Compressed Sensor Map Matching for Reliable Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems for autonomous vehicles and robots face accuracy issues due to satellite interference and lack of permanent infrastructure, requiring robust and adaptive methods for position and orientation determination.
Innovation Solution
A method involving sensor data compression using techniques like variational autoencoders and aggregation to create a compressed data item, which is then searched within a map to determine position and orientation, allowing for robustness against uncertainties and situation-dependent changes without pre-identification of dominant features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If satellite-based navigation systems are used for position determination, then position accuracy can be achieved under favorable reception conditions, but accuracy deteriorates due to multiple propagation in developed areas and satellite visibility shading by houses or trees
Solution Approach 1:
The patent introduces an intermediary system consisting of permanently installed infrastructure objects (reflectors, markers) and a corresponding map database that mediates between the vehicle's sensors and the position determination goal. This intermediary infrastructure provides stable reference points that enable accurate position determination independent of satellite visibility conditions, resolving the contradiction between measurement precision and reliability.
2Reliability
If road markings and digital road maps are used for position determination, then position can be ascertained without satellite signals, but the method requires pre-identification of dominant features and predefined criteria
Solution Approach 1:
The patent extracts and stores the characteristics of permanently installed infrastructure objects (shapes, positions, orientations) in a map database during a preprocessing phase. This extraction removes the complexity of real-time feature identification from the vehicle's onboard system, as the vehicle only needs to compare sensor data against the pre-stored map data, thereby reducing device complexity while maintaining reliability.
Solution Approach 2:
The patent performs preliminary action by pre-identifying and storing the characteristics of dominant features (infrastructure objects) in the map database before actual position determination takes place. This preliminary mapping phase separates the complex feature identification task from the real-time positioning task, reducing onboard computational complexity while ensuring reliable position determination.
3Measurement precision
If comprehensive sensor data are recorded and processed for position determination, then accuracy can be improved, but data processing time and computational resources increase
Solution Approach 1:
The patent extracts only the essential characteristics of permanently installed infrastructure objects (position, orientation, shape parameters) and stores them in a compressed map database format. This selective extraction removes unnecessary data, reducing the amount of information that needs to be processed in real-time while preserving the accuracy needed for position determination.
Solution Approach 2:
The patent performs preliminary data processing by pre-computing and storing the characteristics of infrastructure objects in the map database. This preliminary action moves the computationally intensive feature extraction and characterization tasks to an offline phase, allowing real-time positioning to use pre-processed data and thereby reducing data processing time during actual operation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy and reliability of position determination, enabling continuous and accurate orientation assessment even in environments with limited satellite visibility, and increases operational reliability by combining different localization methods and actuating systems for precise movement.
Implementation Method 1
The measured data may include, for example, an intensity of electromagnetic radiation, which was received as the response of the surroundings to an electromagnetic scanning radiation. The electromagnetic scanning radiation may be, for example, a light beam or a radar beam, which is scanned through the surroundings. The measured data may then include, for example, a lidar or radar scan of the surroundings, which measures the intensity of the scanning radiation reflected in each case.
Data Source
AI summary
A method for position determination. The method includes: recording measured data from the surroundings of a vehicle, robot, or mobile device, using at least one sensor situated on the vehicle, robot, and/or mobile device; compressing the measured data to form a compressed data item; searching for the compressed data item in a map, the map associating compressed data items at least with a position or pose in two- or three-dimensional space; in response to the compressed data item being found in the map, using the position or pose associated with the compressed data item by the map to ascertain the position or pose of the vehicle, robot, or mobile device. A method for creating a map for the position determination is also described.