Patent
US 12,066,518 B2GAN-BASED DATA SYNTHESIS FOR SEMI-SUPERVISED LEARNING OF A RADAR SENSOR
Matthew Paul Harrison
BDCM A2 LLC, Dover, DE (US)·Aug. 20, 2024·US
Copyright © 2026 Matter42. All rights reserved.
Patent
Atlas literature
Patent
US 12,066,518 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example environment in which a beam steering radar in an autonomous vehicle is used to detect and identify objects, according to various …
FIG. 2 illustrates an example network environment in 60 which a radar system may be implemented in accordance with one or more implementations of the subject …
FIG. 3 is a schematic diagram of a beam steering radar system as in
FIG. 4 is a schematic diagram of a multi-sensor fusion platform in accordance with various examples: B₂
FIG. 5 illustrates an example range-doppler map captured by a beam steering radar system as in
FIG. 6 is a schematic diagram illustrating various sensors and their perception engine networks in accordance with one or more implementations:
FIG. 7 is a schematic diagram illustrating a system for training a second beam steering radar from a first beam steering radar in accordance with one or more …
FIG. 8 is a flowchart for a GAN-based data synthesis for semi-supervised learning of a radar sensor in accordance with one or more implementations of the …
FIG. 9 is a flowchart for a method for semi-supervised training of a radar system in accordance with various implementations of the subject technology: and
FIG. 10 conceptually illustrates an electronic system with which one or more embodiments of the subject technology may be implemented.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method for semi-supervised training of a radar system, comprising: training a first radar network of the radar system with a first set of radar object detection labels corresponding to a first set of radar data; training a generative adversarial network (GAN) with the trained first radar network; synthesizing a training data set for a second radar network of the radar system with the trained GAN; training the second radar network with the synthesized training data set; and generating a second set of radar object detection labels based on the training of the second radar network.
The method of claim 1, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The method of claim 1, further comprising: training one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The method of claim 1, wherein the synthesized train-ing data set comprises a data set and corresponding labels that are generated during an inference from the first set of radar data and the first set of radar object detection labels.
The method of claim 1, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar system.
The method of claim 1, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A system for training a radar, comprising: 35 a first radar network that provides a first set of radar object detection labels corresponding to a first set of radar data; a generative adversarial network (GAN) module trained with the first radar network; 40 a second radar network; and the GAN module configured to train the second radar network using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The system of claim 9, wherein the GAN module comprises a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar.
The system of claim 9, wherein the GAN module is configured to synthesize a training set for the second radar network of the radar using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A non-transitory computer readable medium compris-ing computer executable instructions stored thereon to cause one or more processing units to: train a first radar network of a radar system with a first set of radar object detection labels corresponding to a first set of radar data; train a generative adversarial network (GAN) with the trained first radar network; synthesize a training data set for a second radar network of the radar system with the trained GAN; train the second radar network with the synthesized training data set; and generate a second set of radar object detection labels based on the training of the second radar network.
The non-transitory computer readable medium of claim 16, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The non-transitory computer readable medium of claim 16, wherein the instructions further cause the one or more processing units to: train one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The non-transitory computer readable medium of claim 16, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the GAN comprises a combination of a generative network and a discriminative network, wherein the generative network is configured for generating new data instances based on the first set of radar data and the discriminative network is configured to distinguish the new data instances from the fake data.
The non-transitory computer readable medium of claim 16, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of param-eters or a scan pattern, and wherein the training of the second radar network by the GAN is performed prior to deployment of the second beam steering radar. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
first beam steering radar network
No layer stack recorded.
second beam steering radar network
No layer stack recorded.
generative adversarial network (GAN) module
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 4
Patent
Atlas literature
Patent
US 12,066,518 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example environment in which a beam steering radar in an autonomous vehicle is used to detect and identify objects, according to various …
FIG. 2 illustrates an example network environment in 60 which a radar system may be implemented in accordance with one or more implementations of the subject …
FIG. 3 is a schematic diagram of a beam steering radar system as in
FIG. 4 is a schematic diagram of a multi-sensor fusion platform in accordance with various examples: B₂
FIG. 5 illustrates an example range-doppler map captured by a beam steering radar system as in
FIG. 6 is a schematic diagram illustrating various sensors and their perception engine networks in accordance with one or more implementations:
FIG. 7 is a schematic diagram illustrating a system for training a second beam steering radar from a first beam steering radar in accordance with one or more …
FIG. 8 is a flowchart for a GAN-based data synthesis for semi-supervised learning of a radar sensor in accordance with one or more implementations of the …
FIG. 9 is a flowchart for a method for semi-supervised training of a radar system in accordance with various implementations of the subject technology: and
FIG. 10 conceptually illustrates an electronic system with which one or more embodiments of the subject technology may be implemented.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method for semi-supervised training of a radar system, comprising: training a first radar network of the radar system with a first set of radar object detection labels corresponding to a first set of radar data; training a generative adversarial network (GAN) with the trained first radar network; synthesizing a training data set for a second radar network of the radar system with the trained GAN; training the second radar network with the synthesized training data set; and generating a second set of radar object detection labels based on the training of the second radar network.
