Vehicle Position Estimation Using Point Group Maps for Automated Parking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated parking systems face challenges in accurately estimating the self-position of a vehicle when the amount of acquired map data is insufficient.
Innovation Solution
An information processing apparatus is developed that includes a point group data acquisition unit, movement amount estimation unit, and position estimation unit, which generates local surrounding information and calculates a coordinate transform formula to accurately estimate the vehicle's position using point group data and movement information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the amount of acquired map data is limited, then the system can operate with fewer resources and in more environments, but the position estimation accuracy deteriorates
Solution Approach 1:
The system performs preliminary actions by acquiring and storing map data of the parking area before the actual parking operation. The map data acquisition unit collects point group data representing the parking area layout in advance, creating a reference map that can be used for position estimation during automated parking. This preliminary data collection enables the system to operate with limited real-time sensor data while maintaining accuracy.
Solution Approach 2:
The patent introduces map data as an intermediary element between the vehicle's sensors and the position estimation algorithm. The map data serves as a reference framework that mediates the matching process between observed point groups from sensors and expected point groups from the map. This intermediary enables accurate position estimation even when direct sensor observations are limited or noisy.
2Measurement precision
If more map data is acquired to improve position estimation accuracy, then the measurement precision improves, but the loss of time and computational resources increases
Solution Approach 1:
The system extracts only the essential and relevant features from the map data for position estimation. Instead of processing complete high-resolution maps, the patent extracts point group data representing key geometric features of the parking area (parking space boundaries, walls, obstacles). This extraction reduces data volume and processing time while maintaining the accuracy needed for parking operations.
Solution Approach 2:
The system performs partial action by using only the portion of map data that is relevant for the current position estimation task. The map data acquisition unit selectively acquires point group data for specific features (parking space corners, boundary lines) rather than complete environmental mapping. This partial data approach reduces processing requirements while providing sufficient information for accurate parking guidance.
3Measurement precision
If complex position estimation algorithms are used to improve accuracy, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The system uses copying by creating a simplified digital representation (point group map) of the physical parking area. Instead of implementing complex algorithms to interpret raw sensor data directly, the patent copies the essential geometric structure of the environment into a point group format that can be efficiently matched against sensor observations. This copying approach simplifies the estimation algorithm while maintaining accuracy.
Solution Approach 2:
The patent replaces complex mechanical/computational position estimation systems with a simpler pattern matching approach. Instead of using sophisticated algorithms to infer position from limited sensor data, the system substitutes a direct matching process between observed point groups and map point groups. This substitution reduces computational complexity while achieving accurate position estimation through geometric correspondence.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An information processing apparatus includes: a point group data acquisition unit configured to acquire, based on information from a sensor configured to detect an object existing in surroundings of a vehicle, point group data related to a plurality of points representing the object; a movement amount estimation unit configured to estimate a movement amount of the vehicle; a storage unit configured to store, as a point group map recorded in association with position information including a latitude and a longitude, relative positions of the plurality of points relative to a first reference position that is a place on a travel path of the vehicle; and a position estimation unit configured to estimate a position of the vehicle based on the point group map, the point group data, and the movement amount.