Curated Access Point Inference for Autonomous Vehicle Pickups
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in identifying suitable pickup and drop-off locations due to the lack of detailed information about buildings and access points in existing digital maps, leading to inefficient location selection and difficulty in reaching intended destinations.
Innovation Solution
Utilizing detailed electronic map information, such as roadgraph data, in conjunction with other features to infer access points for pickup and drop-off locations by filtering and selecting appropriate features based on distance and criteria such as walking time or wait time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If digital maps are used for autonomous driving, then roadway and static object details are available, but details about buildings and access points are missing
Solution Approach 1:
The patent combines roadgraph data from digital maps with curated location data from multiple sources (GPS, parcel information, building footprints) to create a comprehensive location identification system. This merging of data sources resolves the information gap about buildings and access points while maintaining systematic processing through the roadgraph framework.
Solution Approach 2:
The system performs preliminary filtering of roadgraph features based on curated location data before selecting pickup or drop-off points. By pre-processing and organizing location information from multiple sources into structured datasets, the system prepares comprehensive location information in advance, reducing the need for complex real-time processing.
2Ease of operation
If general roadgraph features are selected for pickup locations, then location selection is simple, but the selected location may not be convenient for users to reach their destinations
Solution Approach 1:
The patent applies local quality by filtering roadgraph features based on their specific characteristics and proximity to curated location data. Instead of uniformly selecting any roadgraph feature, the system identifies features with specific properties (near buildings, access points, or destinations) to ensure each selected location is locally optimized for user convenience while maintaining overall system simplicity.
3Measurement precision
If multiple map data sources are integrated, then location information accuracy is improved, but data processing complexity increases
Solution Approach 1:
The patent uses the roadgraph data structure as an intermediary framework to integrate multiple map data sources. Rather than directly combining disparate data formats from GPS, parcel information, and building footprints, the system mediates through the roadgraph structure, which organizes and standardizes the integration process, improving location accuracy while managing data processing complexity.
Data Source
AI summary
Aspects of the technology provide a method including receiving a request for a user to be picked up or dropped off by an autonomous vehicle, in which the request identifying a location, and determining a land parcel containing the identified location. The method also includes identifying a set of features that are within a selected distance from the identified location, filtering the set of identified features to obtain only curated features that are within the selected distance from the identified location, determining a distance between each curated feature and the identified location, and inferring an access point for the identified location based on the distances determined between each curated feature and the identified location. The inferred access point can then be provided to enable the autonomous vehicle to perform a pickup or drop-off.