On-board unit machine learning communication model

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current vehicle-to-X communication systems face challenges in optimizing maneuver coordination between vehicles, particularly in complex traffic situations, due to inadequate consideration of environmental parameters and communication parameters, leading to suboptimal traffic flow and efficiency.

Innovation Solution

An on-board unit equipped with a machine-learning communication model that determines optimal communication parameters based on traffic situation data, including vehicle dynamics and environment conditions, to enhance maneuver coordination by optimizing coordination messages and radio channel usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If maneuver coordination is implemented between vehicles, then traffic flow efficiency and driving comfort are improved, but radio channel usage increases and communication resources are consumed

Engineering Contradiction:
Improvetraffic flow efficiencyVSAvoidradio usage
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

The system dynamically adjusts communication parameters (transmission power, message frequency, payload size) based on traffic situation parameters detected by the environment determination unit. The machine-learning model determines optimal communication parameters that adapt to changing traffic conditions, reducing radio usage when full coordination is not necessary while maintaining traffic flow efficiency.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements partial coordination by selectively coordinating maneuvers only when beneficial, rather than continuously coordinating all vehicle interactions. The machine-learning model evaluates traffic situations and determines when coordination is necessary, avoiding unnecessary communication overhead while maintaining efficiency in critical scenarios.

Inventive Principle:
Principle #16Partial or excessive action

2Reliability

If communication parameters are optimized based on machine-learning models, then maneuver coordination effectiveness is improved, but system complexity and computational requirements increase

Engineering Contradiction:
Improvemaneuver coordination effectivenessVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The machine-learning communication model acts as an intermediary between the environment determination unit and the coordination unit. It processes traffic situation data and translates it into optimal communication parameters, simplifying the overall system architecture while improving coordination effectiveness. The model serves as a bridge that handles the complexity of parameter optimization internally.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The machine-learning model is pre-trained with extensive traffic situation data and coordination outcomes before deployment. This preliminary training allows the model to quickly determine optimal communication parameters during runtime without requiring complex real-time computations, reducing system complexity while maintaining high coordination effectiveness.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If coordination messages are transmitted frequently, then maneuver coordination reliability is improved, but radio channel congestion and energy consumption increase

Engineering Contradiction:
Improvemaneuver coordination reliabilityVSAvoidradio channel efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system dynamically adjusts the frequency and timing of coordination message transmissions based on real-time traffic situation data. The machine-learning model determines optimal communication parameters including transmission frequency, adapting to changing traffic conditions. This dynamic approach maintains coordination reliability while avoiding radio channel congestion by reducing transmissions when conditions are stable.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3896942A1On-board unit, method for cooperative driving, model determination unit, method for determining a machine-learning communication model, system, method, vehicle, and user equipment
Publication Date: 2021.10.20 ROBERT BOSCH GMBH
  • EP3896942A1 patent drawingFigure 1
  • EP3896942A1 patent drawingFigure 2
  • EP3896942A1 patent drawingFigure 3

AI summary

An on-board unit (OBU1; OBU2) for cooperative driving of a road user is provided. The on-board unit (OBU1; OBU2) comprises: an environment determination unit (102; 112) being configured to determine traffic situation data (tsD) representing a traffic situation in which the road user participates; a communication scheme determination unit (104; 114) being configured to determine at least one communication parameter (cP) in dependence on the determined traffic situation data (tsD) using a machine-learning communication model (110; 120); and a coordination unit (106; 116) being configured to communicate in dependence on the at least one communication parameter (cP) with at least one further on-board unit (OBU2; OBU1) of another road user via at least one coordination message (cM) which is transmitted via a radio channel (RCH).