Autonomous Vehicle Localization Using Static Object Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face localization inaccuracies due to sensor signal loss, which can lead to incorrect routing and potential collisions, especially on highways, as they rely on high definition maps for navigation.
Innovation Solution
The use of known static objects marked on high definition maps to determine real-time localization errors, with the vehicle calculating distances to these objects and activating alarms or fail-safe procedures if errors exceed predefined ranges, allowing for manual override or switching to vision-based localization if necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the vehicle uses sensor-based localization techniques, then routing efficiency is improved, but localization accuracy deteriorates due to sensor signal loss
Solution Approach 1:
The patent introduces static objects (such as road signs, buildings, or other fixed infrastructure) as intermediary reference points between the vehicle and the HD map. These static objects serve as mediators that provide stable, verifiable location references independent of sensor signals. The vehicle detects these static objects using sensors, identifies their known locations from the HD map, and uses them to verify and correct localization accuracy, thereby resolving the contradiction between routing efficiency and localization precision.
2Productivity
If the vehicle relies on HD map localization, then route planning efficiency is improved, but safety deteriorates due to potential incorrect routing
Solution Approach 1:
The patent implements a feedback mechanism where the vehicle continuously detects static objects in the environment, compares their observed positions with expected positions from the HD map, and uses this comparison feedback to verify localization accuracy. When discrepancies exceed a threshold, the system triggers safety protocols such as alarms or fail-safe procedures. This feedback loop ensures that the efficiency benefits of HD map-based routing do not compromise safety, as the system can detect and respond to localization errors in real-time.
3Ease of operation
If the vehicle operates in autonomous mode without manual oversight, then ease of operation is improved, but reliability deteriorates due to inability to handle localization errors
Solution Approach 1:
The patent implements a dynamic system that automatically adjusts the level of autonomous operation based on localization quality. When localization accuracy is verified to be within acceptable thresholds using static object references, the vehicle operates in full autonomous mode for ease of operation. When discrepancies are detected, the system dynamically transitions to alert the driver or activate fail-safe procedures, thereby maintaining reliability. This dynamic adjustment allows the system to optimize between autonomous convenience and safety based on real-time conditions.
Data Source
AI summary
In one embodiment, a method for monitoring a localization function in an autonomous driving vehicle (ADV) can use known static objects as ground truths to determine when the localization function encounter errors. The known static objects are marked on a high definition (HD) map for the real-time driving environment. When the ADV detects one or more known static objects, the ADV can use sensor data, locations of the one or more static objects, and one or more error tolerance parameters to create a localization error tolerance area surrounding a current location of the ADV. The ADV can project the tolerance area on the HD map, performs a localization operation to generate an expected location of the ADV on the HD map, and determines whether the generated location falls within the projected tolerance area. If the generated location falls outside the projected tolerance area, indicating a localization function of the ADV encounter errors, the ADV can generate an alarm to alert a human driver to switch to a manual driving mode. If no human driver is available in the ADV, the ADV can activate a vision-based fail-safe localization procedure.