Patent
US 12,608,953 B2USING A GAN DISCRIMINATOR FOR ANOMALY DETECTION
Dimitar H. Lukarski, Ryan M. Wiesenberg, Jeffrey M. Walls
Toyota Jidosha Kabushiki Kaisha, Toyota (JP)·Apr. 21, 2026·US
Copyright © 2026 Matter42. All rights reserved.
Patent
Atlas literature
Patent
US 12,608,953 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates one embodiment of a detection system that is associated with using a discriminator to detect anoma- lies in sensor data.
FIG. 2 illustrates one embodiment of the detection system of
FIG. 3 illustrates one embodiment of a generative neural network.
FIG. 4 illustrates an example of a discriminator network.
FIG. 5 illustrates a flowchart for one embodiment of a method that is associated with training a model to synthesize 20 probe data using a generative …
FIG. 6 is a diagram showing an architecture for training with a GAN.
FIG. 7 illustrates a flowchart for one embodiment of a method associated with identifying anomalies within sensor 25 data.
FIG. 8 illustrates one example of sensor data associated with a roadway that includes an anomaly.
FIG. 9 illustrates one embodiment of a vehicle within which systems and methods disclosed herein may be imple- 30 mented.
FIG. 15 9. However, the vehicle 900 can include a different arrange- ment of vehicle systems. It should be appreciated that although particular vehicle systems …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A detection system for identifying anomalies, compris-ing: one or more processors; a memory communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adver-sarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The detection system of claim 1, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The detection system of claim 1, wherein the instruc-tions to determine the presence of the anomaly include instructions to process the sensor data using the discrimi-nator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discrimi-nator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The detection system of claim 1, wherein the discrimi-nator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The detection system of claim 1, wherein the instruc-tions further include instructions to train, prior to determin-ing the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The detection system of claim 1, wherein the instruc-tions to provide the indicator with the sensor data include instructions to perform one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly.
A non-transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The non-transitory computer-readable medium of claim 9, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The non-transitory computer-readable medium of claim 9, wherein the instructions to determine the presence of the anomaly include instructions to process the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the instructions further include instructions to train, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
A method, comprising: acquiring sensor data about a roadway; determining a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generating an indicator for the sensor data according to whether the anomaly is present; and providing the indicator with the sensor data.
The method of claim 14, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The method of claim 14, wherein determining the presence of the anomaly includes processing the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein generating the indicator includes flagging the sensor data to identify a presence of the anomaly.
The method of claim 14, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The method of claim 14, further comprising: training, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The method of claim 14, wherein providing the indicator with the sensor data includes one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
anomaly detection system
No layer stack recorded.
Performance values and ranges asserted in the specification or claims.
| Property | Value | Material |
|---|---|---|
Thickness | 20–40 cm | — |
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 10
Patent
Atlas literature
Patent
US 12,608,953 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates one embodiment of a detection system that is associated with using a discriminator to detect anoma- lies in sensor data.
FIG. 2 illustrates one embodiment of the detection system of
FIG. 3 illustrates one embodiment of a generative neural network.
FIG. 4 illustrates an example of a discriminator network.
FIG. 5 illustrates a flowchart for one embodiment of a method that is associated with training a model to synthesize 20 probe data using a generative …
FIG. 6 is a diagram showing an architecture for training with a GAN.
FIG. 7 illustrates a flowchart for one embodiment of a method associated with identifying anomalies within sensor 25 data.
FIG. 8 illustrates one example of sensor data associated with a roadway that includes an anomaly.
FIG. 9 illustrates one embodiment of a vehicle within which systems and methods disclosed herein may be imple- 30 mented.
FIG. 15 9. However, the vehicle 900 can include a different arrange- ment of vehicle systems. It should be appreciated that although particular vehicle systems …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A detection system for identifying anomalies, compris-ing: one or more processors; a memory communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adver-sarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The detection system of claim 1, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The detection system of claim 1, wherein the instruc-tions to determine the presence of the anomaly include instructions to process the sensor data using the discrimi-nator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discrimi-nator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The detection system of claim 1, wherein the discrimi-nator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The detection system of claim 1, wherein the instruc-tions further include instructions to train, prior to determin-ing the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The detection system of claim 1, wherein the instruc-tions to provide the indicator with the sensor data include instructions to perform one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly.
A non-transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The non-transitory computer-readable medium of claim 9, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The non-transitory computer-readable medium of claim 9, wherein the instructions to determine the presence of the anomaly include instructions to process the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the instructions further include instructions to train, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
A method, comprising: acquiring sensor data about a roadway; determining a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generating an indicator for the sensor data according to whether the anomaly is present; and providing the indicator with the sensor data.
The method of claim 14, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The method of claim 14, wherein determining the presence of the anomaly includes processing the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein generating the indicator includes flagging the sensor data to identify a presence of the anomaly.
The method of claim 14, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The method of claim 14, further comprising: training, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The method of claim 14, wherein providing the indicator with the sensor data includes one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
anomaly detection system
No layer stack recorded.
Performance values and ranges asserted in the specification or claims.
| Property | Value | Material |
|---|---|---|
Thickness | 20–40 cm | — |
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 10
Patent
Atlas literature
Patent
US 12,608,953 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates one embodiment of a detection system that is associated with using a discriminator to detect anoma- lies in sensor data.
FIG. 2 illustrates one embodiment of the detection system of
FIG. 3 illustrates one embodiment of a generative neural network.
FIG. 4 illustrates an example of a discriminator network.
FIG. 5 illustrates a flowchart for one embodiment of a method that is associated with training a model to synthesize 20 probe data using a generative …
FIG. 6 is a diagram showing an architecture for training with a GAN.
