Position Estimating Device for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of feature position detection in vehicle-captured images obtained by a vehicle-mounted camera is insufficient due to the lack of consistent feature information from sensors and external devices, making it challenging to generate precise correction information for map updates in autonomous driving systems.
Innovation Solution
A position estimating device that uses a processor to detect the vehicle's position from fixed sensors and satellite positioning data to estimate the real-space position of features in vehicle-captured images, correcting vehicle positions based on differences between sensor data and image timestamps, and integrating this information to enhance feature detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If feature position detection relies on vehicle-captured images from vehicle-mounted cameras, then the system can operate without external sensor information, but the detection accuracy becomes insufficient due to vehicle position errors
Solution Approach 1:
The patent introduces a server as an intermediary that collects and processes sensor information from multiple vehicles. This server acts as a mediator between individual vehicles and the map information database, enabling vehicles to access corrected feature position data without directly implementing complex sensor fusion algorithms themselves.
Solution Approach 2:
The system implements a feedback mechanism where sensor information from vehicles is sent to the server, which then generates correction information based on this feedback. The correction information is transmitted back to vehicles to improve their feature position detection accuracy, creating a continuous improvement loop.
2Measurement precision
If the system uses sensor information from multiple vehicles to improve detection accuracy, then feature position precision improves, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent divides the system into distinct functional segments: vehicles equipped with sensors, a central server for data processing, and a map information database. This segmentation allows each component to perform its specific function independently, reducing overall system complexity while maintaining high detection accuracy through coordinated operation.
Solution Approach 2:
Vehicles autonomously collect and transmit their own sensor information to the server without requiring direct control or coordination from other vehicles. Each vehicle independently generates and sends its data, simplifying the interaction model while still contributing to the collective improvement of detection accuracy.
3Measurement precision
If correction information is generated by identifying the same feature in multiple vehicles' sensor data, then detection accuracy improves, but the requirement for consistent feature information from multiple sources increases system constraints
Solution Approach 1:
The server implements a universal processing mechanism that can handle sensor information from any vehicle regardless of the specific features detected. The system is designed to process diverse data sources and automatically identify corresponding features, making the correction mechanism adaptable to various vehicle types, sensor configurations, and environmental conditions.
Data Source
AI summary
A position estimating device includes a processor configured to detect a first position of a vehicle traveling a predetermined road section at a first time, based on a fixed sensor installed on or near the predetermined road section, estimate a second position of the vehicle at a second time, based on the first position of the vehicle at the first time, the second time being a time when a vehicle-captured image representing a predetermined feature is generated by a vehicle-mounted camera mounted on the vehicle, and estimate a real-space position of the predetermined feature, based on the estimated second position.