Brian Gregory Donohue

US Patent:

20210302169, Sep 30, 2021

Filed:

Mar 31, 2020

Appl. No.:

16/836602

Inventors:

- San Francisco CA, US
Matthew Fox - San Francisco CA, US
Austin Bae - San Francisco CA, US
Brian Joseph Donohue - San Francisco CA, US

International Classification:

G01C 21/32
G05D 1/00
G05D 1/02

Abstract:

The subject disclosure relates to ways to determine a data collection surveillance cadence. In some aspects, a process of the disclosed technology includes steps for receiving historic map data for one or more geographic regions, wherein each of the one or more geographic regions comprises one or more map features, calculating a change rate for each of the one or more map features, and determining a surveillance cadence for each of the one or more geographic regions based on the change rate for each of the one or more map features. Systems and machine-readable media are also provided.

US Patent:

20210302170, Sep 30, 2021

Filed:

Mar 31, 2020

Appl. No.:

16/836799

Inventors:

- San Francisco CA, US
Matthew Fox - San Francisco CA, US
Brian Joseph Donohue - San Francisco CA, US
Kangyuan Niu - Northridge CA, US
Katherine Leung - Milpitas CA, US

International Classification:

G01C 21/32
G06F 16/29
G06F 16/23

Abstract:

The subject disclosure relates techniques for evaluating map quality. In some aspects, a process of the disclosed technology includes steps for receiving change data indicating one or more feature discrepancies associated with one or more geographic regions of a digital map, analyzing the change data to determine which of the one or more feature discrepancies resulted in verified updates to the digital map, and generating a quality score for each of the geographic map regions based on the verified updates. Systems and machine-readable media are also provided.

US Patent:

20210302171, Sep 30, 2021

Filed:

Mar 31, 2020

Appl. No.:

16/836848

Inventors:

- San Francisco CA, US
Matthew Fox - San Francisco CA, US
Austin Bae - San Francisco CA, US
Brian Joseph Donohue - San Francisco CA, US
Srishti Iyer Koduvayur - Emeryville CA, US

International Classification:

G01C 21/32
G05D 1/02

Abstract:

The subject disclosure relates techniques for evaluating map change signals. In some aspects, a process of the disclosed technology includes steps for receiving, at a change detection system, a plurality of change detection signals, wherein each of the change detection signals provides information regarding changes to at least one map feature on a digital map, determining, a relevance value for each of the change detection signals, and prioritizing each of the plurality of change detection signals based on the relevance value for each of the change detection signals. Systems and machine-readable media are also provided.

US Patent:

20210302981, Sep 30, 2021

Filed:

Mar 31, 2020

Appl. No.:

16/836612

Inventors:

- San Francisco CA, US
Robin Yang - Oakland CA, US
Lucio Otavio Marchioro Rech - San Mateo CA, US
Thomas Bachant - San Francisco CA, US
Brian Joseph Donohue - San Francisco CA, US
George Hines - Kensington CA, US
Carlos Miguel Lasa - Union City CA, US
Patrick John William Casey - San Francisco CA, US

Assignee:

GM Cruise Holdings LLC - San Francisco CA

International Classification:

G05D 1/02
G05D 1/00
B60W 60/00

Abstract:

Systems and methods are provided for accelerating autonomous vehicle testing. In particular, autonomous vehicle testing is accelerated by providing proactive waypoints. Systems and methods are provided for proactively seeking out times and locations in which an autonomous vehicle will most likely encounter on-road exposure of a particular set of variables. By increasing on-road exposure to a particular set of variables, an autonomous vehicle's response to the set of variables be more efficiently tested. According to various implementations, autonomous vehicles are automatically dispatched to routed to areas in which a test criteria frequently occurs, during particular times when the test criteria is likely to occur.

