-
公开(公告)号:US11941519B2
公开(公告)日:2024-03-26
申请号:US16699920
申请日:2019-12-02
Applicant: Waymo LLC
Inventor: Pok Man Chu , Edward Hsiao
Abstract: Aspects of the disclosure relate to training a machine learning model on a distributed computing system. The model can be trained using selected processors of the training platform. The distributed system automatically modifies the model for instantiation on each processor, adjusts an input pipeline to accommodate the capabilities of selected processors, and coordinates the training between those processors. Simultaneous processing at each stage can be scaled to reduce or eliminate bottlenecks in the distributed system. In addition, autonomous monitoring and re-allocating of resources can further reduce or eliminate bottlenecks. The training results may be aggregated by the distributed system, and a final model may then be transmitted to a user device.
-
公开(公告)号:US11783596B2
公开(公告)日:2023-10-10
申请号:US17738339
申请日:2022-05-06
Applicant: Waymo LLC
Inventor: Edward Hsiao , Yu Ouyang , Maoqing Yao
CPC classification number: G06V20/584 , G06N3/045 , G06N3/049 , G06T7/75 , G06V10/56 , G06V20/588 , G06T2207/20084 , G06T2207/20132
Abstract: Machine-learning models are described detecting the signaling state of a traffic signaling unit. A system can obtain an image of the traffic signaling unit, and select a model of the traffic signaling unit that identifies a position of each traffic lighting element on the unit. First and second neural network inputs are processed with a neural network to generate an estimated signaling state of the traffic signaling unit. The first neural network input can represent the image of the traffic signaling unit, and the second neural network input can represent the model of the traffic signaling unit. Using the estimated signaling state of the traffic signaling unit, the system can inform a driving decision of a vehicle.
-
公开(公告)号:US20240092392A1
公开(公告)日:2024-03-21
申请号:US18522528
申请日:2023-11-29
Applicant: WAYMO LLC
Inventor: David Silver , Carl Kershaw , Jonathan Hsiao , Edward Hsiao
CPC classification number: B60W60/0015 , B60W60/0025 , G06F18/24 , G06V20/584 , G06V40/10 , G08G1/095 , B60W2554/4029 , B60W2554/408
Abstract: Aspects of the disclosure relate to detecting and responding to malfunctioning traffic signals for a vehicle having an autonomous driving mode. For instance, information identifying a detected state of a traffic signal for an intersection. An anomaly for the traffic signal may be detected based on the detected state and prestored information about expected states of the traffic signal. The vehicle may be controlled in the autonomous driving mode based on the detected anomaly.
-
公开(公告)号:US20240075959A1
公开(公告)日:2024-03-07
申请号:US18504729
申请日:2023-11-08
Applicant: Waymo LLC
Inventor: Edward Hsiao , Maoqing Yao , David Margines , Yosuke Higashi
CPC classification number: B60W60/0025 , G05D1/0088 , G08G1/095 , B60W2552/00
Abstract: Aspects of the disclosure relate to controlling a vehicle having an autonomous driving mode. For instance, a current state of a traffic light may be determined. One of a plurality of yellow light durations may be selected based on the current state of the traffic light. When the traffic light will turn red may be predicted based on the selected one. The prediction may be used to control the vehicle in the autonomous driving mode.
-
公开(公告)号:US20210343150A1
公开(公告)日:2021-11-04
申请号:US17336856
申请日:2021-06-02
Applicant: Waymo LLC
Inventor: Maxim Krivokon , Abhijit S. Ogale , Edward Hsiao , Andreas Wendel
Abstract: Methods and system are provided for training and using a model to determine states of lanes of interest. For instance, image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light are received and used to train the model such that the model is configured to, in response to receiving an image and a lane of interest included in the image, output a lane state for the lane of interest. This model is then used by a vehicle in order to determine a state of a lane of interest. This state is then used to control the vehicle in an autonomous driving mode based on the state of the lane of interest.
-
公开(公告)号:US11056005B2
公开(公告)日:2021-07-06
申请号:US16169080
申请日:2018-10-24
Applicant: Waymo LLC
Inventor: Maxim Krivokon , Abhijit S. Ogale , Edward Hsiao , Andreas Wendel
Abstract: Methods and system are provided for training and using a model to determine states of lanes of interest. For instance, image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light are received and used to train the model such that the model is configured to, in response to receiving an image and a lane of interest included in the image, output a lane state for the lane of interest. This model is then used by a vehicle in order to determine a state of a lane of interest. This state is then used to control the vehicle in an autonomous driving mode based on the state of the lane of interest.
-
公开(公告)号:US20220335731A1
公开(公告)日:2022-10-20
申请号:US17738339
申请日:2022-05-06
Applicant: Waymo LLC
Inventor: Edward Hsiao , Yu Ouyang , Maoqing Yao
Abstract: Machine-learning models are described detecting the signaling state of a traffic signaling unit. A system can obtain an image of the traffic signaling unit, and select a model of the traffic signaling unit that identifies a position of each traffic lighting element on the unit. First and second neural network inputs are processed with a neural network to generate an estimated signaling state of the traffic signaling unit. The first neural network input can represent the image of the traffic signaling unit, and the second neural network input can represent the model of the traffic signaling unit. Using the estimated signaling state of the traffic signaling unit, the system can inform a driving decision of a vehicle.
-
公开(公告)号:US20220027645A1
公开(公告)日:2022-01-27
申请号:US16936739
申请日:2020-07-23
Applicant: Waymo LLC
Inventor: Edward Hsiao , Yu Ouyang , Maoqing Yao
Abstract: Machine-learning models are described detecting the signaling state of a traffic signaling unit. A system can obtain an image of the traffic signaling unit, and select a model of the traffic signaling unit that identifies a position of each traffic lighting element on the unit. First and second neural network inputs are processed with a neural network to generate an estimated signaling state of the traffic signaling unit. The first neural network input can represent the image of the traffic signaling unit, and the second neural network input can represent the model of the traffic signaling unit. Using the estimated signaling state of the traffic signaling unit, the system can inform a driving decision of a vehicle.
-
公开(公告)号:US20210397827A1
公开(公告)日:2021-12-23
申请号:US16906594
申请日:2020-06-19
Applicant: Waymo LLC
Inventor: David Silver , Carl Kershaw , Jonathan Hsiao , Edward Hsiao
Abstract: Aspects of the disclosure relate to detecting and responding to malfunctioning traffic signals for a vehicle having an autonomous driving mode. For instance, information identifying a detected state of a traffic signal for an intersection. An anomaly for the traffic signal may be detected based on the detected state and prestored information about expected states of the traffic signal. The vehicle may be controlled in the autonomous driving mode based on the detected anomaly.
-
公开(公告)号:US20210166117A1
公开(公告)日:2021-06-03
申请号:US16699920
申请日:2019-12-02
Applicant: Waymo LLC
Inventor: Pok Man Chu , Edward Hsiao
Abstract: Aspects of the disclosure relate to training a machine learning model on a distributed computing system. The model can be trained using selected processors of the training platform. The distributed system automatically modifies the model for instantiation on each processor, adjusts an input pipeline to accommodate the capabilities of selected processors, and coordinates the training between those processors. Simultaneous processing at each stage can be scaled to reduce or eliminate bottlenecks in the distributed system. In addition, autonomous monitoring and re-allocating of resources can further reduce or eliminate bottlenecks. The training results may be aggregated by the distributed system, and a final model may then be transmitted to a user device.
-
-
-
-
-
-
-
-
-