IP Library › Granted Patent US 12,743,663
Granted Patent B1
US 12,743,663 · App. 19/032,037 · Granted Sep 22, 2026

Artificially intelligent systems, devices, and methods for learning and/or using visual surrounding for autonomous object operation

Inventor: Jasmin Cosic (Melbourne, FL)
G06N20/00G06F3/00G06F18/22
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,743,663
App. No.
19/032,037
Granted
Sep 22, 2026
Kind
B1
Abstract

Aspects of the disclosure generally relate to computing devices and/or systems, and may be generally directed to devices, systems, methods, and/or applications for learning operation of an application or an object of an application in various visual surroundings, storing this knowledge in a knowledgebase (i.e. neural network, graph, sequences, etc.), and enabling autonomous operation of the application or the object of the application.

Claims (121)

1 . A system comprising:

one or more non-transitory machine readable media storing machine readable code that, when executed, causes at least:

accessing a knowledgebase that includes one or more inputs for inputting at least a portion of a digital picture, wherein the one or more inputs are correlated with one or more instruction sets for operating a first object of a first application;

receiving or generating a stream of digital pictures that includes a first digital picture that depicts at least a portion of a surrounding of: the first object of the first application, a second object of the first application, or a first object of a second application, wherein the stream further includes a second digital picture that depicts at least a portion of a surrounding of: the first object of the first application, the second object of the first application, or the first object of the second application;

determining the one or more instruction sets for operating the first object of the first application at least by: inputting at least a portion of the first digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application; and

autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the one or more instruction sets for operating the first object of the first application, wherein the autonomously performing is performed at least in response to the determining.

2 . The system of claim 1 , wherein the first digital picture depicts a first-person view from a perspective of: the first object of the first application, the second object of the first application, or the first object of the second application, wherein the second digital picture depicts a first-person view from a perspective of: the first object of the first application, the second object of the first application, or the first object of the second application.

3 . The system of claim 1 , wherein the first digital picture depicts a third-person view from a perspective of an observer of: the first object of the first application, the second object of the first application, or the first object of the second application, wherein the second digital picture depicts a third-person view from a perspective of an observer of: the first object of the first application, the second object of the first application, or the first object of the second application.

4 . The system of claim 1 , wherein the first digital picture depicts a top-down view from above: the first object of the first application, the second object of the first application, or the first object of the second application, wherein the second digital picture depicts a top-down view from above: the first object of the first application, the second object of the first application, or the first object of the second application.

5 . The system of claim 1 , wherein the first digital picture depicts at least a portion of: the first object of the first application, the second object of the first application, or the first object of the second application, wherein the second digital picture depicts at least a portion of: the first object of the first application, the second object of the first application, or the first object of the second application.

6 . The system of claim 1 , wherein the first object of the first application is a first avatar of the first application, wherein the second object of the first application is a second avatar of the first application, wherein the first object of the second application is a first avatar of the second application.

7 . The system of claim 1 , further comprising:

a server, wherein the server receives the one or more instruction sets for operating the first object of the first application from a first device, wherein a second device receives the one or more instruction sets for operating the first object of the first application from the server, wherein the autonomously performing is performed on the second device.

8 . The system of claim 1 , wherein the first digital picture depicts the at least the portion of the surrounding of the first object of the first application,

wherein the one or more instruction sets for operating the first object of the first application are applied to the first object of the first application,

wherein the first object of the first application autonomously performs the one or more operations defined by the one or more instruction sets for operating the first object of the first application.

9 . The system of claim 1 , wherein the first digital picture depicts the at least the portion of the surrounding of the second object of the first application,

wherein the one or more instruction sets for operating the first object of the first application are applied to the second object of the first application,

wherein the second object of the first application autonomously performs the one or more operations defined by the one or more instruction sets for operating the first object of the first application.

10 . The system of claim 1 , wherein the first digital picture depicts the at least the portion of the surrounding of the first object of the second application,

wherein the one or more instruction sets for operating the first object of the first application are applied to the first object of the second application,

wherein the first object of the second application autonomously performs the one or more operations defined by the one or more instruction sets for operating the first object of the first application.

11 . The system of claim 1 , wherein the first digital picture depicts the at least the portion of the surrounding of: the first object of the first application, the second object of the first application, or the first object of the second application at a first time, wherein the second digital picture depicts the at least the portion of the surrounding of: the first object of the first application, the second object of the first application, or the first object of the second application at a second time.

12 . The system of claim 1 , wherein at least a portion of the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes operating the first object of the first application by a non-human user.

13 . The system of claim 1 , wherein the one or more instruction sets for operating the first object of the first application include one or more information about one or more states of at least a portion of the first object of the first application.

14 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application.

15 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a third object of the first application.

16 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a first object of a third application.

17 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein at least a portion of the correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application is learned in a learning process,

wherein at least a portion of a correlation between the one or more inputs and the another one or more instruction sets for operating the first object of the first application is learned in the learning process.

18 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein at least a portion of the correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application is learned in a learning process,

wherein at least a portion of a correlation between the one or more inputs and the another one or more instruction sets for operating the first object of the first application is learned in another learning process.

19 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein a weight included in or associated with the correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application is learned in a learning process,

wherein a weight included in or associated with a correlation between the one or more inputs and the another one or more instruction sets for operating the first object of the first application is learned in the learning process.

20 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein a weight included in or associated with the correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application is learned in a learning process,

wherein a weight included in or associated with a correlation between the one or more inputs and the another one or more instruction sets for operating the first object of the first application is learned in another learning process.

21 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein at least a portion of the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes operating the first object of the first application by a user,

wherein at least a portion of the another one or more instruction sets for operating the first object of the first application is learned in another learning process that includes operating the first object of the first application by the user.

22 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein at least a portion of the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes operating the first object of the first application by a user,

wherein at least a portion of the another one or more instruction sets for operating the first object of the first application is learned in another learning process that includes operating the first object of the first application by another user.

23 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a third object of the first application,

wherein at least a portion of the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes operating the first object of the first application by a user,

wherein at least a portion of the one or more instruction sets for operating the third object of the first application is learned in another learning process that includes operating the third object of the first application by the user.

24 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a third object of the first application,

wherein at least a portion of the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes operating the first object of the first application by a user,

wherein at least a portion of the one or more instruction sets for operating the third object of the first application is learned in another learning process that includes operating the third object of the first application by another user.

25 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a first object of a third application,

wherein at least a portion of the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes operating the first object of the first application by a user,

wherein at least a portion of the one or more instruction sets for operating the first object of the third application is learned in another learning process that includes operating the first object of the third application by the user.

26 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a first object of a third application,

wherein at least a portion of the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes operating the first object of the first application by a user,

wherein at least a portion of the one or more instruction sets for operating the first object of the third application is learned in another learning process that includes operating the first object of the third application by another user.

27 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein the one or more instruction sets for operating the first object of the first application and their temporally corresponding digital picture that depicts at least a portion of a surrounding of the first object of the first application are learned in a learning process that includes operating the first object of the first application at least partially by a user,

wherein the another one or more instruction sets for operating the first object of the first application and their temporally corresponding digital picture that depicts at least a portion of a surrounding of the first object of the first application are learned in another learning process that includes operating the first object of the first application at least partially by the user.

