Autonomous Vehicle Environment Modeling for Reliable Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for modeling a navigation environment for autonomous vehicles face challenges in managing the consistency and reliability of sensor data, leading to incomplete and inaccurate decision-making.
Innovation Solution
A method and device for modeling a navigation environment that involves constructing a global environmental model, selecting relevant information based on integrity indices, and providing a selective environmental model tailored to specific decision deadlines, ensuring data consistency and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a global environmental model is constructed from all sensor data, then completeness of environmental information is improved, but data consistency and reliability deteriorate due to errors and inaccuracies in sensor data
Solution Approach 1:
The patent segments the environmental model into multiple layers (e.g., static environment, dynamic objects, road users) and processes data at different levels of detail. This allows comprehensive environmental coverage while filtering out inconsistent data at each layer, resolving the contradiction between completeness and reliability.
Solution Approach 2:
The patent applies different quality standards and processing methods to different regions of the environmental model based on their importance. Critical areas (e.g., immediate surroundings, road users) receive higher scrutiny and validation, while less critical areas use simpler processing. This ensures reliability for decision-critical information while maintaining overall completeness.
2Measurement precision
If all sensor data is processed for decision-making, then accuracy of situation description is improved, but processing time and computational complexity worsen
Solution Approach 1:
The patent performs preliminary processing of sensor data including calibration, synchronization, and basic filtering before the decision-making process. This preliminary action prepares the data in advance, reducing the computational burden during real-time decision-making while maintaining accuracy.
Solution Approach 2:
The patent processes only the necessary portion of sensor data required for the current decision context. Rather than processing all data uniformly, it selectively processes data based on relevance to the current situation and decision requirements, reducing processing time while maintaining sufficient accuracy.
3Reliability
If multiple perception means are used to improve data reliability, then consistency between data sources worsens due to potential conflicts between different sensors
Solution Approach 1:
The patent introduces an intermediary layer that mediates between multiple sensor data sources. This intermediary performs data fusion, conflict resolution, and consistency validation, reconciling differences between sensors while maintaining the reliability benefits of multi-sensor input.
Solution Approach 2:
The patent implements feedback mechanisms that continuously monitor data consistency across multiple sensors and adjust processing accordingly. When inconsistencies are detected, the system uses feedback to weight or filter conflicting data sources, maintaining reliability while ensuring consistency.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
A method for modelling a navigation environment of a vehicle (100) equipped with environment perception means (1), with a decision module (2) and with an autonomous control means (20) for autonomously controlling the vehicle, characterized in that it comprises the following steps: - a step (E1) of defining a global environment model (M_ENV_G) of the vehicle as being a structured set of information constructed from data supplied by the environment perception means (1), - a step (E2) of receiving, from the decision module (2), a request (RDP) for information relating to a decision to be taken (DP) to control the vehicle by way of the autonomous control means (20).