Feature Availability Prediction for Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomously controllable vehicles face challenges in reliable localization due to the inability to detect sufficient features by environmental sensors, especially in high-traffic conditions, which hinders effective route planning and vehicle control.
Innovation Solution
A method for predicting the availability of feature-based localization by receiving map data, ascertaining features on roadways, calculating availability values based on detectability criteria including sensor type, directional characteristic, and traffic volume, and outputting availability information to inform route selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If environmental sensors are used to detect features for vehicle localization, then localization capability is improved, but in high-traffic conditions the detectability of features deteriorates due to occlusion by other vehicles
Solution Approach 1:
The system performs preliminary calculation of availability values for multiple potential routes before the vehicle actually travels. By pre-assessing which routes have sufficient detectable features based on map data and current traffic conditions, the system can select optimal routes in advance, avoiding situations where features become undetectable during travel.
Solution Approach 2:
The patent introduces an intermediary computational system that processes map data, sensor characteristics, and traffic information to generate availability values. This intermediary layer translates raw data about road features and sensor capabilities into predictive metrics that guide route selection, mediating between the vehicle's localization needs and environmental conditions.
2Productivity
If the vehicle selects routes based on shortest travel time, then productivity is improved, but localization reliability deteriorates when features are not detectable
Solution Approach 1:
The system changes the routing parameter from purely time-based optimization to a composite parameter that includes feature availability. By calculating availability values that incorporate sensor detectability, traffic conditions, and feature density, the system selects routes that optimize both travel time and localization reliability, rather than minimizing time alone.
Solution Approach 2:
The route selection process is made dynamic by continuously updating availability calculations based on current traffic conditions and re-evaluating potential routes. The system can adapt route choices in real-time as traffic patterns change, ensuring that the selected route maintains sufficient feature detectability throughout the journey.
3Measurement precision
If more features are required for accurate localization, then measurement precision is improved, but the availability of detectable features worsens in high-traffic environments
Solution Approach 1:
The system applies local quality assessment by evaluating feature detectability specifically for each roadway segment and lane rather than treating the entire route uniformly. By calculating availability values for specific local areas and selecting routes or lanes with higher local feature availability, the system ensures sufficient detectable features are present where the vehicle actually travels.
Data Source
AI summary
A method for predicting the availability of feature-based localization of a vehicle. The method includes: receiving map data from a feature map of a road traffic network; ascertaining, on the basis of the feature information from the feature map, features for at least one roadway to be used by the vehicle; calculating an availability value for the features of the at least one roadway to be used by the vehicle with respect to an availability criterion; and outputting availability information that includes the availability value and relates to the features of the roadway to be used.