US 12,221,021 B2
Adaptive personal thermal control in a vehicle
Alaa M. Khamis, Courtice (CA); Lei Li, Whitby (CA); Paul H. K. Hui, Oshawa (CA); Todd M. Tumas, Taylor, MI (US); and Jarvis Chau, Markham (CA)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Feb. 3, 2022, as Appl. No. 17/592,005.
Prior Publication US 2023/0242019 A1, Aug. 3, 2023
Int. Cl. B60N 2/56 (2006.01); B60W 40/08 (2012.01)
CPC B60N 2/56 (2013.01) [B60W 40/08 (2013.01); B60W 2040/0872 (2013.01); B60W 2540/21 (2020.02); B60W 2540/221 (2020.02)] 16 Claims
OG exemplary drawing
 
1. A system in a vehicle, the system comprising:
a personal thermal device, the personal thermal device providing heating or cooling to an individual occupant of the vehicle; and
a controller implementing reinforcement learning to control the personal thermal device, the controller being configured to obtain states, from one or more sensors, indicating current conditions, to obtain a score that is determined according to the states and that represents a reward used in the reinforcement learning, and to provide a stochastic policy indicating a probability of taking a particular action to control the personal thermal device based on the score acting as a feedback for feedback control of the personal thermal device using the reinforcement learning, wherein the states include human influence factors (HIF) determined according to manual adjustments of the personal thermal device by the occupant and according to sentiment analysis of verbal and non-verbal feedback provided by the occupant, system influence factors (SIF) that are parameters affecting a temperature experienced by the occupant, and context influence factors (CIF) that are not specific to the occupant, wherein the sentiment analysis includes mapping verbal expressions to defined affect states and wherein the defined affect states include positive, neutral and negative.