Adaptive Thresholding for Intensity Map Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current navigation systems for autonomous vehicles face challenges in accurately determining vehicle location due to the complexity of distinguishing relevant geographic features from irrelevant ones using intensity values from sensors.
Innovation Solution
An autonomous navigation system employing intensity-based localization, which includes sensors on a vehicle and a computing device that processes intensity values by removing values below an adaptive threshold to generate a clear intensity map, allowing for accurate comparison with a virtual map to determine the vehicle's position.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If all intensity values from sensors are used for localization, then more data is available for comparison, but irrelevant features increase noise and reduce localization accuracy
Solution Approach 1:
The patent extracts only the relevant intensity values from the sensor data by applying a threshold filter. This removes irrelevant features (noise) while retaining the meaningful data needed for accurate localization, directly resolving the contradiction between having more data and achieving higher precision
Solution Approach 2:
The patent applies different treatment to different intensity values based on their relevance. By thresholding, it distinguishes between relevant features (above threshold) and irrelevant features (below threshold), giving different quality weights to different data points, thus improving localization accuracy without losing all data
2Ease of operation
If a fixed threshold is used to filter intensity values, then processing is simple and fast, but it cannot adapt to varying environmental conditions and reduces measurement accuracy
Solution Approach 1:
The patent transforms the static fixed threshold into a dynamic adaptive threshold that automatically adjusts based on the actual sensor data distribution. This is achieved by calculating the threshold from statistical properties (mean and standard deviation) of the intensity values, allowing the system to adapt to varying environmental conditions while maintaining processing efficiency
Solution Approach 2:
The patent changes the threshold parameter dynamically based on environmental conditions. Instead of using a constant value, the threshold is recalculated for each localization event based on the current sensor data characteristics, enabling the system to maintain high accuracy across different lighting and environmental conditions
Data Source
AI summary
A system, device, and methods for autonomous navigation using intensity-based localization. One example computer-implemented method includes receiving data including a plurality of intensity values from one or more sensors disposed on a vehicle as the vehicle traverses a route and generating a first group of intensity values wherein the first group includes at least some of the plurality of intensity values received. The method further includes removing the intensity values below an adaptive threshold from the first group of intensity values to generate a second group of intensity values, comparing the second group of intensity values to an intensity map, and generating a localized vehicle position based on the comparison between the second group of intensity values and the intensity map.