Systems and methods for deep reinforcement learning using a brain-artificial intelligence interface

P Sajda, S Saproo, V Shih, SB Roy… - US Patent …, 2023 - Google Patents
The present disclosure relates to systems and methods for providing a hybrid brain-
computer-interface (hBCI) that can detect an individual's reinforcement signals (eg, level of …

Sensory-based dynamic game-state configuration

CM Sumant, N Victor, T Agarwal, P Ganeshan… - US Patent …, 2020 - Google Patents
Abstract Systems presented herein may automatically and dynamically modify a video game
being played by a user based at least in part on a determined or predicted emotional state of …

Personalized behavior of computer controlled avatars in a virtual reality environment

R Herbrich, ME Tipping, M Hatton - US Patent 7,090,576, 2006 - Google Patents
Racing-based computer games typically include a mode in which one or more human
players can compete against one or more computer-controlled opponents. For example, a …

Ubiquitous natural user system for human-machine interaction

WD Kelsey, BD Laughlin, RN Blair - US Patent 9,645,652, 2017 - Google Patents
(57) ABSTRACT A system is provided that includes sensor (s) configured to provide sensed
input including measurements of motion of a user during performance of a task, and in which …

Methods and systems for reinforcement learning

MR Nazari, AO Jadid, M Kabul - US Patent 10,762,424, 2020 - Google Patents
Exemplary embodiments can maximize long-term value in a machine learning system. The
system may employ an offline training process and an online training process. In the offline …

Temporal information prediction in autonomous machine applications

Y Wu, P Janis, X Tong, CC Yang, M Park… - US Patent …, 2023 - Google Patents
In various examples, a sequential deep neural network (DNN) may be trained using ground
truth data generated by correlating (eg, by cross-sensor fusion) sensor data with image data …

Artificial reality multi-modal input switching model

E Pinchon, JL Spurlock, N Aschenbach… - US Patent …, 2022 - Google Patents
Embodiments described herein disclose methods and sys tems directed to input mode
selection in artificial reality. In some implementations, various input modes enable a user to …

Multi-state model for robot and user interaction

RI Sanchez, MM Chalabi, KB Krauskopf - US Patent 8,818,556, 2014 - Google Patents
The subject disclosure is directed towards a robot device including a model that controls a
robot's task-related operations to perform tasks and user-engagement operations to interact …

Artificial intelligence for emulating human playstyles

C Somers, J Rupert - US Patent 10,839,215, 2020 - Google Patents
An artificially intelligent entity can emulate human behavior in video games. An AI model can
be made by receiving gameplay logs of a video gameplay session, generating, based on the …

Autonomous system operator cognitive state detection and alerting

JS Higgins, A Singhal - US Patent 10,576,994, 2020 - Google Patents
Autonomous systems, such as vehicles being operated in a self-driving mode, may allow for
human occupants to be inattentive to the operation of the system. However, events may …