28 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application,

wherein the one or more instruction sets for operating the first object of the first application and their temporally corresponding digital picture that depicts at least a portion of a surrounding of the first object of the first application are learned in a learning process that includes operating the first object of the first application at least partially by a user,

wherein the another one or more instruction sets for operating the first object of the first application and their temporally corresponding digital picture that depicts at least a portion of a surrounding of the first object of the first application are learned in another learning process that includes operating the first object of the first application at least partially by another user.

29 . The system of claim 1 , wherein the one or more inputs are further correlated with another one or more instruction sets for operating the first object of the first application, wherein the machine readable code, when executed, further causes at least:

further determining the another one or more instruction sets for operating the first object of the first application at least by: inputting the second digital picture into the one or more inputs, and using a correlation between the one or more inputs and the another one or more instruction sets for operating the first object of the first application; and

further autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the another one or more instruction sets for operating the first object of the first application, wherein the further autonomously performing is performed at least in response to the further determining.

30 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a third object of the first application, wherein the machine readable code, when executed, further causes at least:

further determining the one or more instruction sets for operating the third object of the first application at least by: inputting the second digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the third object of the first application; and

further autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the one or more instruction sets for operating the third object of the first application, wherein the further autonomously performing is performed at least in response to the further determining.

31 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a first object of a third application, wherein the machine readable code, when executed, further causes at least:

further determining the one or more instruction sets for operating the first object of the third application at least by: inputting the second digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first object of the third application; and

further autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the one or more instruction sets for operating the first object of the third application, wherein the further autonomously performing is performed at least in response to the further determining.

32 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a third object of the first application, wherein the machine readable code, when executed, further causes at least:

receiving or generating a third digital picture that depicts at least a portion of a surrounding of a fourth object of the first application;

further determining the one or more instruction sets for operating the third object of the first application at least by: inputting at least a portion of the third digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the third object of the first application; and

further autonomously performing, by the fourth object of the first application, one or more operations defined by the one or more instruction sets for operating the third object of the first application, wherein the further autonomously performing is performed at least in response to the further determining.

33 . The system of claim 1 , wherein the one or more inputs are further correlated with one or more instruction sets for operating a first object of a third application, wherein the machine readable code, when executed, further causes at least:

receiving or generating a third digital picture that depicts at least a portion of a surrounding of a third object of the first application;

further determining the one or more instruction sets for operating the first object of the third application at least by: inputting at least a portion of the third digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first object of the third application; and

further autonomously performing, by the third object of the first application, one or more operations defined by the one or more instruction sets for operating the first object of the third application, wherein the further autonomously performing is performed at least in response to the further determining.

34 . The system of claim 1 , wherein the machine readable code, when executed, further causes at least:

modifying the one or more instruction sets for operating the first object of the first application in the knowledgebase,

wherein the determining includes determining the modified one or more instruction sets for operating the first object of the first application at least by: the inputting the at least the portion of the first digital picture into the one or more inputs, and using a correlation between the one or more inputs and the modified one or more instruction sets for operating the first object of the first application,

wherein the autonomously performing includes autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the modified one or more instruction sets for operating the first object of the first application.

35 . The system of claim 1 , wherein the machine readable code, when executed, further causes at least:

modifying a copy of the determined one or more instruction sets for operating the first object of the first application,

wherein the autonomously performing includes autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the modified the copy of the one or more instruction sets for operating the first object of the first application.

36 . The system of claim 1 , wherein the machine readable code, when executed, further causes at least:

modifying the first digital picture,

wherein the inputting the first digital picture into the one or more inputs includes: inputting the modified first digital picture into the one or more inputs.

37 . The system of claim 1 , wherein the one or more inputs are correlated with the one or more instruction sets for operating the first object of the first application using at least one or more connections, wherein the using the correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application includes using at least one connection of the one or more connections between the one or more inputs and the one or more instruction sets for operating the first object of the first application.

38 . The system of claim 1 , wherein the knowledgebase is a neural network,

wherein the one or more inputs are one or more input neurons of the neural network,

wherein the neural network further comprises one or more output neurons that include or are associated with the one or more instruction sets for operating the first object of the first application,

wherein the one or more input neurons are correlated with the one or more output neurons using at least one or more connections,

wherein the using the correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application includes using at least one connection of the one or more connections between the one or more input neurons and the one or more output neurons.

39 . The system of claim 1 , wherein the knowledgebase further includes one or more outputs that include or are associated with the one or more instruction sets for operating the first object of the first application,

wherein an information included in or associated with the correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application is learned in a learning process that includes:

receiving or generating a third digital picture;

obtaining or receiving the one or more instruction sets for operating the first object of the first application that temporally correspond to the third digital picture;

inputting at least a portion of the received or the generated third digital picture into the one or more inputs; and

applying the obtained or the received one or more instruction sets for operating the first object of the first application to the one or more outputs.

40 . The system of claim 1 , wherein the first application is a first video game, wherein the second application is a second video game.

41 . The system of claim 1 , wherein the first application is a first simulation program, wherein the second application is a second simulation program.

42 . The system of claim 1 , wherein the one or more inputs for inputting the at least the portion of the digital pictures include: one input for inputting one portion of the digital picture, multiple inputs for inputting multiple portions of the digital picture, or one input for inputting the digital picture, wherein the at least the portion of the first digital picture includes: one portion of the first digital picture, multiple portions of the first digital picture, or an entire first digital picture, wherein the stream of digital pictures is a sequence of digital pictures that depict at least a portion of a surrounding of: the first object of the first application, the second object of the first application, or the first object of the second application over time, wherein the receiving the stream of digital pictures includes receiving the stream of digital pictures from a renderer, wherein the generating the stream of digital pictures includes generating the stream of digital pictures by a renderer, wherein the first application or the second application includes: a video game, a computer game, a simulation program, a program including text processing, a program including number processing, a program including picture processing, a program including object processing, or an application program, wherein at least a portion of the knowledgebase is stored in or on: at least one non-transitory machine readable medium of the one or more non-transitory machine readable media, or another one or more non-transitory machine readable media, wherein the machine readable code is executed by one or more processors that cause the accessing, the receiving or the generating, the determining, and the autonomously performing.

43 . A method comprising:

accessing a knowledgebase that includes one or more inputs for inputting at least a portion of a digital picture, wherein the one or more inputs are correlated with one or more instruction sets for operating a first object of a first application;

receiving or generating a stream of digital pictures that includes a first digital picture that depicts at least a portion of a surrounding of: the first object of the first application, a second object of the first application, or a first object of a second application, wherein the stream further includes a second digital picture that depicts at least a portion of a surrounding of: the first object of the first application, the second object of the first application, or the first object of the second application;

determining the one or more instruction sets for operating the first object of the first application at least by: inputting at least a portion of the first digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application; and

autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the one or more instruction sets for operating the first object of the first application, wherein the autonomously performing is performed at least in response to the determining.

