Map Update Probability Distribution for Autonomous Vehicle Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High-precision maps used by autonomous vehicle-driving systems may become inconsistent due to incomplete feature detection by sensors, leading to discontinuities in lane line representation.
Innovation Solution
A processor-based apparatus that detects reference points corresponding to road features from surrounding data, updates probability distributions to enhance the positional accuracy of these features, and generates maps with improved reliability distributions for delivery to vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If map information is updated based on sensor-detected features only, then the map can be updated with real-world data, but the positional accuracy of features deteriorates due to incomplete detection
Solution Approach 1:
The system uses probability distributions as a feedback mechanism to continuously refine feature positions. Each detection updates the probability distribution, which in turn guides future detections and corrections, creating a self-improving system that resolves incomplete detections over time
Solution Approach 2:
The system changes the parameter representation from deterministic point positions to probability distributions. This allows the system to express uncertainty and gradually converge to accurate positions through multiple updates, transforming the nature of how feature positions are stored and refined
2Loss of information
If sensors are used to detect all features around the vehicle, then complete feature detection may be achieved, but detection reliability worsens due to sensor limitations
Solution Approach 1:
The system merges multiple detection results into a unified probability distribution. By combining information from multiple sensors and multiple detection instances, the system achieves both completeness and reliability that neither individual sensor nor single detection could provide alone
Data Source
AI summary
An apparatus for updating a map detects the positions of reference points corresponding to a feature on a road being traveled by a vehicle from surrounding data representing features around the vehicle, and updates probability distributions associated with the respective reference points so that the probabilities of existence of the reference points at the detected positions of the reference points increase. Each of the probability distributions indicates the probability of existence of the corresponding reference point as a function of position.