Access Point Inference for Autonomous Vehicle Pickup Locations
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 increased walking distances for users.
Innovation Solution
The system utilizes detailed electronic map information, combining roadgraph data with curated features from different map sources to infer the most appropriate access point for pickup or drop-off, considering factors like walking time and distance, to enable precise location selection for autonomous vehicle operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If detailed electronic map information and curated features are integrated, then location selection accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments map information into two distinct layers: roadgraph data (roadways, intersections, drivable areas) and curated features (buildings, access points, destinations). This segmentation allows each layer to be processed and optimized independently, improving location selection accuracy without creating an unmanageably complex monolithic system.
Solution Approach 2:
The system introduces an intermediary access point inference mechanism that bridges roadgraph locations and curated building features. This intermediary layer processes the relationship between roadway infrastructure and building access points, enabling accurate location selection while abstracting the complexity of multi-source data integration.
2Ease of operation
If access point inference is performed, then user walking distance is reduced, but computational requirements increase
Solution Approach 1:
The system performs preliminary action by pre-processing and curating building features and access points before they are needed for location selection. Access points are inferred and stored in advance, so when a pickup or drop-off location needs to be selected, the system can quickly match roadgraph locations with pre-computed access points, reducing both user walking distance and real-time computational requirements.
Solution Approach 2:
The system applies local quality by making access point inference location-specific and context-dependent. Rather than computing all possible access points uniformly, the system infers access points based on the specific roadgraph location and surrounding context, optimizing computational resources while minimizing user walking distance for each specific pickup or drop-off scenario.
Data Source
Figure 1A
Figure 1B
Figure 1C
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.