44 . A system comprising:

means for storing machine readable code that, when executed, causes at least:

accessing a knowledgebase that includes one or more inputs for inputting at least a portion of a digital picture, wherein the one or more inputs are correlated with one or more instruction sets for operating a first object of a first application;

receiving or generating a stream of digital pictures that includes a first digital picture that depicts at least a portion of a surrounding of: the first object of the first application, a second object of the first application, or a first object of a second application, wherein the stream further includes a second digital picture that depicts at least a portion of a surrounding of: the first object of the first application, the second object of the first application, or the first object of the second application;

determining the one or more instruction sets for operating the first object of the first application at least by: inputting at least a portion of the first digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first object of the first application; and

autonomously performing, by the first object of the first application or by the second object of the first application or by the first object of the second application, one or more operations defined by the one or more instruction sets for operating the first object of the first application, wherein the autonomously performing is performed at least in response to the determining,

wherein the one or more inputs are further correlated with one or more instruction sets for operating a first object of a third application, wherein the machine readable code, when executed, further causes at least:

receiving or generating a third digital picture that depicts at least a portion of a surrounding of a third object of the first application;

further determining the one or more instruction sets for operating the first object of the third application at least by: inputting at least a portion of the third digital picture into the one or more inputs, and using a correlation between the one or more inputs and the one or more instruction sets for operating the first object of the third application; and

further autonomously performing, by the third object of the first application, one or more operations defined by the one or more instruction sets for operating the first object of the third application, wherein the further autonomously performing is performed at least in response to the further determining.

