Autonomous Vehicle Pickup Mapping Using Passenger Inconvenience Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining convenient and safe pickup and drop-off locations, leading to inconvenience for passengers, especially those with disabilities or minors, due to difficulties in coordinating with human drivers and inefficient location selection.
Innovation Solution
A method to assess the inconvenience of pickup and drop-off locations by analyzing passenger movement data using vehicle perception systems, calculating inconvenience distances, and generating map data to optimize future stopping locations for autonomous vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If autonomous vehicles use automated dispatch instructions to pickup locations, then operational efficiency is improved, but passenger convenience deteriorates due to increased walking distance
Solution Approach 1:
The system performs preliminary assessment of pickup locations by analyzing historical passenger movement data, observed distances, and road edge distances before actual pickups occur. This allows the autonomous vehicle to pre-select optimal stopping locations that balance operational efficiency with passenger convenience, rather than making decisions after arrival.
Solution Approach 2:
The system implements feedback loops where passenger pickup/dropoff data is continuously collected and used to update inconvenience values for locations. This feedback mechanism allows the system to learn from past experiences and progressively improve location selection, resolving the contradiction between efficiency and convenience over time.
2Ease of operation
If autonomous vehicles stop at optimized locations based on map data, then passenger experience is improved, but system complexity increases due to data processing requirements
Solution Approach 1:
The system performs self-assessment by automatically collecting its own pickup/dropoff data, calculating observed distances, determining road edge distances, and computing inconvenience values without external intervention. This self-service capability reduces the need for complex external processing systems while improving passenger experience.
Solution Approach 2:
The system creates simplified representations of complex spatial relationships by generating map data with inconvenience values that copy essential information about location quality. This allows complex passenger experience considerations to be encoded in simple, usable format for vehicle decision-making.
3Measurement precision
If the system collects and analyzes detailed passenger movement data, then location assessment accuracy is improved, but data processing time increases
Solution Approach 1:
The system collects comprehensive passenger movement data including all observed positions and movements, but processes only the essential elements needed for location assessment (observed distance and road edge distance). This partial processing approach maintains high assessment accuracy while avoiding unnecessary processing overhead.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Aspects of the disclosure relate to generating map data. For instance, data generated by a perception system 372 of a vehicle 101 may be received. This data corresponds to a plurality of observations including observed positions of a passenger of the vehicle as the passenger approached the vehicle at a first location. The data may be used to determine an observed distance traveled by a passenger to reach a vehicle. A road edge distance between an observed position of an observation of the plurality of observations and a nearest road edge to the observed position may be determined. An inconvenience value for the first location may be determined using the observed distance and the road edge distance. The map data is then generated using the inconvenience value.