The method of claim 1, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The method of claim 1, further comprising: training one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The method of claim 1, wherein the synthesized train-ing data set comprises a data set and corresponding labels that are generated during an inference from the first set of radar data and the first set of radar object detection labels.
The method of claim 1, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar system.
The method of claim 1, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A system for training a radar, comprising: 35 a first radar network that provides a first set of radar object detection labels corresponding to a first set of radar data; a generative adversarial network (GAN) module trained with the first radar network; 40 a second radar network; and the GAN module configured to train the second radar network using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The system of claim 9, wherein the GAN module comprises a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar.
The system of claim 9, wherein the GAN module is configured to synthesize a training set for the second radar network of the radar using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A non-transitory computer readable medium compris-ing computer executable instructions stored thereon to cause one or more processing units to: train a first radar network of a radar system with a first set of radar object detection labels corresponding to a first set of radar data; train a generative adversarial network (GAN) with the trained first radar network; synthesize a training data set for a second radar network of the radar system with the trained GAN; train the second radar network with the synthesized training data set; and generate a second set of radar object detection labels based on the training of the second radar network.
The non-transitory computer readable medium of claim 16, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The non-transitory computer readable medium of claim 16, wherein the instructions further cause the one or more processing units to: train one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The non-transitory computer readable medium of claim 16, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the GAN comprises a combination of a generative network and a discriminative network, wherein the generative network is configured for generating new data instances based on the first set of radar data and the discriminative network is configured to distinguish the new data instances from the fake data.
The non-transitory computer readable medium of claim 16, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of param-eters or a scan pattern, and wherein the training of the second radar network by the GAN is performed prior to deployment of the second beam steering radar. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
first beam steering radar network
No layer stack recorded.
second beam steering radar network
No layer stack recorded.
generative adversarial network (GAN) module
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 4
Patent
Atlas literature
Patent
US 12,066,518 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example environment in which a beam steering radar in an autonomous vehicle is used to detect and identify objects, according to various …
FIG. 2 illustrates an example network environment in 60 which a radar system may be implemented in accordance with one or more implementations of the subject …
FIG. 3 is a schematic diagram of a beam steering radar system as in
FIG. 4 is a schematic diagram of a multi-sensor fusion platform in accordance with various examples: B₂
FIG. 5 illustrates an example range-doppler map captured by a beam steering radar system as in
FIG. 6 is a schematic diagram illustrating various sensors and their perception engine networks in accordance with one or more implementations:
FIG. 7 is a schematic diagram illustrating a system for training a second beam steering radar from a first beam steering radar in accordance with one or more …
FIG. 8 is a flowchart for a GAN-based data synthesis for semi-supervised learning of a radar sensor in accordance with one or more implementations of the …
FIG. 9 is a flowchart for a method for semi-supervised training of a radar system in accordance with various implementations of the subject technology: and
FIG. 10 conceptually illustrates an electronic system with which one or more embodiments of the subject technology may be implemented.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method for semi-supervised training of a radar system, comprising: training a first radar network of the radar system with a first set of radar object detection labels corresponding to a first set of radar data; training a generative adversarial network (GAN) with the trained first radar network; synthesizing a training data set for a second radar network of the radar system with the trained GAN; training the second radar network with the synthesized training data set; and generating a second set of radar object detection labels based on the training of the second radar network.
The method of claim 1, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The method of claim 1, further comprising: training one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The method of claim 1, wherein the synthesized train-ing data set comprises a data set and corresponding labels that are generated during an inference from the first set of radar data and the first set of radar object detection labels.
The method of claim 1, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar system.
The method of claim 1, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A system for training a radar, comprising: 35 a first radar network that provides a first set of radar object detection labels corresponding to a first set of radar data; a generative adversarial network (GAN) module trained with the first radar network; 40 a second radar network; and the GAN module configured to train the second radar network using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The system of claim 9, wherein the GAN module comprises a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar.
The system of claim 9, wherein the GAN module is configured to synthesize a training set for the second radar network of the radar using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A non-transitory computer readable medium compris-ing computer executable instructions stored thereon to cause one or more processing units to: train a first radar network of a radar system with a first set of radar object detection labels corresponding to a first set of radar data; train a generative adversarial network (GAN) with the trained first radar network; synthesize a training data set for a second radar network of the radar system with the trained GAN; train the second radar network with the synthesized training data set; and generate a second set of radar object detection labels based on the training of the second radar network.