Continuity (4)
Continuation 17394024 · Aug 4, 2021
Continuation 16237743 · Jan 1, 2019
Continuation 15835434 · Dec 7, 2017
Continuation 15245046 · Aug 23, 2016
References Cited (400)
US 4370707A · Phillips et al. · 1983 [cited by applicant]
US 4730315A · Saito et al. · 1988 [cited by applicant]
US 4860203A · Corrigan et al. · 1989 [cited by applicant]
US 5219264A · McClure et al. · 1993 [cited by applicant]
US 5560011A · Uyama · 1996 [cited by applicant]
US 5592661A · Eisenberg et al. · 1997 [cited by applicant]
US 5602982A · Judd et al. · 1997 [cited by applicant]
US 5758333A · Bauer et al. · 1998 [cited by applicant]
US 5874834A · New · 1999 [cited by applicant]
US 5983232A · Zhang · 1999 [cited by applicant]
US 6026234A · Hanson et al. · 2000 [cited by applicant]
US 6088731A · Kiraly et al. · 2000 [cited by applicant]
US 6106299A · Ackermann et al. · 2000 [cited by applicant]
US 6126330A · Knight · 2000 [cited by applicant]
US 6314558B1 · Angel et al. · 2001 [cited by applicant]
US 6408262B1 · Leerberg et al. · 2002 [cited by applicant]
US 6643842B2 · Angel et al. · 2003 [cited by applicant]
US 6728689B1 · Drissi et al. · 2004 [cited by applicant]
US 6735632B1 · Kiraly et al. · 2004 [cited by applicant]
US 6754631B1 · Din · 2004 [cited by applicant]
US 6801912B2 · Moskowitz et al. · 2004 [cited by applicant]
US 6842877B2 · Robarts et al. · 2005 [cited by applicant]
US 6850942B2 · Cotner et al. · 2005 [cited by applicant]
US 6915105B2 · Masuda · 2005 [cited by applicant]
US 6973446B2 · Mamitsuka et al. · 2005 [cited by applicant]
US 6996758B1 · Herron et al. · 2006 [cited by applicant]
US 7017153B2 · Gouriou et al. · 2006 [cited by applicant]
US 7052277B2 · Kellman · 2006 [cited by applicant]
US 7082435B1 · Guzman et al. · 2006 [cited by applicant]
US 7090576B2 · Herbrich et al. · 2006 [cited by applicant]
US 7113946B2 · Cosic · 2006 [cited by applicant]
US 7117225B2 · Cosic · 2006 [cited by applicant]
US 7222127B1 · Bem et al. · 2007 [cited by applicant]
US 7240335B2 · Angel et al. · 2007 [cited by applicant]
US 7249349B2 · Hundt et al. · 2007 [cited by applicant]
US 7395255B2 · Li · 2008 [cited by applicant]
US 7399224B2 · Hirai · 2008 [cited by applicant]
US 7409401B2 · Hansen et al. · 2008 [cited by applicant]
US 7424705B2 · Lewis et al. · 2008 [cited by applicant]
US 7444338B1 · Fisher · 2008 [cited by applicant]
US 7478371B1 · Gove · 2009 [cited by applicant]
US 7484205B2 · Venkatapathy · 2009 [cited by applicant]
US 7533128B1 · Sanchez et al. · 2009 [cited by applicant]
US 7565340B2 · Herlocker et al. · 2009 [cited by applicant]
US 7675519B2 · Tobias · 2010 [cited by applicant]
US 7721218B2 · Awe et al. · 2010 [cited by applicant]
US 7765537B2 · Havin et al. · 2010 [cited by applicant]
US 7797259B2 · Jiang et al. · 2010 [cited by applicant]
US 7831564B1 · Wei et al. · 2010 [cited by applicant]
US 7840060B2 · Podilchuk · 2010 [cited by applicant]
US 7849114B2 · Boss et al. · 2010 [cited by applicant]
US 7925984B2 · Awe et al. · 2011 [cited by applicant]
US 7987144B1 · Drissi et al. · 2011 [cited by applicant]
US 8005828B2 · Buchner et al. · 2011 [cited by applicant]
US 8019699B2 · Baxter · 2011 [cited by applicant]
US 8078556B2 · Adi et al. · 2011 [cited by applicant]
US 8090669B2 · Shahani et al. · 2012 [cited by applicant]
US 8137112B2 · Woolf et al. · 2012 [cited by applicant]
US 8142268B2 · Thomas et al. · 2012 [cited by applicant]
US 8152640B2 · Shirakawa et al. · 2012 [cited by applicant]
US 8166463B2 · Gill et al. · 2012 [cited by applicant]
US 8195674B1 · Bem et al. · 2012 [cited by applicant]
US 8196119B2 · Gill et al. · 2012 [cited by applicant]
US 8244730B2 · Gupta · 2012 [cited by applicant]
US 8245163B1 · Yuan et al. · 2012 [cited by applicant]
US 8251704B2 · Woolf et al. · 2012 [cited by applicant]
US 8261199B2 · Cradick et al. · 2012 [cited by applicant]
US 8266608B2 · Hecht et al. · 2012 [cited by applicant]
US 8335805B2 · Cosic · 2012 [cited by applicant]
US 8356026B2 · Heimendinger · 2013 [cited by applicant]
US 8364612B2 · Van Gael et al. · 2013 [cited by applicant]
US 8386401B2 · Virkar et al. · 2013 [cited by applicant]
US 8397227B2 · Fan et al. · 2013 [cited by applicant]
US 8417740B2 · Cosic · 2013 [cited by applicant]
US 8453061B2 · Bromenshenkel et al. · 2013 [cited by applicant]
US 8464225B2 · Greifeneder · 2013 [cited by applicant]
US 8549359B2 · Zheng · 2013 [cited by applicant]
US 8572035B2 · Cosic · 2013 [cited by applicant]
US 8589414B2 · Waite et al. · 2013 [cited by applicant]
US 8595154B2 · Breckenridge et al. · 2013 [cited by applicant]
US 8639644B1 · Hickman et al. · 2014 [cited by applicant]
US 8655260B2 · Yueh et al. · 2014 [cited by applicant]
US 8655900B2 · Cosic · 2014 [cited by applicant]
US 8667472B1 · Molinari · 2014 [cited by applicant]
US 8682485B2 · Anhalt et al. · 2014 [cited by applicant]
US 8762428B2 · Kulack et al. · 2014 [cited by applicant]
US 8793205B1 · Fisher · 2014 [cited by applicant]
US 8949186B1 · Yueh et al. · 2015 [cited by applicant]
US 8965621B1 · Urmson et al. · 2015 [cited by applicant]
US 8996432B1 · Fu · 2015 [cited by applicant]
US 9008840B1 · Ponulak et al. · 2015 [cited by applicant]
US 9047324B2 · Cosic · 2015 [cited by applicant]
US 9047568B1 · Fisher · 2015 [cited by applicant]
US 9085080B2 · Mian · 2015 [cited by applicant]
US 9158813B2 · Ntoulas et al. · 2015 [cited by applicant]
US 9195934B1 · Hunt et al. · 2015 [cited by applicant]
US 9221396B1 · Zhu · 2015 [cited by applicant]
US 9235214B2 · Anderson · 2016 [cited by applicant]
US 9268454B2 · Hamilton, II et al. · 2016 [cited by applicant]
US 9282309B1 · Cosic · 2016 [cited by applicant]
US 9283674B2 · Hoffman et al. · 2016 [cited by applicant]
US 9298749B2 · Cosic · 2016 [cited by applicant]
US 9305216B1 · Mishra · 2016 [cited by applicant]
US 9325314B2 · Shin · 2016 [cited by applicant]
US 9335766B1 · Silver · 2016 [cited by applicant]
US 9346167B2 · O'Connor et al. · 2016 [cited by applicant]
US 9367806B1 · Cosic · 2016 [cited by applicant]
US 9372902B2 · Hosie et al. · 2016 [cited by applicant]
US 9409051B2 · Kaleal, III et al. · 2016 [cited by applicant]
US 9434072B2 · Buehler et al. · 2016 [cited by applicant]
US 9435653B2 · Zeng · 2016 [cited by applicant]
US 9443192B1 · Cosic · 2016 [cited by applicant]
US 9488984B1 · Williams et al. · 2016 [cited by applicant]
US 9604359B1 · Grotmol et al. · 2017 [cited by applicant]
US 9630317B2 · Izhikevich et al. · 2017 [cited by applicant]
US 9682481B2 · Lutz et al. · 2017 [cited by applicant]
US 9766626B1 · Zhu et al. · 2017 [cited by applicant]
US 9789605B2 · Meier et al. · 2017 [cited by applicant]
US 9864933B1 · Cosic · 2018 [cited by applicant]
US 9881420B2 · Miller · 2018 [cited by applicant]
US 9978425B2 · Kirk et al. · 2018 [cited by applicant]
US 10022867B2 · Saboo et al. · 2018 [cited by applicant]
US 10067915B1 · Mishraky et al. · 2018 [cited by applicant]
