公开(公告)号：US20230347931A1

公开(公告)日：2023-11-02

申请号：US18308626

申请日：2023-04-27

Applicant: Perceptive Automata, Inc.

Inventor： Jeffrey Donald Zaremba ,  Chuan Yen Ian Goh ,  Omar Al Assad ,  Till S. Hartman ,  Sonia Poltoraski ,  Samuel English Anthony

IPC: B60W60/00 ,  G06V20/56 ,  B60W40/04

CPC classification number: B60W60/001 ,  G06V20/56 ,  B60W40/04 ,  B60W2420/42 ,  B60W2554/4041

Abstract: A system evaluates modifications to components of an autonomous vehicle (AV) stack. The system receives driving recommendations traffic scenarios based on user annotations of video frames showing each traffic scenario. For each traffic scenario, the system predicts driving recommendations based on the AV stack. The system determines a measure of quality of driving recommendation by comparing predicted driving recommendations based on the AV stack with the driving recommendations received for the traffic scenario. The measure of quality of driving recommendation is used for evaluating components of the AV stack. The system determines a driving recommendation for an AV corresponding to ranges of SOMAI (state of mind) score and sends signals to controls of the autonomous vehicle to navigate the autonomous vehicle according to the driving recommendation. The system identifies additional training data for training machine learning model based on the measure of driving quality.

公开(公告)号：US20230351772A1

公开(公告)日：2023-11-02

申请号：US18308622

申请日：2023-04-27

Applicant: Perceptive Automata, Inc.

Inventor： Sonia Poltoraski ,  Till S. Hartman ,  Jeffrey Donald Zaremba ,  Samuel English Anthony ,  Chuan Yen Ian Goh ,  Omar Al Assad

IPC: G06V20/58 ,  B60W60/00 ,  G06V10/774 ,  G06V20/40

CPC classification number: G06V20/58 ,  B60W60/0027 ,  G06V10/774 ,  G06V20/40 ,  B60W2420/42 ,  G06V10/82

Abstract: A system evaluates modifications to components of an autonomous vehicle (AV) stack. The system receives driving recommendations traffic scenarios based on user annotations of video frames showing each traffic scenario. For each traffic scenario, the system predicts driving recommendations based on the AV stack. The system determines a measure of quality of driving recommendation by comparing predicted driving recommendations based on the AV stack with the driving recommendations received for the traffic scenario. The measure of quality of driving recommendation is used for evaluating components of the AV stack. The system determines a driving recommendation for an AV corresponding to ranges of SOMAI (state of mind) score and sends signals to controls of the autonomous vehicle to navigate the autonomous vehicle according to the driving recommendation. The system identifies additional training data for training machine learning model based on the measure of driving quality.

公开(公告)号：US20230347932A1

公开(公告)日：2023-11-02

申请号：US18308634

申请日：2023-04-27

Applicant: Perceptive Automata, Inc.

Inventor： Jeffrey Donald Zaremba ,  Chuan Yen Ian Goh ,  Omar Al Assad ,  Till S. Hartman ,  Sonia Poltoraski ,  Samuel English Anthony ,  James Gowers

IPC: B60W60/00 ,  G05B13/02 ,  G08G1/01 ,  B60W40/06 ,  B60W40/12

CPC classification number: B60W60/001 ,  G05B13/0265 ,  G08G1/0125 ,  B60W40/06 ,  B60W40/12 ,  B60W2552/00

Abstract: A system evaluates modifications to components of an autonomous vehicle (AV) stack. The system receives driving recommendations traffic scenarios based on user annotations of video frames showing each traffic scenario. For each traffic scenario, the system predicts driving recommendations based on the AV stack. The system determines a measure of quality of driving recommendation by comparing predicted driving recommendations based on the AV stack with the driving recommendations received for the traffic scenario. The measure of quality of driving recommendation is used for evaluating components of the AV stack. The system determines a driving recommendation for an AV corresponding to ranges of SOMAI (state of mind) score and sends signals to controls of the autonomous vehicle to navigate the autonomous vehicle according to the driving recommendation. The system identifies additional training data for training machine learning model based on the measure of driving quality.