US 12,434,645 B2
Computing systems and methods for generating user-specific automated vehicle actions using artificial intelligence
Hassan Benqassmi, Fremont, CA (US); Maja Buhr, Santa Cruz, CA (US); Chris Busenbark, Creedmoor, NC (US); Anusha Joshi, Santa Clara, CA (US); Jason Kamin, Half Moon Bay, CA (US); Mahmoud Khalil, San Jose, CA (US); Isabel Litton, Santa Clara, CA (US); and Samina Reddy, Fremont, CA (US)
Assigned to Mercedes-Benz Group AG, Stuttgart (DE)
Filed by Mercedes-Benz Group AG, Stuttgart (DE)
Filed on Dec. 14, 2022, as Appl. No. 18/081,318.
Prior Publication US 2024/0198937 A1, Jun. 20, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. B60R 16/037 (2006.01); B60W 10/00 (2006.01)
CPC B60R 16/037 (2013.01) [B60W 10/00 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computing system comprising:
a control circuit configured to:
receive context data associated with a plurality of user interactions with a vehicle function, of a plurality of different vehicle functions, of a vehicle over a plurality of instances in time, wherein the context data comprises data indicative of a plurality of user-selected settings for the vehicle function and data indicative of one or more observed conditions associated with the respective user-selected settings;
generate, using a machine-learned clustering model selected from a plurality of machine-learned clustering models, a user-activity cluster for the vehicle function based on the context data, the machine-learned clustering model being configured to identify the user-activity cluster based on at least a portion of the user-selected settings and at least a portion of the one or more observed conditions associated with the respective user-selected settings
wherein each respective machine-learned clustering model of the plurality of machine-learned clustering models is associated with a different vehicle function of the plurality of different vehicle functions and wherein the machine-learned clustering model is selected based on the vehicle function;
determine an automated vehicle action based on the user-activity cluster, wherein the automated vehicle action is indicative of an automated setting for the vehicle function and one or more triggering conditions for automatically implementing the automated setting; and
output command instructions for the vehicle to implement the automated vehicle action for automatically controlling the vehicle function in accordance with the automated setting based on whether the vehicle detects the one or more triggering conditions.