US 10112113B2 · Krishnamurthy · 2018 [cited by applicant]
US 10131052B1 · Gabardos · 2018 [cited by applicant]
US 10162740B1 · Setty et al. · 2018 [cited by applicant]
US 10181213B2 · Bullivant et al. · 2019 [cited by applicant]
US 10217261B2 · Li et al. · 2019 [cited by applicant]
US 10317854B2 · Nakagawa et al. · 2019 [cited by applicant]
US 10350751B2 · Guerin et al. · 2019 [cited by applicant]
US 10406441B2 · Nathan et al. · 2019 [cited by applicant]
US 10452974B1 · Cosic · 2019 [cited by applicant]
US 10475225B2 · Park et al. · 2019 [cited by applicant]
US 10484333B2 · Sethi et al. · 2019 [cited by applicant]
US 10607134B1 · Cosic · 2020 [cited by applicant]
US 11023788B2 · Huberman et al. · 2021 [cited by applicant]
US 11055583B1 · Cosic · 2021 [cited by applicant]
US 11238344B1 · Cosic · 2022 [cited by applicant]
US 11497052B1 · Zhang et al. · 2022 [cited by applicant]
US 11526275B2 · Randall et al. · 2022 [cited by applicant]
US 11694059B2 · Li et al. · 2023 [cited by applicant]
US 11694682B1 · Reinspach et al. · 2023 [cited by applicant]
US 11887231B2 · Park · 2024 [cited by applicant]
US 12554325B2 · Hussami · 2026 [cited by examiner]
US 20020003571A1 · Schofield et al. · 2002 [cited by applicant]
US 20020019822A1 · Seki et al. · 2002 [cited by applicant]
US 20030026588A1 · Elder et al. · 2003 [cited by applicant]
US 20030032467A1 · Mayer et al. · 2003 [cited by applicant]
US 20030065662A1 · Cosic · 2003 [cited by applicant]
US 20030122578A1 · Masui et al. · 2003 [cited by applicant]
US 20030171146A1 · Mayer et al. · 2003 [cited by applicant]
US 20030216834A1 · Allard · 2003 [cited by applicant]
US 20040117771A1 · Venkatapathy · 2004 [cited by applicant]
US 20040194017A1 · Cosic · 2004 [cited by applicant]
US 20040249774A1 · Caid et al. · 2004 [cited by applicant]
US 20040267521A1 · Cutler et al. · 2004 [cited by applicant]
US 20050149517A1 · Cosic · 2005 [cited by applicant]
US 20050149542A1 · Cosic · 2005 [cited by applicant]
US 20050154745A1 · Hansen et al. · 2005 [cited by applicant]
US 20050240412A1 · Fujita · 2005 [cited by applicant]
US 20050245303A1 · Graepel et al. · 2005 [cited by applicant]
US 20050289105A1 · Cosic · 2005 [cited by applicant]
US 20060047612A1 · Stanley et al. · 2006 [cited by applicant]
US 20060181236A1 · Brogardh · 2006 [cited by applicant]
US 20060184410A1 · Ramamurthy et al. · 2006 [cited by applicant]
US 20060190930A1 · Hecht et al. · 2006 [cited by applicant]
US 20060259466A1 · Bilotti · 2006 [cited by applicant]
US 20060265406A1 · Chkodrov et al. · 2006 [cited by applicant]
US 20070006159A1 · Hecht et al. · 2007 [cited by applicant]
US 20070050606A1 · Ferren et al. · 2007 [cited by applicant]
US 20070050719A1 · Lui et al. · 2007 [cited by applicant]
US 20070058856A1 · Boregowda et al. · 2007 [cited by applicant]
US 20070061735A1 · Hoffberg et al. · 2007 [cited by applicant]
US 20070106633A1 · Reiner · 2007 [cited by applicant]
US 20080071770A1 · Schloter et al. · 2008 [cited by applicant]
US 20080144893A1 · Guo et al. · 2008 [cited by applicant]
US 20080207330A1 · Beale · 2008 [cited by applicant]
US 20080215508A1 · Hanneman et al. · 2008 [cited by applicant]
US 20080254429A1 · Woolf et al. · 2008 [cited by applicant]
US 20080281764A1 · Baxter · 2008 [cited by applicant]
US 20080288259A1 · Chambers et al. · 2008 [cited by applicant]
US 20090044113A1 · Jones et al. · 2009 [cited by applicant]
US 20090067727A1 · Hirohata · 2009 [cited by applicant]
US 20090070337A1 · Romem et al. · 2009 [cited by applicant]
US 20090110061A1 · Lee et al. · 2009 [cited by applicant]
US 20090131152A1 · Busse · 2009 [cited by applicant]
US 20090136095A1 · Marcon et al. · 2009 [cited by applicant]
US 20090141969A1 · Yu et al. · 2009 [cited by applicant]
US 20090199095A1 · Nicol, II et al. · 2009 [cited by applicant]
US 20090222388A1 · Hua et al. · 2009 [cited by applicant]
US 20090287643A1 · Corville et al. · 2009 [cited by applicant]
US 20090288001A1 · Hamilton, II · 2009 [cited by applicant]
US 20090324010A1 · Hou · 2009 [cited by applicant]
US 20100023541A1 · Cosic · 2010 [cited by applicant]
US 20100033780A1 · Gitter · 2010 [cited by applicant]
US 20100063663A1 · Tolstedt · 2010 [cited by applicant]
US 20100063949A1 · Eaton et al. · 2010 [cited by applicant]
US 20100082536A1 · Cosic · 2010 [cited by applicant]
US 20100114746A1 · Bobbitt et al. · 2010 [cited by applicant]
US 20100138370A1 · Wu et al. · 2010 [cited by applicant]
US 20100220930A1 · Sun · 2010 [cited by applicant]
US 20100241595A1 · Felsher · 2010 [cited by applicant]
US 20100278420A1 · Shet et al. · 2010 [cited by applicant]
US 20110004586A1 · Cherryholmes et al. · 2011 [cited by applicant]
US 20110007079A1 · Perez et al. · 2011 [cited by applicant]
US 20110030031A1 · Lussier et al. · 2011 [cited by applicant]
US 20110085734A1 · Berg et al. · 2011 [cited by applicant]
US 20110093435A1 · Zha et al. · 2011 [cited by applicant]
US 20110218672A1 · Maisonnier et al. · 2011 [cited by applicant]
US 20110270794A1 · Drory et al. · 2011 [cited by applicant]
US 20120089570A1 · Zha et al. · 2012 [cited by applicant]
US 20120150773A1 · DiCorpo et al. · 2012 [cited by applicant]
US 20120167057A1 · Schmich et al. · 2012 [cited by applicant]
US 20120192096A1 · Bowman et al. · 2012 [cited by applicant]
US 20120284026A1 · Cardillo et al. · 2012 [cited by applicant]
US 20120290347A1 · Elazouni et al. · 2012 [cited by applicant]
US 20130007532A1 · Miller et al. · 2013 [cited by applicant]
US 20130047049A1 · Chen et al. · 2013 [cited by applicant]
US 20130156345A1 · Shmunk · 2013 [cited by applicant]
US 20130159021A1 · Felsher · 2013 [cited by applicant]
US 20130204907A1 · Alonso Alarcon et al. · 2013 [cited by applicant]
US 20130218932A1 · Cosic · 2013 [cited by applicant]
US 20130226974A1 · Cosic · 2013 [cited by applicant]
US 20130238533A1 · Mrkar et al. · 2013 [cited by applicant]
US 20130278501A1 · Bulzacki · 2013 [cited by applicant]
US 20130278631A1 · Border et al. · 2013 [cited by applicant]
US 20130304684A1 · Yufik · 2013 [cited by applicant]
US 20130325768A1 · Sinyavskiy et al. · 2013 [cited by applicant]
US 20130329946A1 · Archibald et al. · 2013 [cited by applicant]
US 20130343640A1 · Buehler et al. · 2013 [cited by applicant]
US 20140004950A1 · Szufnara · 2014 [cited by applicant]
US 20140052717A1 · Franks et al. · 2014 [cited by applicant]
US 20140075249A1 · Sato et al. · 2014 [cited by applicant]
US 20140089232A1 · Buibas · 2014 [cited by applicant]
US 20140136013A1 · Wolverton et al. · 2014 [cited by applicant]
US 20140143276A1 · Rogers et al. · 2014 [cited by applicant]
US 20140161250A1 · Leeds et al. · 2014 [cited by applicant]
US 20140164430A1 · Hadjieleftheriou et al. · 2014 [cited by applicant]
US 20140177946A1 · Lim et al. · 2014 [cited by applicant]
US 20140207580A1 · Minnis et al. · 2014 [cited by applicant]
US 20140211988A1 · Fan et al. · 2014 [cited by applicant]
US 20140277718A1 · Izhikevich et al. · 2014 [cited by applicant]
