-
公开(公告)号：US20210356968A1
公开(公告)日：2021-11-18
申请号：US17321309
申请日：2021-05-14
Applicant: Perceptive Automata, Inc.
Inventor： Jeffrey D. Zaremba , Till S. Hartmann , Samuel English Anthony
Abstract: A system uses a machine learning based model to determine attributes describing states of mind and behavior of traffic entities in video frames captured by an autonomous vehicle. The system classifies video frames according to traffic scenarios depicted, where each scenario is associated with a filter based on vehicle attributes, traffic attributes, and road attributes. The system identifies a set of video frames associated with ground truth scenarios for validating the accuracy of the machine learning based model and predicts attributes of traffic entities in the video frames. The system analyzes video frames captured after the set of video frames to determine actual attributes of the traffic entities. Based on a comparison of the predicted attributes and actual attributes, the system determines a likelihood of the machine learning based model making accurate predictions and uses the likelihood to generate a navigation action table for controlling the autonomous vehicle.
-
公开(公告)号：US11919545B2
公开(公告)日：2024-03-05
申请号：US17321309
申请日：2021-05-14
Applicant: Perceptive Automata, Inc.
Inventor： Jeffrey D. Zaremba , Till S. Hartmann , Samuel English Anthony
IPC: B60W60/00 , G05D1/00 , G05D1/02 , G06F18/21 , G06F18/2113 , G06F18/214 , G06F18/40 , G06N3/08 , G06N5/04 , G06N20/00 , G06V10/764 , G06V10/82 , G06V20/40 , G06V20/56 , G06V20/58 , G06V40/20
CPC classification number: B60W60/00272 , B60W60/001 , G05D1/0221 , G05D1/0246 , G06F18/2113 , G06F18/214 , G06F18/217 , G06F18/40 , G06N3/08 , G06N5/04 , G06N20/00 , G06V10/764 , G06V10/82 , G06V20/41 , G06V20/56 , G06V20/58 , G06V40/23 , B60W2420/42 , B60W2420/52 , B60W2552/05 , B60W2554/4029 , B60W2554/4041 , B60W2554/4044 , B60W2554/4045 , B60W2554/4046 , B60W2554/408 , B60W2554/801 , G05D2201/0213
Abstract: A system uses a machine learning based model to determine attributes describing states of mind and behavior of traffic entities in video frames captured by an autonomous vehicle. The system classifies video frames according to traffic scenarios depicted, where each scenario is associated with a filter based on vehicle attributes, traffic attributes, and road attributes. The system identifies a set of video frames associated with ground truth scenarios for validating the accuracy of the machine learning based model and predicts attributes of traffic entities in the video frames. The system analyzes video frames captured after the set of video frames to determine actual attributes of the traffic entities. Based on a comparison of the predicted attributes and actual attributes, the system determines a likelihood of the machine learning based model making accurate predictions and uses the likelihood to generate a navigation action table for controlling the autonomous vehicle.
-
公开(公告)号：US11840261B2
公开(公告)日：2023-12-12
申请号：US17321297
申请日：2021-05-14
Applicant: Perceptive Automata, Inc.
Inventor： Till S. Hartmann , Jeffrey D. Zaremba , Samuel English Anthony
IPC: G05D1/02 , G06N20/00 , G06N5/04 , G06N3/08 , G06V20/40 , G06V20/56 , G06F18/40 , G06F18/214 , G06F18/21 , G06F18/2113 , G06V10/764 , G06V10/82 , G06V20/58 , G06V40/20 , B60W60/00
CPC classification number: B60W60/00272 , B60W60/001 , G05D1/0221 , G05D1/0246 , G06F18/214 , G06F18/217 , G06F18/2113 , G06F18/40 , G06N3/08 , G06N5/04 , G06N20/00 , G06V10/764 , G06V10/82 , G06V20/41 , G06V20/56 , G06V20/58 , G06V40/23 , B60W2420/42 , B60W2420/52 , B60W2552/05 , B60W2554/408 , B60W2554/4029 , B60W2554/4041 , B60W2554/4044 , B60W2554/4045 , B60W2554/4046 , B60W2554/801 , G05D2201/0213
Abstract: A system uses a machine learning based model to determine attributes describing states of mind and behavior of traffic entities in video frames captured by an autonomous vehicle. The system classifies video frames according to traffic scenarios depicted, where each scenario is associated with a filter based on vehicle attributes, traffic attributes, and road attributes. The system identifies a set of video frames associated with ground truth scenarios for validating the accuracy of the machine learning based model and predicts attributes of traffic entities in the video frames. The system analyzes video frames captured after the set of video frames to determine actual attributes of the traffic entities. Based on a comparison of the predicted attributes and actual attributes, the system determines a likelihood of the machine learning based model making accurate predictions and uses the likelihood to generate a navigation action table for controlling the autonomous vehicle.
-
公开(公告)号：US20210357662A1
公开(公告)日：2021-11-18
申请号：US17321297
申请日：2021-05-14
Applicant: Perceptive Automata, Inc.
Inventor： Till S. Hartmann , Jeffrey D. Zaremba , Samuel English Anthony
Abstract: A system uses a machine learning based model to determine attributes describing states of mind and behavior of traffic entities in video frames captured by an autonomous vehicle. The system classifies video frames according to traffic scenarios depicted, where each scenario is associated with a filter based on vehicle attributes, traffic attributes, and road attributes. The system identifies a set of video frames associated with ground truth scenarios for validating the accuracy of the machine learning based model and predicts attributes of traffic entities in the video frames. The system analyzes video frames captured after the set of video frames to determine actual attributes of the traffic entities. Based on a comparison of the predicted attributes and actual attributes, the system determines a likelihood of the machine learning based model making accurate predictions and uses the likelihood to generate a navigation action table for controlling the autonomous vehicle.
-
-
-
Search Results
4
records
(took 0.011 seconds)
