Abstract
When a vehicle has multiple occupants engaged in a conversation, audio instructions from a digital map/ navigation application can be disruptive and/or unnecessary. This disclosure describes techniques, implemented with specific user permission to access and analyze data related to the presence of multiple users in a vehicle and the conversational context. With user permission, the ongoing conversation in the vehicle is analyzed locally using a large language model and the analysis is used to enhance the audio delivery of dynamic navigational guidance. A transcript of the conversation related to the ongoing drive is provided to an LLM along with a prompt to revise the original turn-by-turn instructions based on the transcript. The LLM can modify the instructions, e.g., to incorporate a user request for an alternative route/ route characteristic, to omit or change the time of delivery of individual instructions, etc. The quality, accuracy, and personalization of the revisions to the instructions can be enhanced by custom training a base LLM via LLM alignment. Implementation of the techniques can make audio-based navigational guidance less disruptive and more useful.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Hartmann, Florian and Sharifi, Matthew, "LLM-based Navigation Guidance Revisions Based on Conversational Context", Technical Disclosure Commons, (July 08, 2025)
https://www.tdcommons.org/dpubs_series/8326