US 20140278754A1 · Cronin et al. · 2014 [cited by applicant]
US 20150006171A1 · Westby et al. · 2015 [cited by applicant]
US 20150023186A1 · Vasseur et al. · 2015 [cited by applicant]
US 20150023205A1 · Vasseur et al. · 2015 [cited by applicant]
US 20150039304A1 · Wein · 2015 [cited by applicant]
US 20150055821A1 · Fotland · 2015 [cited by applicant]
US 20150089081A1 · Thubert et al. · 2015 [cited by applicant]
US 20150258683A1 · Izhikevich et al. · 2015 [cited by applicant]
US 20150264306A1 · Marilly et al. · 2015 [cited by applicant]
US 20150269156A1 · Awadallah et al. · 2015 [cited by applicant]
US 20150269415A1 · Gelbman · 2015 [cited by applicant]
US 20150283702A1 · Izhikevich et al. · 2015 [cited by applicant]
US 20150310041A1 · Kier et al. · 2015 [cited by applicant]
US 20150324685A1 · Bohn et al. · 2015 [cited by applicant]
US 20150339213A1 · Lee et al. · 2015 [cited by applicant]
US 20150363687A1 · Gocek · 2015 [cited by applicant]
US 20160063118A1 · Campbell et al. · 2016 [cited by applicant]
US 20160077166A1 · Morozov et al. · 2016 [cited by applicant]
US 20160140999A1 · Cosic · 2016 [cited by applicant]
US 20160142650A1 · Cosic · 2016 [cited by applicant]
US 20160167226A1 · Schnittman · 2016 [cited by applicant]
US 20160243701A1 · Gildert et al. · 2016 [cited by applicant]
US 20160274187A1 · Menon et al. · 2016 [cited by applicant]
US 20160306806A1 · Fackler · 2016 [cited by applicant]
US 20160328480A1 · Owens et al. · 2016 [cited by applicant]
US 20170010106A1 · Shashua · 2017 [cited by applicant]
US 20170024877A1 · Versace et al. · 2017 [cited by applicant]
US 20170161958A1 · Eilat · 2017 [cited by applicant]
US 20170200078A1 · Bichler · 2017 [cited by applicant]
US 20180017791A1 · Beckman · 2018 [cited by applicant]
US 20180060144A1 · Capobianco et al. · 2018 [cited by applicant]
US 20180068564A1 · Tanigawa et al. · 2018 [cited by applicant]
US 20180096261A1 · Chu et al. · 2018 [cited by applicant]
US 20180101146A1 · Hariharan et al. · 2018 [cited by applicant]
US 20180120813A1 · Coffman et al. · 2018 [cited by applicant]
US 20180137403A1 · Kaur · 2018 [cited by applicant]
US 20180174207A1 · Potucek et al. · 2018 [cited by applicant]
US 20180375720A1 · Yang et al. · 2018 [cited by applicant]
US 20190028545A1 · Yang et al. · 2019 [cited by applicant]
US 20190034765A1 · Kaehler et al. · 2019 [cited by applicant]
US 20190096503A1 · Chakravarty et al. · 2019 [cited by applicant]
US 20190102049A1 · Anzu res · 2019 [cited by applicant]
US 20190107839A1 · Parashar et al. · 2019 [cited by applicant]
US 20190213446A1 · Tsou et al. · 2019 [cited by applicant]
US 20190347334A1 · Sundaramoorthy et al. · 2019 [cited by applicant]
US 20200334853A1 · Ciuc · 2020 [cited by applicant]
US 20210233045A1 · Singh et al. · 2021 [cited by applicant]
US 20210374146A1 · Hrastnik et al. · 2021 [cited by applicant]
US 20220342601A1 · Daoud et al. · 2022 [cited by applicant]
JP 2016126605 · 2016 [cited by applicant]
Karen Simonyan and Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Visual Recognition, ICLR 2015 (Apr. 10, 2015). [cited by applicant]
Katrakazas, Christos, et al., Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions, Transportation Research Part C: Emerging Technologies vol. 60 (Sep. 24, 20… [cited by applicant]
Ken Goldberg, Robots With Their Heads in the Clouds, Medium, https://medium.com/aspen-ideas/robots-with-their-heads-in-the-clouds-e88ac44def8a (Aug. 25, 2014). [cited by applicant]
Kye-Hyeon Kim, Sanghoon Hong, Byungseok Roh, Yeongjae Cheon, Minje Park, PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection, arXiv:1608.08021 (Sep. 30, 2016). [cited by applicant]
Li, Xiaohui, et al., Real-time trajectory planning for autonomous urban driving: Framework, algorithms, and verifications, IEEE 2016 (Oct. 26, 2015). [cited by applicant]
Liang-Chieh Chen, George Papandreou, Florian Schroff, Hartwig Adam, Rethinking Atrous Convolution for Semantic Image Segmentation, arXiv:1706.05587 (Jun. 17, 2017). [cited by applicant]
Liang-Chieh Chen, George Papandreou, iasonas Kokkinos, Kevin Murphy, Alan L Yuille, DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs, arXiv:1606.00915 (Jun.… [cited by applicant]
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille, Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs, ICLR 2015 (Jun. 7, 2016). [cited by applicant]
Liang-Chieh Chen, George Papandreou, Kevin Murphy, Alan L. Yuille, Weakly-and semi-supervised learning of a DCNN for semantic image segmentation, arXiv:1502.02734 (Oct. 5, 2015). [cited by applicant]
Lifeng An, Xinyu Zhang, Hongbo Gao and Yuchao Liu, Semantic segmentation-aided visual odometry for urban autonomous driving (Oct. 30, 2017). [cited by applicant]
M. Abadi, A. Agarwal, et al., Tensorflow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, arXiv:1603.04467 (Mar. 16, 2016). [cited by applicant]
Ma, Liang, et al., Efficient sampling-based motion planning for on-road autonomous driving, IEEE 2015 (Feb. 13, 2015). [cited by applicant]
Marcus Waibel, RoboEarth: A World Wide Web for Robots, IEEE Spectrum, https://spectrum.IEEE.org/roboearth-a-world-wide-web-for-robots (Feb. 5, 2011). [cited by applicant]
Mark Everingham, S. M. Ali Eslami, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserma, The Pascal Visual Object Classes Challenge—A Retrospective, IJCV (Jan. 1, 2015). [cited by applicant]
Mohammad O. A. Aqel, Mohammad H. Marhaban, M. Iqbal Saripan and Napsiah Bt. Ismail, Review of visual odometry: types, approaches, challenges, and applications (Oct. 28, 2016). [cited by applicant]
Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich, Feedforward Semantic Segmentation With Zoom-Out Features, CVPR 2015 (Dec. 2, 2014). [cited by applicant]
Moritz Werling, Julius Ziegler, Soren Kammel, Sebastian Thrun, Optimal trajectory generation for dynamic street scenarios in a frenet frame, IEEE 2010 (Jul. 15, 2010). [cited by applicant]
Net-Scale Technologies, Inc., Autonomous Off-Road Vehicle Control Using End-to-End Learning, Final Technical Report, DARPA-IPTO (Jul. 30, 2004). [cited by applicant]
Niloufar Pourian, S. Karthikeyan, and B.S. Manjunath, Weakly supervised graph based semantic segmentation by learning communities of image-parts, ICCV 2015 (Feb. 18, 2016). [cited by applicant]
Oliver Pink, Visual map matching and localization using a global feature map, IEEE 2008 (Jun. 23, 2008). [cited by applicant]
Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus, Yann LeCun, OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, ICLR 2014 (Feb. 24, 2014). [cited by applicant]
Pomerleau, Dean, “Neural Network Perception for Mobile Robot Guidance” (Jul. 31, 1993). [cited by applicant]
R. K. Satzoda and Mohan M. Trivedi, Vision-Based Lane Analysis: Exploration of Issues and Approaches for Embedded Realization, IEEE 2013 (Sep. 12, 2013). [cited by applicant]
