Autonomous Driving IoT Platform for VRU Intention Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face challenges in preventing accidents with vulnerable road users due to reliance on in-built sensors and roadside units, lacking direct and voluntary information from vulnerable road users.
Innovation Solution
An in-vehicle IoT platform in autonomous vehicles detects vulnerable road users through a combination of mobile device data and vehicle sensors, using machine learning models to predict movement intentions and inform autonomous driving decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous driving systems rely only on in-built sensors and roadside units, then system complexity is reduced, but detection precision and reliability for vulnerable road users deteriorate
Solution Approach 1:
The patent merges multiple data sources including in-vehicle sensors, roadside units, and mobile device data from vulnerable road users into a unified detection system. This combination integrates diverse information streams to improve detection precision while distributing system complexity across multiple components rather than concentrating it in a single system.
Solution Approach 2:
The patent introduces mobile devices as intermediary components that voluntarily provide additional data about vulnerable road users. These devices act as mediators between the autonomous vehicle system and the road environment, enhancing detection capabilities without requiring direct integration of all sensing functions into the vehicle itself.
2Reliability
If traditional sensor-only approaches are used, then ease of operation is maintained, but reliability in preventing accidents with vulnerable road users deteriorates
Solution Approach 1:
The patent implements a self-service mechanism where vulnerable road users voluntarily activate mobile applications on their own devices to provide identification and movement data. This approach enhances reliability by enabling vulnerable road users to actively participate in their own safety without requiring complex operational procedures from autonomous vehicle operators.
3Loss of information
If only in-vehicle sensor data is used, then loss of information is minimized within the vehicle system, but loss of information occurs from excluding voluntary data from vulnerable road users
Solution Approach 1:
The patent creates a multi-functional data integration platform that processes diverse information types including sensor data, mobile device data, and voluntary user information. This universal system handles multiple data sources through a unified architecture, reducing information loss while managing complexity through standardized processing protocols.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for supporting autonomous driving of an autonomous vehicle, in particular in terms of an interaction with a vulnerable road user that is in the vicinity of the autonomous vehicle, the method comprising: detecting, by an in-vehicle IoT platform of the autonomous vehicle, a vulnerable road user, 'VRU', having a mobile device in the vicinity of the autonomous vehicle, wherein a mobility application runs on the mobile device of the VRU and sends VRU-specific data to the in-vehicle IoT platform of the autonomous vehicle, wherein the VRU is detected based on the VRU-specific data and/or in-vehicle sensor data of the autonomous vehicle; determining, by the in-vehicle IoT platform, a movement intention prediction for the VRU based onthe VRU-specific data provided bythe mobile device, wherein the movement intention prediction is computed by the use of a machine learning model, wherein the VRU-specific data of the mobile device areemployed as input data for said machine learning model; and performing, by the in-vehicle IoT platform, an autonomous driving decision for the autonomous vehicle based on said movement intention prediction. Furthermore, a corresponding system for supporting autonomous driving of an autonomous vehicle is disclosed.