Autonomous Vehicle Pickup Point Selection With Ranked Heuristics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional taxi services lack precision in communicating pickup and drop-off locations to users, often relying on physical signals, phone calls, or in-person discussions.
Innovation Solution
A method and system that utilize pre-stored map information and a set of ranked heuristics to identify a recommended pickup or drop-off point for autonomous vehicles, ensuring that the selected location satisfies the highest-ranked heuristic and is one of the pre-determined stopping locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional taxi services use physical signals, phone calls, or in-person discussions to communicate pickup locations, then the communication method is simple and requires minimal technology, but the precision and clarity of location information provided to users is insufficient
Solution Approach 1:
The system pre-stores map information and pre-determines multiple candidate stopping locations before the user requests a ride. When a user provides a pickup location, the system has already processed and ranked potential stopping points using heuristics, enabling rapid presentation of precise location options without real-time computational complexity.
Solution Approach 2:
The patent introduces an intermediary processing layer between the user's simple location input and the vehicle's stopping decision. This layer includes pre-stored map data, heuristic rules, and ranking algorithms that translate vague user inputs into precise, actionable stopping locations, thereby improving location precision without requiring complex real-time processing.
2Loss of information
If the vehicle stops at any location near the user's requested pickup point, then the vehicle can be flexible in its stopping options, but the user may not receive clear and accurate information about where to meet the vehicle
Solution Approach 1:
The system presents multiple candidate stopping locations to the user with clear visual or textual information about each option's characteristics (e.g., distance from requested location, accessibility features). The user can review these options and select their preferred stopping point, providing feedback that guides the final vehicle destination. This ensures both information clarity and location flexibility.
Solution Approach 2:
The system dynamically adjusts the presentation of stopping locations based on user preferences, historical data, and real-time conditions. The heuristic ranking can be reweighted or modified based on user feedback, allowing the system to adapt between providing highly structured recommendations versus offering broader flexibility, thereby reducing information loss while maintaining adaptability.
3Reliability
If the system uses multiple heuristics with rankings to determine the recommended stopping location, then the location selection becomes more accurate and useful, but the computational process becomes more complex
Solution Approach 1:
The system pre-computes and stores multiple heuristics and their weighting rules in advance. Instead of evaluating complex algorithms in real-time when a user requests a ride, the system has already prepared the decision-making framework, allowing it to quickly apply pre-ranked heuristics to candidate locations and generate reliable recommendations with minimal computational overhead.
Solution Approach 2:
The patent divides the location selection process into separate, modular heuristic components (e.g., distance from requested location, proximity to landmarks, accessibility considerations, safety factors). Each heuristic is an independent evaluation criterion that can be applied sequentially to candidate locations. This segmentation makes the overall complex process manageable and allows the system to reliably assess multiple factors without overwhelming computational complexity.
Data Source
AI summary
Aspects of the disclosure relate to arranging a pick up and drop off locations between a driverless vehicle and a passenger. As an example, a method of doing so may include receiving a request for a vehicle from a client computing device, wherein the request identifies a first location. Pre-stored map information and the first location are used to identify a recommended point according to a set of heuristics. Each heuristic of the set of heuristics has a ranking such that the recommended point corresponds to a location that satisfies at least one of the heuristics having a first rank and such that no other location satisfies any other heuristic of the set of heuristics having a higher rank than the first rank. The pre-stored map information identifying a plurality of pre-determined locations for the vehicle to stop, and the recommended point is one of the plurality of pre-determined locations. The recommended point is then provided the client computing device for display on a display of the client computing device with a map.