Andres Morales

US Patent:

20210271901, Sep 2, 2021

Filed:

May 20, 2021

Appl. No.:

17/325562

Inventors:

- Foster City CA, US
Marin Kobilarov - Mountain View CA, US
Andres Guillermo Morales Morales - San Francisco CA, US
Kai Zhenyu Wang - San Francisco CA, US

International Classification:

G06K 9/00
G06K 9/62
G08G 1/04
G08G 1/01
G06T 11/60
G08G 1/052
G08G 1/056
G05B 13/02

Abstract:

Techniques for determining predictions on a top-down representation of an environment based on vehicle action(s) are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) can capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle or a pedestrian). A multi-channel image representing a top-down view of the object(s) and the environment can be generated based on the sensor data, map data, and/or action data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) can be encoded in the image. Action data can represent a target lane, trajectory, etc. of the first vehicle. Multiple images can be generated representing the environment over time and input into a prediction system configured to output prediction probabilities associated with possible locations of the object(s) in the future, which may be based on the actions of the autonomous vehicle.

US Patent:

20210004611, Jan 7, 2021

Filed:

Jul 5, 2019

Appl. No.:

16/504147

Inventors:

- Foster City CA, US
Marin Kobilarov - Mountain View CA, US
Andres Guillermo Morales Morales - San Francisco CA, US
Kai Zhenyu Wang - Foster City CA, US

International Classification:

G06K 9/00
G06K 9/62
G08G 1/04
G08G 1/01
G06T 11/60
G08G 1/052
G08G 1/056
G05B 13/02

Abstract:

Techniques for determining predictions on a top-down representation of an environment based on vehicle action(s) are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) can capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle or a pedestrian). A multi-channel image representing a top-down view of the object(s) and the environment can be generated based on the sensor data, map data, and/or action data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) can be encoded in the image. Action data can represent a target lane, trajectory, etc. of the first vehicle. Multiple images can be generated representing the environment over time and input into a prediction system configured to output prediction probabilities associated with possible locations of the object(s) in the future, which may be based on the actions of the autonomous vehicle.

US Patent:

20180060609, Mar 1, 2018

Filed:

Oct 23, 2017

Appl. No.:

15/790542

Inventors:

- Mountain View CA, US
Andrew Abramson - Sunnyvale CA, US
Neel Rao - San Francisco CA, US
Shawn Willden - Morgan UT, US
Andres Guillermo Morales - San Francisco CA, US
James Brooks Miller - Sunnyvale CA, US

International Classification:

G06F 21/72
G06F 21/62
H04L 9/32
G06F 21/53
H04L 9/08
G06F 21/74

Abstract:

A computing device executes one or more trusted execution environment (TEE) processes in a TEE of a processor. The one or more TEE processes cryptographically protect a secret and a policy. The policy specifies a plurality of conditions on usage of the secret. A particular non-TEE process generates a request whose fulfillment involves an action requiring use of the secret. Responsive to the request, one or more non-TEE processes determine whether a first subset of the plurality of conditions is satisfied. Responsive to the first subset of the plurality of conditions being satisfied, the one or more TEE processes determine that a second, different subset of the plurality of conditions is satisfied. Responsive to determining the second subset of the plurality of conditions is satisfied, the one or more TEE processes use the secret to perform the action.

US Patent:

20160350561, Dec 1, 2016

Filed:

Aug 21, 2015

Appl. No.:

14/832446

Inventors:

- Mountain View CA, US
Andrew Abramson - Sunnyvale CA, US
Neel Rao - San Francisco CA, US
Shawn Edward Willden - Morgan UT, US
Andres Guillermo Morales - San Francisco CA, US
James Brooks Miller - Sunnyvale CA, US

International Classification:

G06F 21/72
H04L 9/32
H04L 9/08
G06F 21/53

Abstract:

A computing device executes one or more trusted execution environment (TEE) processes in a TEE of a processor. The one or more TEE processes cryptographically protect a secret and a policy. The policy specifies a plurality of conditions on usage of the secret. A particular non-TEE process generates a request whose fulfillment involves an action requiring use of the secret. Responsive to the request, one or more non-TEE processes determine whether a first subset of the plurality of conditions is satisfied. Responsive to the first subset of the plurality of conditions being satisfied, the one or more TEE processes determine that a second, different subset of the plurality of conditions is satisfied. Responsive to determining the second subset of the plurality of conditions is satisfied, the one or more TEE processes use the secret to perform the action.