US 12,084,080 B2
Systems and methods for learning and managing robot user interfaces
Guy Rosman, Newton, MA (US); Daniel J. Brooks, Arlington, MA (US); Simon A. I. Stent, Cambridge, MA (US); Tiffany Chen, San Jose, CA (US); Emily Sarah Sumner, Mountain View, CA (US); Shabnam Hakimi, San Francisco, CA (US); Jonathan DeCastro, Arlington, MA (US); and Deepak Edakkattil Gopinath, Chicago, IL (US)
Assigned to Toyota Research Institute, Inc., Los Altos, CA (US); and Toyota Jidosha Kabushiki Kaisha, Toyota (JP)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US)
Filed on Aug. 26, 2022, as Appl. No. 17/896,187.
Claims priority of provisional application 63/358,997, filed on Jul. 7, 2022.
Prior Publication US 2024/0010218 A1, Jan. 11, 2024
Int. Cl. B60W 50/14 (2020.01); B25J 9/16 (2006.01); B25J 11/00 (2006.01); B60W 40/09 (2012.01); B60W 50/00 (2006.01); B60W 60/00 (2020.01); G06N 3/04 (2023.01)
CPC B60W 50/14 (2013.01) [B25J 9/161 (2013.01); B25J 9/163 (2013.01); B25J 11/008 (2013.01); B60W 40/09 (2013.01); B60W 50/0097 (2013.01); B60W 60/0015 (2020.02); G06N 3/04 (2013.01); B60W 2050/0083 (2013.01); B60W 2050/143 (2013.01); B60W 2050/146 (2013.01); B60W 2556/10 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system for learning and managing robot user interfaces, the system comprising:
a processor; and
a memory storing machine-readable instructions that, when executed by the processor, cause the processor to:
generate, based on input data that includes information about past interactions of a particular user with a robot and with one or more existing Human-Machine Interfaces (HMIs) of the robot, a latent space using one or more encoder neural networks, wherein the latent space is a reduced-dimensionality representation of learned behavior and characteristics of the particular user; and
use the latent space as input to train a first decoder neural network associated with one of (1) a new HMI of the robot distinct from the one or more existing HMIs of the robot and (2) a particular HMI among the one or more existing HMIs of the robot to alter operation of the particular HMI;
wherein the trained first decoder neural network is deployed in the robot to control, at least in part, operation of one of the new HMI and the particular HMI in accordance with the learned behavior and characteristics of the particular user.