Vehicle Position Correction Using Landmarks in GPS-Denied Parking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Global Positioning Systems (GPS) and similar global navigation satellite systems (GNSS) lose signal in indoor and underground environments, leading to inaccurate vehicle positioning and driver confusion.
Innovation Solution
Detecting landmarks using vehicle sensors to correct vehicle position estimates without relying on prestored digital maps, generating a topographical map based on detected landmarks in one section to update positions in subsequent sections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS/GNSS satellite signals are used for vehicle positioning, then positioning accuracy is improved, but the system fails in indoor and underground environments where satellite signals are obstructed
Solution Approach 1:
The patent introduces landmarks as intermediary objects that mediate between the vehicle's motion and position estimation. Instead of directly relying on satellite signals, the system detects landmarks (such as corners, speed bumps, or other environmental features) and uses their known or detectable positions as reference points to correct and update the vehicle's estimated position, thereby enabling positioning in environments where GPS signals are unavailable
Solution Approach 2:
The patent replaces the satellite-based radio navigation system with a landmark-based detection and recognition system. Using vehicle-mounted sensors (cameras, LIDAR, or other detection devices), the system detects landmarks and determines their positions relative to the vehicle, substituting the external satellite signal dependency with a local environmental feature-based positioning mechanism
2Adaptability or versatility
If dead reckoning is used to estimate vehicle position in GPS-denied environments, then environmental adaptability is improved, but positioning accuracy deteriorates due to error accumulation
Solution Approach 1:
The patent implements a feedback mechanism where detected landmarks serve as reference points to verify and correct the vehicle's estimated position. When a landmark is detected and its position is determined (either from a pre-stored map or through detection), the system compares this with the dead reckoning estimate and updates the position estimation accordingly, thereby eliminating accumulated errors and improving accuracy
Solution Approach 2:
The patent performs preliminary detection and mapping of landmarks in the environment before vehicle navigation. By pre-identifying landmark positions and creating a topographical representation, the system establishes a reference framework that can be used for subsequent position correction, reducing the need for real-time complex calculations and improving responsiveness
Data Source
AI summary
Systems and methods are provided for correcting vehicle position estimations are provided. In an example implementation, the systems and methods disclosed herein detect a first landmark and determining a first position of the detected first landmark in a first section of an environment using one or more sensors of a vehicle while the vehicle travels in the first section, estimate a position of the vehicle in a second section of the environment, and update the estimated position of the vehicle in the second section according to the first position of the detected first landmark in the first section of the environment. In an illustrative example, the environment can be an indoor environment, such as, but not limited to, a multi-floor parking structure where the first section a floor and the second section is another floor.