US Patent:

20210302996, Sep 30, 2021

Filed:

Mar 31, 2020

Appl. No.:

16/836517

Inventors:

- San Francisco CA, US
Jeremy Allan - Menlo Park CA, US
Robin Yang - Oakland CA, US
Andrew Robinson - San Francisco CA, US
Lucio Rech Marchioro Rech - San Francisco CA, US
Brian Joseph Donohue - San Francisco CA, US
Kavya Sambana - Castro Valley CA, US

International Classification:

G05D 1/02
G01C 21/34
B60W 60/00
G01C 21/36
G08G 1/16

Abstract:

The subject disclosure relates to techniques for real-time lane validation. A process of the disclosed technologies can include steps for receiving a route from a remote computing system, the route indicating lanes on the route that an autonomous vehicle must traverse, traversing at least one lane of the lanes on the route, and sending sensor data to the remote computing system after traversing the at least one lane, the sensor data indicating whether the at least one lane is in accordance with a virtual lane of a virtual map, the virtual lane corresponding to the at least one lane.

US Patent:

20200409354, Dec 31, 2020

Filed:

Jun 28, 2019

Appl. No.:

16/457696

Inventors:

- San Francisco CA, US
Brian Donohue - San Francisco CA, US
Lucio Rech - San Francisco CA, US
Stephen Worlow - San Francisco CA, US
Daniel Blick - San Francisco CA, US
Varun Bharadwaj - San Francisco CA, US

International Classification:

G05D 1/00
G06N 5/02
G07C 5/08
G07C 5/00

Abstract:

Systems and methods provide for routing an autonomous vehicles based on an assessment of its limitations. The autonomous vehicle can avoid problematic routes by applying a set of rules to a map, where the set of rules are associated with a feature that causes a failure of the autonomous vehicle due to an autonomous vehicle limitation. Based on the application of the set of rules, a portion of a route on the map that is associated with the feature can be identified, and an identifier can be applied to the identified portion of the route associated with the feature on a routing map. The portion of the route can be omitted from a routable graph applied to the routing map, such that the route for the autonomous vehicle is generated in accordance with the routable graph.

US Patent:

20200409355, Dec 31, 2020

Filed:

Aug 30, 2019

Appl. No.:

16/557635

Inventors:

- San Francisco CA, US
Brian Donohue - San Francisco CA, US
Lucio Rech - San Francisco CA, US
Stephen Worlow - San Francisco CA, US
Daniel Blick - San Francisco CA, US
Varun Bharadwaj - San Francisco CA, US

International Classification:

G05D 1/00
G07C 5/08
G06N 5/02
G07C 5/00

Abstract:

Systems and methods provide for routing autonomous vehicles by simulating an autonomous vehicle traversing a route on a map representing a physical area. A router flag can be generated at a specific location on the map. A router flag rule that defines a factor that caused a failure of the autonomous vehicle can then be created at the location, and the autonomous vehicle can be simulated traversing the to identify at least one other area on the map where the autonomous vehicle is likely to fail. An identifier can be applied to the other area on the map where the autonomous vehicle is likely to fail according to the router flag rule. The other area with the applied identifier can be omitted from a routable graph applied to the routing map, such that the route for the autonomous vehicle is generated in accordance with the routable graph.

US Patent:

20200363215, Nov 19, 2020

Filed:

May 13, 2019

Appl. No.:

16/410402

Inventors:

- San Francisco CA, US
Brian Donohue - San Francisco CA, US
Alexander Sennikov - San Francisco CA, US
Irfan Lone - San Francisco CA, US
Steve Xie - San Francisco CA, US
Juan Fasola - San Francisco CA, US

International Classification:

G01C 21/32
G01S 17/89
G05D 1/00
G05D 1/02

Abstract:

The present technology provides a system that can update aspects of an authoritative map portion stored on an autonomous vehicle using low-resolution data from the at least one sensor of the autonomous vehicle, and therefore avoids the need for dispatching the special purpose mapping vehicle for these updates. The captured low-resolution data can be compared with the high-resolution map portion to determine that the sensor data reflects a feature in a way that is inconsistent with how that feature is represented in the authoritative map portion. The sensor data can then be used to relabel the authoritative map portion.