In-Vehicle Position Estimation Using Coordinate Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic driving systems face challenges in accurately estimating vehicle position in outdoor environments due to various disturbances, which are not addressed by current technologies.
Innovation Solution
An in-vehicle processing apparatus that utilizes point cloud data and sensor information to estimate vehicle position by creating local periphery information and establishing a relationship between coordinate systems, allowing for robust position estimation despite disturbances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional position detection means is used in outdoor environments, then the system can obtain position information, but the position estimation accuracy deteriorates due to various disturbances
Solution Approach 1:
The patent introduces an intermediary coordinate transformation system that maps positions from a GPS-based first coordinate system to a map-based second coordinate system. This intermediary transformation process filters out disturbances by using pre-stored map data as a reference framework, thereby improving position estimation accuracy in outdoor environments.
Solution Approach 2:
The patent creates a virtual copy of the geographic environment through pre-stored map data in the storage unit. This digital copy serves as a stable reference that is immune to environmental disturbances, allowing the system to compare and correct real-time position data against the stored map representation.
2Reliability
If multiple coordinate systems are transformed, then position estimation robustness improves, but the calculation complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-storing map data and establishing the relationship between the first and second coordinate systems before actual position estimation is needed. This advance preparation simplifies real-time processing, as the transformation framework is already in place and does not need to be constructed during operation.
Solution Approach 2:
The patent replaces complex real-time geometric transformations with a simplified lookup and comparison process against pre-stored map data. Instead of performing intricate coordinate calculations in real-time, the system substitutes this with a more efficient data retrieval and matching operation that achieves the same position estimation goal with reduced computational burden.
Data Source
AI summary
An in-vehicle processing apparatus is capable of performing position estimation resistant to disturbance. The in-vehicle processing apparatus includes: a storage unit that stores point cloud data including a plurality of coordinates of a point representing a portion of an object in a first coordinate system; a sensor input unit that acquires an output of a sensor that acquires information regarding vicinity of a vehicle; a movement information acquisition unit that acquires information related to movement of the vehicle; a local periphery information creation unit that generates local periphery information including a position of the vehicle in a second coordinate system and a plurality of coordinates of a point representing a portion of an object in the second coordinate system on the basis of information acquired by the sensor input unit and the movement information acquisition unit; and a position estimation unit that estimates a relationship between the first coordinate system and the second coordinate system on the basis of the point cloud data and the local periphery information and then estimates the position of the vehicle in the first coordinate system.