Landmark-Based AV Routing From Spoken Destination Cues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional navigation systems are unable to utilize dynamic environmental features and spoken location descriptions to inform navigation and route planning for autonomous vehicles, limiting their ability to determine precise map locations and provide efficient ride-sharing services.
Innovation Solution
The system extracts navigation cues from speech data and identifies salient environmental characteristics (landmarks) to determine map locations, enabling autonomous vehicles to navigate and route based on verbal descriptions without requiring precise address or geolocation information, using a landmark extraction module and a landmark identification module that reference map databases and environmental data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional navigation systems use only precise address or geolocation information, then routing accuracy is maintained, but the system cannot utilize dynamic environmental features and spoken location descriptions
Solution Approach 1:
The system introduces landmarks as intermediary entities that bridge the gap between imprecise speech descriptions and precise map locations. Speech instructions are converted into landmark references, which then serve as mediators to identify specific geographic locations through comparison with map database information, enabling both verbal input flexibility and location precision.
Solution Approach 2:
The system replaces the traditional mechanical approach of direct coordinate matching with a semantic processing system that uses natural language processing and environmental feature recognition. Speech data is processed through linguistic analysis to extract landmark references, which are then matched against environmental sensor data and map databases to determine locations, substituting direct geometric matching with semantic interpretation.
2Measurement precision
If the system processes large quantities of sensor data for navigation, then routing accuracy improves, but computational complexity and processing time increase
Solution Approach 1:
The system extracts only the essential navigation-relevant features from large quantities of sensor data by focusing on landmark identification. Environmental sensors capture comprehensive data, but the processing system selectively extracts features that match known landmarks in the map database, filtering out irrelevant information and reducing computational burden while maintaining routing accuracy.
Solution Approach 2:
The system performs preliminary processing by pre-building and storing landmark information in map databases before navigation operations. During actual routing, the system compares real-time sensor data against these pre-processed landmark profiles, avoiding the need to analyze all raw sensor data from scratch and reducing real-time computational complexity while preserving routing precision.
Data Source
AI summary
The subject disclosure relates to ways to resolve autonomous vehicle (AV) routes based on verbal descriptions of landmark features. In some aspects, a process of the disclosed technology includes steps for receiving speech instructions, wherein the speech instructions indicate an autonomous vehicle (AV) destination, analyzing the speech instructions to identify one or more landmarks associated with the AV destination, and determining location information corresponding with the one or more landmarks. In some aspects, the process further includes calculating a route based on the location information corresponding with the one or more landmarks. Systems and machine-readable media are also provided.