Cost and Convergence Maps for Automated Driving Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for creating maps for automated driving vehicles face ambiguities due to the use of repetitive features, which can lead to inaccuracies in localization and mapping.
Innovation Solution
A method involving the generation of cost and convergence maps from sensor data using alignment algorithms, where minima in these maps are used to extract features that can differentiate between unique and repetitive environmental elements, optimizing localization and mapping processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If repetitive features (e.g., traffic-lane markings, reflector posts) are used for localization and mapping, then the quantity of extractable features increases, but ambiguities in mapping and localization arise
Solution Approach 1:
The patent segments features into two distinct categories: periodic features (repetitive elements like traffic-lane markings and reflector posts) and non-periodic features (unique elements). This segmentation allows the system to process each type differently, using periodic features for coarse localization and non-periodic features for precise positioning, thereby resolving the ambiguity problem while maintaining high feature quantity
Solution Approach 2:
The patent changes the parameter of feature identification by introducing temporal and spatial analysis parameters. By analyzing the temporal occurrence and spatial distribution of features, the system can distinguish between periodic and non-periodic features, transforming the raw feature data into categorized information that eliminates localization ambiguities
2Manufacturing precision
If alignment algorithms process sensor measurement data to create digital maps, then mapping capability is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent applies preliminary action by pre-categorizing features as periodic or non-periodic before the main alignment process. This pre-processing step organizes the sensor data in advance, allowing the alignment algorithm to focus computational resources on critical non-periodic features while handling periodic features through simplified models, thereby reducing overall computational complexity while maintaining mapping precision
Solution Approach 2:
The patent extracts and separates periodic features from the general feature set, handling them through specialized periodic feature processing. This extraction removes the computationally intensive aspect of processing all features uniformly, allowing the alignment algorithm to operate more efficiently on the remaining non-periodic features while still achieving high mapping precision
Data Source
AI summary
A method for ascertaining features in an environment of at least one mobile unit for implementation of a localization and/or mapping by a control unit. In the course of the method, sensor measurement data of the environment are received, the sensor measurement data received are transformed by an alignment algorithm into a cost function and a cost map is generated with the aid of the cost function, a convergence map is generated based on the alignment algorithm. At least one feature is extracted from the cost map and/or the convergence map and stored, the at least one feature being provided in order to optimize a localization and/or mapping. A control unit, a computer program, and a machine-readable storage medium are also described.