Autonomous Vehicle Pickup Using Semantic Landmark Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in precisely identifying pickup locations due to changing environmental conditions and the absence of a human driver, leading to uncertainty and confusion for passengers regarding where to meet the vehicle.
Innovation Solution
The system uses semantic information, such as photos or videos from client devices, to identify specific pickup locations based on semantic markers like permanent landmarks, and adjusts the location if initial progress is slower than expected, ensuring safe and accessible meeting points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicles use generic pickup locations without semantic information, then the system operation is simple, but the pickup precision and passenger identification efficiency deteriorate
Solution Approach 1:
The patent introduces semantic information (photos, videos, landmarks) as an intermediary between the autonomous vehicle and the passenger. This intermediary enables precise location identification without requiring complex direct communication protocols, thereby improving pickup precision while maintaining manageable system complexity
Solution Approach 2:
The system performs preliminary actions by collecting and processing semantic information about the pickup location before the vehicle arrives. This includes capturing photos, identifying landmarks, and determining the specified location in advance, which enables more accurate pickup without adding complexity during the actual pickup process
2Reliability
If autonomous vehicles wait for passengers at the exact requested pickup location, then the pickup accuracy is high, but the system adaptability to changing environmental conditions deteriorates
Solution Approach 1:
The patent implements dynamics by allowing the specified pickup location to be adjusted based on real-time environmental conditions. The system determines an initial specified location based on semantic information, then dynamically updates it if progress is slower than expected or environmental changes occur, maintaining both reliability and adaptability
Solution Approach 2:
The system uses feedback mechanisms to monitor progress toward the pickup location and environmental conditions. When progress is slower than expected or conditions change, the system receives feedback and updates the specified location accordingly, ensuring reliable pickup while adapting to changing circumstances
3Measurement precision
If autonomous vehicles collect detailed semantic information from client devices, then the location identification accuracy improves, but the information processing time and energy consumption increase
Solution Approach 1:
The patent applies partial action by collecting only the necessary semantic information needed for location identification rather than comprehensive data. The system requests photos or videos from client devices and processes only the essential features (landmarks, location markers), achieving sufficient accuracy without excessive processing time or energy consumption
Data Source
AI summary
A control system for an autonomous vehicle is configured to pick up a passenger at a pickup location. The autonomous vehicle includes a self-driving system and one or more computing devices in communication with the self-driving system. The one or more computing devices are configured to receive a trip request including a pickup location and a destination location, the trip request being associated with a client device; cause the self-driving system to navigate the autonomous vehicle to the pickup location; send a prompt to the client device to collect semantic information; determine a specified location based on the semantic information received in response to the prompt; identify one or more semantic markers for the specified location from the semantic information; and send a message to the client device identifying the specified location using the one or more semantic markers.