FIG. 7 illustrates a flowchart for one embodiment of a method associated with identifying anomalies within sensor 25 data.
FIG. 8 illustrates one example of sensor data associated with a roadway that includes an anomaly.
FIG. 9 illustrates one embodiment of a vehicle within which systems and methods disclosed herein may be imple- 30 mented.
FIG. 15 9. However, the vehicle 900 can include a different arrange- ment of vehicle systems. It should be appreciated that although particular vehicle systems …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A detection system for identifying anomalies, compris-ing: one or more processors; a memory communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adver-sarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The detection system of claim 1, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The detection system of claim 1, wherein the instruc-tions to determine the presence of the anomaly include instructions to process the sensor data using the discrimi-nator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discrimi-nator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The detection system of claim 1, wherein the discrimi-nator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The detection system of claim 1, wherein the instruc-tions further include instructions to train, prior to determin-ing the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The detection system of claim 1, wherein the instruc-tions to provide the indicator with the sensor data include instructions to perform one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly.
A non-transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The non-transitory computer-readable medium of claim 9, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The non-transitory computer-readable medium of claim 9, wherein the instructions to determine the presence of the anomaly include instructions to process the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the instructions further include instructions to train, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
A method, comprising: acquiring sensor data about a roadway; determining a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generating an indicator for the sensor data according to whether the anomaly is present; and providing the indicator with the sensor data.
The method of claim 14, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The method of claim 14, wherein determining the presence of the anomaly includes processing the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein generating the indicator includes flagging the sensor data to identify a presence of the anomaly.
The method of claim 14, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The method of claim 14, further comprising: training, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The method of claim 14, wherein providing the indicator with the sensor data includes one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
anomaly detection system
No layer stack recorded.
Performance values and ranges asserted in the specification or claims.
| Property | Value | Material |
|---|---|---|
Thickness | 20–40 cm | — |
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 10
Patent
Atlas literature
Patent
US 12,608,953 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates one embodiment of a detection system that is associated with using a discriminator to detect anoma- lies in sensor data.
FIG. 2 illustrates one embodiment of the detection system of
FIG. 3 illustrates one embodiment of a generative neural network.
FIG. 4 illustrates an example of a discriminator network.
FIG. 5 illustrates a flowchart for one embodiment of a method that is associated with training a model to synthesize 20 probe data using a generative …
FIG. 6 is a diagram showing an architecture for training with a GAN.
FIG. 7 illustrates a flowchart for one embodiment of a method associated with identifying anomalies within sensor 25 data.
FIG. 8 illustrates one example of sensor data associated with a roadway that includes an anomaly.
FIG. 9 illustrates one embodiment of a vehicle within which systems and methods disclosed herein may be imple- 30 mented.
FIG. 15 9. However, the vehicle 900 can include a different arrange- ment of vehicle systems. It should be appreciated that although particular vehicle systems …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A detection system for identifying anomalies, compris-ing: one or more processors; a memory communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adver-sarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The detection system of claim 1, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The detection system of claim 1, wherein the instruc-tions to determine the presence of the anomaly include instructions to process the sensor data using the discrimi-nator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discrimi-nator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The detection system of claim 1, wherein the discrimi-nator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The detection system of claim 1, wherein the instruc-tions further include instructions to train, prior to determin-ing the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The detection system of claim 1, wherein the instruc-tions to provide the indicator with the sensor data include instructions to perform one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly.
A non-transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to: acquire sensor data about a roadway; determine a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generate an indicator for the sensor data according to whether the anomaly is present; and provide the indicator with the sensor data.
The non-transitory computer-readable medium of claim 9, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The non-transitory computer-readable medium of claim 9, wherein the instructions to determine the presence of the anomaly include instructions to process the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein the instructions to generate the indicator include instructions to flag the sensor data to identify a pres-ence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The non-transitory computer-readable medium of claim 9, wherein the instructions further include instructions to train, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
A method, comprising: acquiring sensor data about a roadway; determining a presence of an anomaly within the sensor data using a discriminator from a generative adversarial network (GAN), wherein the anomaly is an aberration within the sensor data associated with an error in perceiving the roadway; generating an indicator for the sensor data according to whether the anomaly is present; and providing the indicator with the sensor data.
The method of claim 14, wherein the sensor data includes one or more of ortho-graphic images of the roadway, trace data comprised of frames specifying locations and poses of one or more probe vehicles along the roadway, and detections at the frames that are identified aspects of the roadway, including lane boundaries, road boundaries, and road markings.
The method of claim 14, wherein determining the presence of the anomaly includes processing the sensor data using the discriminator to distinguish when the sensor data includes the anomaly by leveraging learned awareness of the discriminator in identifying between real information and synthetic information, and wherein generating the indicator includes flagging the sensor data to identify a presence of the anomaly.
The method of claim 14, wherein the discriminator is a machine-learning model that classifies the sensor data according to a presence of the anomaly.
The method of claim 14, further comprising: training, prior to determining the presence of the anomaly, a probe model of the GAN to synthesize probe data and the discriminator to distinguish between real probe data and synthesized probe data.
The method of claim 14, wherein providing the indicator with the sensor data includes one or more of communicating a request to a set of probe vehicles to acquire additional data about the roadway in an area associated with the anomaly, and generating a map using accumulated data that has been identified as not including the anomaly. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
anomaly detection system
No layer stack recorded.
Performance values and ranges asserted in the specification or claims.
| Property | Value | Material |
|---|---|---|
Thickness | 20–40 cm | — |
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 10