Ravi Kumar Satzoda and Mohan Manubhai Trivedi, Drive Analysis Using Vehicle Dynamics and Vision-Based Lane Semantics, IEEE 2015 (Sep. 25, 2014). [cited by applicant]
Ross Girshick, Fast R-CNN, arXiv:1504.08083 (Sep. 27, 2015). [cited by applicant]
Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014 (Oct. 22, 2014). [cited by applicant]
Scott Drew Pendleton, Hans Andersen, Xinxin Du, Xiaotong Shen, Malika Meghjani, You Hong Eng, Daniela Rus, and Marcelo H. Ang Jr., Perception, planning, control, and coordination for autonomous vehicles, Machines 2017 (… [cited by applicant]
Sean Bell, C. Lawrence Zitnick, Kavita Bala, Ross Girshick, Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks (Dec. 14, 2015). [cited by applicant]
Sebastian Thrun, Michael Montemerlo, The GraphSLAM Algorithm with Applications to Large-Scale Mapping of Urban Structures, Stanford AI Lab (May 1, 2006). [cited by applicant]
Sergey Ioffe, Christian Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, arXiv:1502.03167 (Mar. 2, 2015). [cited by applicant]
Sergey Ioffe, Christian Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate shift, ICML 2015 (Mar. 2, 2015). [cited by applicant]
Seunghoon Hong, Hyeonwoo Noh, Bohyung Han, Decoupled Deep Neural Network for Semisupervised Semantic Segmentation, arXiv:1506.04924 (Jun. 17, 2015). [cited by applicant]
Seunghoon Hong, Junhyuk Oh, Bohyung Han, and Honglak Lee, Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network, arXiv:1512.07928 (Dec. 24, 2015). [cited by applicant]
Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, arXiv:1506.01497 (Jan. 6, 2016). [cited by applicant]
Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet, Zhizhong Su, Dalong Du, Chang Huang, Philip H. S. Torr, Conditional Random Fields as Recurrent Neural Networks, arXiv:1502.03240 (Apr. 13, 2016). [cited by applicant]
Simon Ulbrich, Andreas Reschka, Jens Rieken, Susanne Ernst, Gerrit Bagschik, Frank Dierkes, Marcus Nolte, Markus Maurer, Towards a Functional System Architecture for Automated Vehicles, arXiv:1703.08557 (Mar. 30, 2017). [cited by applicant]
Xiaolin Song, Haotian Cao, and Jiang Huang, Vehicle path planning in various driving situations based on the elastic band theory for highway collision avoidance, Proceedings of the Institution of Mechanical Engineers, P… [cited by applicant]
Takafumi Taketomi, Hideaki Uchiyama, Sei Ikeda, Visual SLAM algorithms: a survey from 2010 to 2016, IPSJ 2017 (Jun. 2, 2017). [cited by applicant]
Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla, SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, arXiv:1511.00561 (Oct. 10, 2016). [cited by applicant]
Watt, Alan & Policarpo, Fabio, 3D Games Real-time Rendering and Software Technology, Chapter 7 “Behavior and Al Games” (Jan. 1, 2001). [cited by applicant]
Wei Liu, Andrew Rabinovich, Alexander C Berg, ParseNet: Looking Wider to See Better, arXiv:1506.04579 (Nov. 19, 2015). [cited by applicant]
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg, SSD: Single Shot MultiBox Detector, arXiv:1512.02325 (Mar. 30, 2016). [cited by applicant]
Wolfram Burgard, Oliver Brock, Cyrill Stachniss, Map-based precision vehicle localization in urban environments, IEEE 2008 (2008); Ji Zhang, Sanjiv Singh, LOAM: Lidar Odometry and Mapping in Real-time, RSS 2014 (Jul. 20… [cited by applicant]
Xiaozhi Chen, Kaustav Kundu, Ziyu Zhang, Huimin Ma, Sanja Fidler, Raquel Urtasun, Monocular 3D Object Detection for Autonomous Driving, CVPR 2016 (Dec. 12, 2016). [cited by applicant]
Xinxin Du1, Marcelo H. Ang Jr., Daniela Rus, Car Detection for Autonomous Vehicle: LIDAR and Vision Fusion Approach Through Deep Learning Framework, IEEE 2017 (Sep. 24-28, 2017). [cited by applicant]
Yu Xiang, Wongun Choi, Yuanqing Lin, and Silvio Savarese, Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection, IEEE 2017 (Mar. 9, 2017). [cited by applicant]
Zhaowei Cai, Quanfu Fan, Rogerio S. Feris, and Nuno Vasconcelos, A Unified Multi- scale Deep Convolutional Neural Network for Fast Object Detection, arXiv:1607.07155 (Jul. 25, 2016). [cited by applicant]
Ziegler, Julius, et al., Trajectory planning for Bertha—A local, continuous methods, IEEE 2014 (Jul. 17, 2014). [cited by applicant]
Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang, Semantic Image Segmentation via Deep Parsing Network, arXiv:1509.02634 (Sep. 24, 2015). [cited by applicant]
Cho, Hyunggi, Young-Woo Seo, B.V.K. Vijaya Kumar and Ragunathan Raj Rajkumar, A multi-sensor fusion system for moving object detection and tracking in urban driving environments, 2014 IEEE International Conference on Ro… [cited by applicant]
Zhang, Yiying, Lei Guo, and Nicolas D. Georganas. “AGILE: An architecture for agent-based collaborative and interactive virtual environments.” Proc. Workshop on Application Virtual Reality Technologies for Future Teleco… [cited by applicant]
Eladhari, Mirjam P., “Semi-Autonomous Avatars in Virtual Game Worlds,” Pre-conference to the ECREA 2010—3rd European Communication Conference, Avatars and Humans. Representing Users in Digital Games, Hamburg, Germany, O… [cited by applicant]
IEEE Spectrum, Evan Ackerman Erico Guizzo, iRobot Brings Visual Mapping and Navigation to the Roomba 980, Sep. 16, 2015. [cited by applicant]
Renaud Dube, et al., SegMap: 3D Segment Mapping using Data-Driven Descriptors, Apr. 25, 2018. [cited by applicant]
Joseph Redmon, Ali Farhadi, YOLO9000: Better, Faster, Stronger, Dec. 25, 2016. [cited by applicant]
Electric Jen, How Does Autopilot React to Disappearing Lane Markings?, https://www.teslarati.com/autopilot-experience-disappearing-lane-markings/, Nov. 18, 2015. [cited by applicant]
Seunghoon Hong, Hyeonwoo Noh, Bohyung Han, Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation, Jun. 17, 2015. [cited by applicant]
Xinxin Dul, Marcelo H. Aug Jr., Sertac Karaman and Daniela Rus, A General Pipeline for 3D Detection of Vehicles, Feb. 12, 2018. [cited by applicant]
Wenjie Luo, Bin Yang and Raquel Urtasun, Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net, 2018. [cited by applicant]
Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Dacheng Tao, Deep Ordinal Regression Network for Monocular Depth Estimation, Jun. 6, 2018. [cited by applicant]
Gene, Firmware 7.1 Sees First Wave of Tesla Autopilot Restrictions, https://www.teslarati.com/tesla-firmware-7-1-rolls-out-autopilot-restrictions/, Jan. 9, 2016. [cited by applicant]
Net-Scale Technologies, Inc., Autonomous Off-Road Vehicle Control Using End-to-End Learning, http://www.net-scale. com, Jul. 30, 2004. [cited by applicant]
Russell Stewart, Mykhaylo Andriluka, End-to-end people detection in crowded scenes, Jul. 8, 2015. [cited by applicant]
Ping Luo, Jiamin Rene, Zhanglin Peng, Ruimao Zhang, Jingyu Li, Differentiable Learning-To-Normalize Via Switchable Normalization, Apr. 24, 2019. [cited by applicant]