The non-transitory computer readable medium of claim 16, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The non-transitory computer readable medium of claim 16, wherein the instructions further cause the one or more processing units to: train one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The non-transitory computer readable medium of claim 16, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the GAN comprises a combination of a generative network and a discriminative network, wherein the generative network is configured for generating new data instances based on the first set of radar data and the discriminative network is configured to distinguish the new data instances from the fake data.
The non-transitory computer readable medium of claim 16, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of param-eters or a scan pattern, and wherein the training of the second radar network by the GAN is performed prior to deployment of the second beam steering radar. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
first beam steering radar network
No layer stack recorded.
second beam steering radar network
No layer stack recorded.
generative adversarial network (GAN) module
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 4
Patent
Atlas literature
Patent
US 12,066,518 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example environment in which a beam steering radar in an autonomous vehicle is used to detect and identify objects, according to various …
FIG. 2 illustrates an example network environment in 60 which a radar system may be implemented in accordance with one or more implementations of the subject …
FIG. 3 is a schematic diagram of a beam steering radar system as in
FIG. 4 is a schematic diagram of a multi-sensor fusion platform in accordance with various examples: B₂
FIG. 5 illustrates an example range-doppler map captured by a beam steering radar system as in
FIG. 6 is a schematic diagram illustrating various sensors and their perception engine networks in accordance with one or more implementations:
FIG. 7 is a schematic diagram illustrating a system for training a second beam steering radar from a first beam steering radar in accordance with one or more …
FIG. 8 is a flowchart for a GAN-based data synthesis for semi-supervised learning of a radar sensor in accordance with one or more implementations of the …
FIG. 9 is a flowchart for a method for semi-supervised training of a radar system in accordance with various implementations of the subject technology: and
FIG. 10 conceptually illustrates an electronic system with which one or more embodiments of the subject technology may be implemented.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method for semi-supervised training of a radar system, comprising: training a first radar network of the radar system with a first set of radar object detection labels corresponding to a first set of radar data; training a generative adversarial network (GAN) with the trained first radar network; synthesizing a training data set for a second radar network of the radar system with the trained GAN; training the second radar network with the synthesized training data set; and generating a second set of radar object detection labels based on the training of the second radar network.
The method of claim 1, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The method of claim 1, further comprising: training one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The method of claim 1, wherein the synthesized train-ing data set comprises a data set and corresponding labels that are generated during an inference from the first set of radar data and the first set of radar object detection labels.
The method of claim 1, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar system.
The method of claim 1, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A system for training a radar, comprising: 35 a first radar network that provides a first set of radar object detection labels corresponding to a first set of radar data; a generative adversarial network (GAN) module trained with the first radar network; 40 a second radar network; and the GAN module configured to train the second radar network using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The system of claim 9, wherein the GAN module comprises a neural network configured to distinguish real data from fake data, wherein the real data comprises the first set of radar data obtained during actual driving conditions acquired via one or more of lidar or camera sensors of the radar.
The system of claim 9, wherein the GAN module is configured to synthesize a training set for the second radar network of the radar using the first set of radar object detection labels and the first set of radar data.
The system of claim 9, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of parameters or a scan pattern.
A non-transitory computer readable medium compris-ing computer executable instructions stored thereon to cause one or more processing units to: train a first radar network of a radar system with a first set of radar object detection labels corresponding to a first set of radar data; train a generative adversarial network (GAN) with the trained first radar network; synthesize a training data set for a second radar network of the radar system with the trained GAN; train the second radar network with the synthesized training data set; and generate a second set of radar object detection labels based on the training of the second radar network.
The non-transitory computer readable medium of claim 16, wherein the first set of radar data is acquired via one or more of lidar or camera sensors of the radar system during an actual driving condition that occurs on a plurality of roads at various times with various weather patterns for one or more days.
The non-transitory computer readable medium of claim 16, wherein the instructions further cause the one or more processing units to: train one or more of lidar or camera sensors on actual driving conditions, wherein the training of the one or more of lidar or camera sensors occurs during the training of the first radar network of the radar system.
The non-transitory computer readable medium of claim 16, wherein the GAN is a neural network configured to distinguish real data from fake data, wherein the GAN comprises a combination of a generative network and a discriminative network, wherein the generative network is configured for generating new data instances based on the first set of radar data and the discriminative network is configured to distinguish the new data instances from the fake data.
The non-transitory computer readable medium of claim 16, wherein the first radar network comprises a first beam steering radar and the second radar network comprises a second beam steering radar, wherein the first beam steering radar and the second beam steering radar have different characteristics in at least one of a configuration of param-eters or a scan pattern, and wherein the training of the second radar network by the GAN is performed prior to deployment of the second beam steering radar. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
first beam steering radar network
No layer stack recorded.
second beam steering radar network
No layer stack recorded.
generative adversarial network (GAN) module
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 4