Michael Barry Smart

US Patent:

20220348220, Nov 3, 2022

Filed:

Jul 5, 2022

Appl. No.:

17/858024

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

B60W 60/00
G01C 21/34
G01C 21/36
G06N 20/00
G06K 9/62
H04W 4/021

Abstract:

A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S; and/or any other suitable processes.

US Patent:

20220332346, Oct 20, 2022

Filed:

Jun 28, 2022

Appl. No.:

17/851321

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

B60W 60/00
G01C 21/34
G01C 21/36
G06N 20/00
G06K 9/62
H04W 4/021

Abstract:

A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S; and/or any other suitable processes.

US Patent:

20220315042, Oct 6, 2022

Filed:

Jun 22, 2022

Appl. No.:

17/846870

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

B60W 60/00
G01C 21/36
H04W 4/021
G01C 21/34
G06N 20/00
G06K 9/62

Abstract:

A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S; and/or any other suitable processes.

US Patent:

20220234610, Jul 28, 2022

Filed:

Feb 25, 2022

Appl. No.:

17/681543

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

B60W 60/00
G06N 20/00
G01C 21/34
G06K 9/62
H04W 4/021
G01C 21/36

Abstract:

A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S; and/or any other suitable processes.

US Patent:

20220236737, Jul 28, 2022

Filed:

Mar 3, 2022

Appl. No.:

17/685905

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

G05D 1/02
G05D 1/00
G06K 9/62
G06N 20/00

Abstract:

A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.

US Patent:

20220214693, Jul 7, 2022

Filed:

Mar 25, 2022

Appl. No.:

17/704301

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

G05D 1/02
G05D 1/00
G06K 9/62
G06N 20/00

Abstract:

A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.

US Patent:

20210380128, Dec 9, 2021

Filed:

May 3, 2021

Appl. No.:

17/306014

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

B60W 60/00
H04W 4/021
G01C 21/36
G01C 21/34
G06K 9/62
G06N 20/00

Abstract:

A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action 8260; and/or any other suitable processes.

US Patent:

20210380129, Dec 9, 2021

Filed:

May 27, 2021

Appl. No.:

17/332748

Inventors:

- Palo Alto CA, US
Apeksha Kumavat - Palo Alto CA, US
Arjun Narang - Palo Alto CA, US
Kinh Tieu - Palo Alto CA, US
Michael Smart - Palo Alto CA, US
Marko Ilievski - Palo Alto CA, US

International Classification:

B60W 60/00
G06N 20/00
G01C 21/36
G01C 21/34
G06K 9/62
H04W 4/021

Abstract:

A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S; and/or any other suitable processes.