Approximate value iteration with complex returns by bounding

R Wright, L Yu, S Loscalzo - US Patent 10,839,302, 2020 - Google Patents
A control system and method for controlling a system, which employs a data set representing
a plurality of states and associated trajectories of an environment of the system; and which …

Hybrid vehicle

M Hotta - US Patent 10,214,196, 2019 - Google Patents
The electronic control unit sets a target value of a charging amount of the electrical storage
device and increases the charging amount to the target value during traveling on the …

Framework and methods of diverse exploration for fast and safe policy improvement

L Yu, A Cohen - US Patent 11,568,236, 2023 - Google Patents
2019-03-19 Assigned to RESEARCH FOUNDATION FOR THE STATE UNIVERSITY OF
NEW YORK reassignment RESEARCH FOUNDATION FOR THE STATE UNIVERSITY OF …

Parameter identification offloading using cloud computing resources

Y Li, JG Kristinsson, FU Syed - US Patent 9,533,597, 2017 - Google Patents
(57) ABSTRACT A vehicle may include battery cells of a battery and at least one controller
configured to control the vehicle based on a state observation associated with the battery …

Battery model with robustness to cloud-specific communication issues

J Meyer - US Patent 9,446,678, 2016 - Google Patents
(57) ABSTRACT A vehicle may include battery cells and a controller config ured to control
the vehicle, based on a state observation of the battery cells, using model parameters …

Object detection and localized extremity guidance

E Martinson, EA Sisbot, J Djugash, K Oguchi… - US Patent …, 2017 - Google Patents
6,198.395 B1 3/2001 Sussman 6,320,496 B1 11/2001 Sokoler et al. 6,486,784 B1 11/2002
Beckers 6,662,141 B2 12/2003 Kaub 6,744,370 B1 6/2004 Sleichter, III et al. 6,774,788 B1 …

Navigation system for estimating routes for users

DFR Weir - US Patent 9,091,561, 2015 - Google Patents
The disclosure includes a system and method for generating a probability model used to
estimate most likely routes for users. The system includes one or more processors …

Inverse reinforcement learning by density ratio estimation

E Uchibe, K Doya - US Patent 10,896,382, 2021 - Google Patents
(57) ABSTRACT A method of inverse reinforcement learning for estimating cost and value
functions of behaviors of a subject includes acquiring data representing changes in state …

Vehicle control through machine learning

R Arvidsson, N Akerblom - US Patent 10,393,880, 2019 - Google Patents
A method is disclosed for managing rules or policies in a vehicle having a controllable unit.
The method may include determining, at the start of a driving, an active route of the vehicle …

Direct inverse reinforcement learning with density ratio estimation

E Uchibe, K Doya - US Patent 10,896,383, 2021 - Google Patents
(57) ABSTRACT A method of inverse reinforcement learning for estimating reward and value
functions of behaviors of a subject includes: acquiring data representing changes in state …