Radar Occupancy Grid for Vehicle Localization in GNSS Denial Environments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Global Navigation Satellite Systems (GNSS) cannot provide positioning data in GNSS denial environments such as indoor parking structures or garages, limiting the accuracy of autonomous vehicle operations to sub-meter levels.
Innovation Solution
The system generates a radar reference map using radar detections to create a radar occupancy grid, allowing for accurate vehicle localization within GNSS denial environments through inexpensive radar sensors, processing radar reflections to identify stationary objects and determine the vehicle's pose.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS receivers are used for vehicle localization, then sub-meter accuracy is achieved, but positioning data cannot be received in GNSS denial environments such as indoor parking structures
Solution Approach 1:
The patent introduces radar sensors as an intermediary system to bridge the localization gap in GNSS denial environments. The radar occupancy grid serves as a mediator between the vehicle's sensors and the environment, enabling localization when GNSS is unavailable by detecting stationary objects and generating a representational model of the surroundings
Solution Approach 2:
The system changes the operational parameters from relying on satellite signals to using radar wave reflections. By transforming the localization approach from optical/electromagnetic satellite communication to radar-based electromagnetic reflection detection, the system maintains functionality across different environmental conditions including GNSS denial areas
2Ease of manufacture
If radar sensors are used for vehicle localization, then cost-effective solution is provided, but achieving high accuracy localization requires sophisticated processing
Solution Approach 1:
The system performs preliminary actions by pre-generating the radar occupancy grid and identifying stationary objects before vehicle localization is needed. This preprocessing creates a reference framework that simplifies real-time localization operations, reducing the computational burden during actual vehicle positioning
Solution Approach 2:
The patent creates a copied representation of the environment through the radar occupancy grid, which is a simplified model that captures essential spatial relationships. This copied model serves as a reference for localization without requiring direct complex processing of raw radar data during vehicle positioning operations
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This method provides highly accurate vehicle localization in GNSS denial environments at a cost-effective manner, enabling reliable autonomous vehicle operations within these areas.
Implementation Method 1
receive radar detections from one or more radar sensors and obtain a vehicle pose within the radar occupancy grid to localize the vehicle within the GNSS denial environment
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This document describes techniques and systems for vehicle localization based on radar detections in garages and other GNSS denial environments. In some examples, a system includes a processor and computer-readable storage media comprising instructions that, when executed, cause the system to obtain structure data regarding a GNSS denial environment and generate, from the structure data, radar localization landmarks. The radar localization landmarks include edges or corners of the GNSS denial environment. The instructions also cause the processor to generate polylines along or between the radar localization landmarks to generate a radar occupancy grid. The instructions further cause the processor to receive radar detections from one or more radar sensors and obtain a vehicle pose within the radar occupancy grid to localize the vehicle within the GNSS denial environment. In this way, the system can provide highly accurate vehicle localization in GNSS denial environments in a cost-effective manner.