Garth Woodworth, Tesla Autopilot ultrasonic sensors handle difficult merging event, https://www.teslarati.com/tesla-autopilot-ultrasonic-sensors-handle-difficult-merging-event/, Feb. 7, 2016. [cited by applicant]
Joshua Owoyemi, Behavioural Cloning Applied to Self-Driving Car on a Simulated Track, Jan. 27, 2017. [cited by applicant]
Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, Apr. 10, 2015. [cited by applicant]
Liang-Chieh Cheri, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam, Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, Aug. 22, 2018. [cited by applicant]
Pierre Sermanet David Eigen Xiang Zhang Michael Mathieu Rob Fergus Yann LeCun, OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, Feb. 24, 2014. [cited by applicant]
Zhichao Yin and Jianping Shi, GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose, Mar. 12, 2018. [cited by applicant]
Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik, UC Berkeley and 21CSI, Rich feature hierarchies for accurate object detection and semantic segmentation, 2014. [cited by applicant]
Brady Berlin, Testa Owners Vote on 7.1 Features & Enhancements, https://www.teslarati.com/tesla-owners-vote-on-7-1-features-enhancements/, Nov. 17, 2015. [cited by applicant]
Bin Yang, Wenjie Luo, Raquel Urtasun, PIXOR: Real-time 3D Object Detection from Point Clouds, Feb. 17, 2019. [cited by applicant]
Seunghoon Hongt Junhyuk Oh, Bohyung Hant Honglak Leet, Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network, Dec. 24, 2015. [cited by applicant]
Amir Sadeghian', Alexandre Alahi2, Silvio Savarese, Tracking The Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies, Dec. 25, 2017. [cited by applicant]
Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla, Senior Member, IEEE, SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, Oct. 10, 2016. [cited by applicant]
Wenging Chu , Yao Liu, Chen Shen, Deng Cai, Member, IEEE, and Xian-Sheng Hua, Fellow, IEEE, Multi-Task Vehicle Detection With Region-of-Interest Voting, Oct. 12, 2017. [cited by applicant]
Young-Sik Shin, Yeong Sang Park and Ayoung Kim, Direct Visual SLAM using Sparse Depth for Camera-LiDAR System, May 2018. [cited by applicant]
Zhedong Zheng Yi Yang, Unsupervised Scene Adaptation with Memory Regularization in vivo, Feb. 7, 2023. [cited by applicant]
Visual Object Classes Challenge 2012 (VOC2012), Pascal2, 2012. [cited by applicant]
Steve Hanley, Testa v7.1 Introduces New Summoning Feature and Autopilot Enhancements, Jan. 9, 2016. [cited by applicant]
Charles R. Qi' * Wei Liu2 Chenxia Wu2 Hao Su3 Leonidas J. Guibas, Frustum PointNets for 3D Object Detection from RGB-D Data, Apr. 13, 2018. [cited by applicant]
Jifeng Dai, et al., Deformable Convolutional Networksb—MSRA COCO Detection & Segmentation Challenge 2017 Entry. [cited by applicant]
Jens Behley and Cyril! Stachniss, Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments, Jun. 2018. [cited by applicant]
Fred Lambert, GM's Cruise is now testing its autonomous and all-electric Chevy Bolt in Scottsdale, Arizona, Aug. 9, 2016. [cited by applicant]
Darrell Etherington, Cruise has around 30 self-driving test car right now, Sep. 14, 2016. [cited by applicant]
Ji Zhang and Sanjiv Singh, LOAM: Lidar Odometry and Mapping in Real-time, Jul. 1, 2014. [cited by applicant]
George Papandreou, Liang-Chieh Chen, Kevin Murphy, Alan L. Yuille, Weakly- and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation, Oct. 5, 2015. [cited by applicant]
Xiaolin Song, Haotian Caol, Jiang Huang, Vehicle path planning in various driving situations based on the elastic band theory for highway collision avoidance, Dec. 12, 2013. [cited by applicant]
Gene, Tesla Model X Firmware 7.0 Features Exposed, https://www.teslarati.com/tesla-model-x-firmware-7-0-features-exposed/, Sep. 30, 2015. [cited by applicant]
Sarthak Sharma'*, Junaid Ahmed Ansaril*, J. Krishna Murthy2, K. Mandava Krishna, Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking, Jul. 27, 2018. [cited by applicant]
Gene, Inside Tesla Version 8.0: release notes and screenshots, https://www.teslarati.com/tesla-version-8-release-notes-screenshots/, Sep. 22, 2016. [cited by applicant]
Eugene Kim, Amazon's $775 million deal for robotics company Kiva is starting to look really smart, https://www.businessinsider.in/amazons-775-million-deal-for-robotics-company-kiva-is-starting-to-look-really-smart/artic… [cited by applicant]
Wilko Schwarting, Javier Alonso-Mora, and Daniela Rust, Planning and Decision-Making for Autonomous Vehicles, 2018. [cited by applicant]
Julius Ziegler, Philipp Bender, Thao Dang and Christoph Stiller, Trajectory Planning for BERTHA—a Local, Continuous Method, Jun. 11, 2014. [cited by applicant]
Zhedong Zheng, Yi Yang, Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation, Oct. 15, 2020. [cited by applicant]
Jesse Levinson, Michael Montemerlo, Sebastian Thrun, Map-Based Precision Vehicle Localization in Urban Environments, 2008. [cited by applicant]
Wenjie Luo, Bin Yang and Raquel Urtasun, Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net, Dec. 2020. [cited by applicant]
Jonathan Long* Evan Shelhamer* Trevor Darrell, Fully Convolutional Networks for Semantic Segmentation, Nov. 14, 2014. [cited by applicant]
Wongun Choi, Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor, Apr. 2015. [cited by applicant]
Young-Woo Seo, Ragunathan Rajkumar, A vision system for detecting and tracking of stoplines, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), Qingdao, China, pp. 1970-1975 (Oct. 2014). [cited by applicant]
R. Azimi, G. Bhatia, R. Rajkumar and P. Mudalige, Ballroom Intersection Protocol: Synchronous Autonomous Driving at Intersections, 2015 IEEE 21st International Conference on Embedded and Real-Time Computing Systems and … [cited by applicant]
Y.-W. Seo and R. R. Rajkumar, Detection and tracking of boundary of unmarked roads, 17th International Conference on Information Fusion (FUSION), Salamanca, Spain, pp. 1-6 (2014). [cited by applicant]
Azimi, R., Bhatia, G., Rajkumar, R., and Mudalige, P., Intersection Management using Vehicular Networks, SAE Technical Paper 2012-01-0292 (Apr. 16, 2012). [cited by applicant]
J. Kim, H. Kim, K. Lakshmanan and R. Rajkumar, Parallel scheduling for cyber-physical systems: Analysis and case study on a self-driving car, 2013 ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), Phi… [cited by applicant]
Reza Azimi, Gaurav Bhatia, Ragunathan Raj Rajkumar, and Priyantha Mudalige. STIP: Spatio-Temporal Intersection Protocols for Autonomous Vehicles, ICCPS 2014: ACM/IEEE. [cited by applicant]
5th International Conference on Cyber-Physical Systems (with CPS Week 2014) (ICCPS '14). IEEE Computer Society, USA, pp. 1-12 (Apr. 2014). [cited by applicant]
Junsung Kim, Ragunathan (Raj) Rajkumar, and Markus Jochim, Towards dependable autonomous driving vehicles: a system-level approach, ACM Sigbed Review, vol. 10, Issue 1, pp. 29-32 (Feb. 2013). [cited by applicant]