Cloud-Based VRU Path Prediction Using Road Topology Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing VRU prediction technologies, such as those based on 5G NR, provide insufficient path prediction for vulnerable road users like pedestrians and cyclists due to the limitations of current message formats, leading to unreliable and short-lived predictions that can compromise vehicle safety.

Innovation Solution

Enhanced VRU prediction through cloud-based processing that combines VRU path history, location, motion state, and road topology data to improve path prediction accuracy, using algorithms that leverage server-based services to analyze and predict VRU movements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If existing VRU prediction technologies based on 5G NR are used, then basic path prediction can be provided, but the prediction reliability and accuracy are insufficient leading to unreliable and short-lived predictions

Engineering Contradiction:

ImproveVRU path prediction reliabilityVSAvoidpath prediction accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent combines multiple data sources including VRU information from messages, stored VRU information, road topology data, and location data into a unified prediction system. The network device integrates these diverse data types to generate enhanced path predictions that are more reliable and accurate than existing single-source approaches.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary actions by storing VRU information and road topology data in advance. The network device uses this pre-stored information to quickly generate accurate path predictions when needed, improving both the speed and reliability of VRU tracking without requiring real-time data collection for all prediction parameters.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If cloud-based processing with multiple data sources is implemented, then path prediction accuracy is improved, but system complexity increases

Engineering Contradiction:

Improvepath prediction accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The network device serves as an intermediary that receives VRU information from various sources, processes it with stored data and road topology information, and generates enhanced path predictions. This intermediary approach allows the system to leverage multiple data sources without requiring each individual component to handle all processing complexity independently.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12520104B2Enhanced vulnerable road user (VRU) prediction through cloud-based processing

Publication Date: 2026.01.06 QUALCOMM INC

AI summary

Disclosed are systems, apparatuses, processes, and computer-readable media for wireless communications. For example, a network device can receive a message comprising vulnerable road unit (VRU) information corresponding to a VRU. The network device can further determine a path prediction for the VRU based on the VRU information and stored VRU information corresponding to the VRU.