Digital Road Map Confidence Updating Under Object Concealment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital road maps lack the ability to dynamically update and maintain accurate confidence values for recognized objects, leading to potential errors and inaccuracies in highly or fully automatic driving systems due to concealment and inconsistent recognition by individual object recognition devices.
Innovation Solution
A system comprising an object recognition device with a capture, evaluation, and transceiver unit, and a backend that generates or updates digital road maps by assigning confidence values based on the presence or absence of objects in captured data, adjusting these values based on recognition and concealment, and integrating data from multiple vehicles to ensure map accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If digital road maps are updated using data from individual object recognition devices, then the map can be continuously updated, but errors and inaccuracies occur due to concealment and inconsistent recognition
Solution Approach 1:
The patent combines data from multiple object recognition devices (vehicles) to determine object presence. The backend receives recognition results from multiple vehicles and uses majority voting or consensus algorithms to determine whether an object is present, thereby compensating for individual device limitations due to concealment or detection errors.
Solution Approach 2:
The system implements a feedback mechanism where the backend continuously receives recognition data from vehicles, updates confidence values for objects in the digital road map, and uses this updated information to improve future recognition accuracy. The confidence values are adjusted based on multiple observations over time.
2Reliability
If confidence values are adjusted based on object presence in captured data, then map accuracy improves, but the system complexity increases due to continuous updating mechanisms
Solution Approach 1:
The digital road map system performs self-updating through automated confidence value adjustment. The backend automatically receives data from vehicles, processes recognition results, and updates object confidence values without requiring manual intervention. The system serves itself by using its own operational data to improve its accuracy.
Solution Approach 2:
The system dynamically changes the confidence value parameter for each object based on recognition data. When an object is consistently detected by multiple vehicles, its confidence value increases; when detection is inconsistent or absent, the confidence value decreases. This parameter adaptation allows the system to maintain accuracy without complex structural changes.
3Reliability
If data from multiple vehicles are integrated to improve recognition reliability, then object detection accuracy increases, but the data processing time and computational load increase
Solution Approach 1:
The system segments the data processing task by having each vehicle independently perform initial object recognition and data filtering before transmitting results to the backend. This preprocessing segmentation reduces the amount of raw data that needs to be processed centrally, thereby reducing overall processing time while maintaining the benefits of multi-vehicle data integration.
Data Source
AI summary
A system for generating confidence values for objects in a digital road map comprising a backend and an object recognition device including: a capture unit, an evaluation unit, a positioning unit, and a transceiver. The capture unit captures surroundings data of a vehicle. The positioning unit determines a position of the captured surroundings data and objects contained therein. The evaluation unit recognizes the objects and concealed objects based on the surroundings data and associates them with position information. The transceiver transmits information generated by the evaluation unit to the backend. The backend generates or updates the map. Each of the objects in the map has an associated confidence value. The backend adjusts the confidence values based on the received data. The backend does not reduce the confidence value of an object if there is a corresponding concealed object in the received data.