C-V2X Event Message Generation for Real-Time Model Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating unpredictable road conditions and adverse weather due to sensor inaccuracies, which can impact their safety and efficiency, and existing technologies struggle to effectively update driving models in real-time.
Innovation Solution
Implementing a C-V2X communication system that allows vehicles to share event messages through roadside units and local edge computing servers, using machine learning to update driving models in real-time based on shared data from surrounding vehicles, enhancing collision prevention and traffic management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicles use sensors to perceive surroundings, then they can navigate and detect obstacles, but sensor accuracy deteriorates in bad weather and challenging road conditions
Solution Approach 1:
The patent combines data from multiple vehicles' sensors through C-V2X communication to create a collective perception system. By merging sensor data from surrounding vehicles, the system compensates for individual sensor limitations in adverse conditions, improving overall measurement precision when single-vehicle sensors fail.
Solution Approach 2:
The patent introduces roadside units (RSUs) and edge computing servers as intermediaries that collect, process, and validate sensor data from multiple vehicles. These intermediaries filter and reconcile sensor information, providing more reliable environmental perception than individual vehicle sensors alone, especially in challenging weather and road conditions.
2Productivity
If autonomous vehicles process and share data in real-time, then driving models can be updated continuously, but network congestion and latency increase
Solution Approach 1:
The patent segments data processing across multiple hierarchical levels: individual vehicles process local sensor data, roadside units aggregate regional data, and edge servers perform comprehensive model updates. This segmentation allows real-time processing at each level without requiring all vehicles to communicate directly with central servers, reducing network latency and congestion.
Solution Approach 2:
The patent uses roadside units and edge computing servers as intermediaries between vehicles and central cloud infrastructure. These intermediaries pre-process and filter data locally, transmitting only essential information to central servers. This reduces the volume of data transmitted over the network, minimizing congestion and latency while enabling continuous model updates.
3Measurement precision
If vehicles share detailed event messages with roadside units, then machine learning models improve accuracy, but network bandwidth consumption increases
Solution Approach 1:
The patent extracts only the most critical features and events from raw sensor data for transmission through C-V2X networks. Instead of sharing complete sensor streams, vehicles transmit selected event messages containing essential information for model training. This extraction maintains machine learning model accuracy while significantly reducing network bandwidth consumption.
Solution Approach 2:
The patent implements partial data sharing where vehicles transmit a subset of sensor data focused on critical events and anomalies. This partial action approach provides sufficient information for effective model training without the excessive bandwidth consumption of transmitting complete sensor datasets from all vehicles.
Data Source
AI summary
A roadside unit (RSU) receives, from a first set of on-board units (OBUs) of a first set of vehicles, messages describing events triggered by the first set of OBUs in response to basic safety messages (BSMs). Each BSM is received by a vehicle from the RSU or another vehicle over a PC5 interface. Each vehicle is operating at less than a threshold distance from the RSU. A timestamp is assigned to each event. A feature vector is extracted from the timestamped events. A machine learning model generates an update to functionality of the RSU based on the feature vector. The machine learning model is trained to update the functionality for vehicular management. The RSU is operated using the updated functionality to communicate with a second set of OBUs of a second set of vehicles for preventing vehicular collisions among the second set of vehicles.