed to be universal and multi-functional, capable of identifying various vehicle behaviors and characteristics at intersections. By developing a comprehensive model that handles multiple detection tasks, the system improves overall navigation productivity without requiring separate complex systems for each function.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12494125B2Assertive vehicle detection model generation

Publication Date: 2025.12.09 GM CRUISE HOLDINGS LLC

AI summary

There is disclosed herein examples of system and procedure for generating a model to be implemented within autonomous vehicles for identifying assertive vehicles at an intersection having stop indicators. The model can be generated via data-driven procedure where captures of the movement of vehicles through an intersection are analyzed and utilized for generating the model. The model may be provided to the autonomous vehicles and may be implemented by the autonomous vehicles for identifying assertive vehicles.