Vehicle Navigation Environment Modeling for Reliable Decision Timing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for modeling a navigation environment of autonomous vehicles face challenges in managing the consistency and reliability of information from various perception means, leading to incomplete and inaccurate data for decision-making.
Innovation Solution
A method and device for modeling a navigation environment that involves defining an overall environmental model, selecting relevant information based on decision deadlines, and determining integrity indices to ensure data reliability and consistency, using multiple perception means and temporal checks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data from multiple environment perception means are collected to improve decision-making accuracy, then the quantity and completeness of information increases, but the complexity of managing consistency and reliability of information increases
Solution Approach 1:
The patent segments the overall environmental model into multiple selective environmental models, each tailored to specific decision types (short-term, medium-term, long-term decisions). This segmentation allows the system to manage information complexity by organizing data according to decision timelines and requirements, making it easier to handle consistency and reliability for each decision category separately.
Solution Approach 2:
The patent introduces an intermediary layer (the selective environmental model generation unit) that sits between the raw perception data and the decision-making module. This intermediary processes, filters, and organizes information from multiple perception means, managing consistency and reliability before presenting data to the decision-making module, thus reducing the complexity burden on the decision-making process.
2Loss of information
If all available environmental data is processed to ensure complete information, then the completeness of the environmental model improves, but the processing time and computational resources increase
Solution Approach 1:
The patent extracts only the necessary information from the overall environmental model based on the specific decision requirements. Instead of processing all available data, the system identifies and extracts relevant information for each decision type (short-term, medium-term, long-term), thereby maintaining information completeness for decision-making while significantly reducing processing time and computational resources.
Solution Approach 2:
The patent applies partial action by generating different selective environmental models with varying levels of detail according to decision deadlines. For urgent short-term decisions, a simplified model with essential information is generated quickly, while for long-term decisions, a more comprehensive model can be processed. This ensures complete information is available when needed without always incurring the full processing cost.
3Productivity
If selective information is extracted from the environmental model for specific decisions, then the processing efficiency improves, but the risk of missing relevant information increases
Solution Approach 1:
The patent implements a dynamic approach where the selective environmental models are adaptively generated based on the specific decision requirements and deadlines. The system dynamically determines which information to extract and how much detail to include, adjusting the level of selectivity according to the decision context. This dynamic adaptation ensures that relevant information is not missed while maintaining high processing efficiency for each decision type.
Data Source
AI summary
A method models a navigation environment of a vehicle equipped with environment perception structure, with a decision module, and with an autonomous controller for autonomously controlling the vehicle. The method includes defining a global environment model of the vehicle as being a structured set of information constructed from data supplied by the environment perception structure, and receiving, from the decision module, a request for information relating to a decision to be taken to control the vehicle by way of the autonomous controller.