Remote Camera Pose Correction for Indoor Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in achieving accurate localization in GNSS denial environments, such as indoor parking structures, where global navigation satellite systems cannot provide positioning data, hindering automated valet parking operations.
Innovation Solution
The system utilizes remote cameras to provide pose corrections, allowing the vehicle to determine an updated pose without expensive onboard sensors, using a processor and computer-readable storage medium to process sensor data and communication systems for accurate localization in GNSS denial environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS receivers are used to achieve sub-meter localization accuracy, then positioning precision is improved, but the system cannot operate in GNSS denial environments such as indoor parking structures
Solution Approach 1:
The patent introduces remote cameras as intermediary devices that capture images of the vehicle from external vantage points. These cameras act as mediators between the vehicle's localization system and the environment, providing positioning data without requiring onboard sensors or GNSS signals. The camera images are processed to extract vehicle pose information, enabling localization in GNSS-denied environments while maintaining sub-meter accuracy.
Solution Approach 2:
The patent replaces traditional mechanical and electronic localization systems (GNSS receivers, onboard sensors) with a vision-based system using remote cameras. Instead of relying on satellite signals or complex onboard sensor fusion, the system substitutes these with optical capture and image processing, eliminating the need for expensive sensor suites while achieving comparable localization accuracy.
2Measurement precision
If expensive onboard sensors are deployed to achieve accurate localization in GNSS denial environments, then measurement precision is improved, but system cost increases
Solution Approach 1:
The patent uses remote cameras to create visual copies or representations of the vehicle from external perspectives. Instead of equipping each vehicle with expensive onboard sensors, the system captures images of the vehicle and processes these visual copies to determine pose information. This approach allows multiple vehicles to share the same remote camera infrastructure, significantly reducing per-vehicle costs while maintaining localization accuracy.
Solution Approach 2:
The patent replaces expensive, complex onboard sensor systems with a simpler, more economical remote camera approach. The system uses standard cameras positioned at remote locations rather than costly LiDAR, radar, or inertial measurement units on each vehicle. This substitution dramatically reduces hardware costs while achieving the required localization precision for automated valet parking operations.
3Device complexity
If remote cameras are used to provide pose corrections, then device complexity is reduced, but the system requires external infrastructure
Solution Approach 1:
The patent merges the localization function with existing remote camera infrastructure. Instead of requiring each vehicle to have independent, complex sensor systems, the solution combines multiple vehicles' localization needs with shared remote camera resources. The remote cameras serve multiple purposes: capturing images for localization, monitoring parking areas, and providing data for multiple vehicles simultaneously, thereby reducing overall system complexity.
Data Source
AI summary
This document describes techniques and systems for vehicle localization based on pose corrections from remote cameras in parking garages and other GNSS denial environments. A system can include a processor and computer-readable storage media comprising instructions that, when executed by the processor, cause the system to determine an estimated pose of the host vehicle within a GNSS denial environment after the host vehicle has been parked at a drop-off area. The system can also receive a corrected pose of the host vehicle from one or more remote cameras in the GNSS denial environment. The instructions further cause the processor to use the corrected pose to determine an updated pose for the host vehicle. In this way, the system can provide highly accurate vehicle localization in GNSS denial environments in a cost-effective manner to support automated valet parking and other autonomous driving functionalities.