Systems and methods for detecting and dynamically mitigating driver fatigue

    公开(公告)号:US11491994B2

    公开(公告)日:2022-11-08

    申请号:US17024998

    申请日:2020-09-18

    Applicant: Waymo LLC

    Abstract: This technology relates to dynamically detecting, managing and mitigating driver fatigue in autonomous systems. For instance, interactions of a driver in a vehicle may be monitored to determine a distance or time when primary tasks associated with operation of the vehicle or secondary tasks issued by the vehicle computing were last performed. If primary tasks or secondary tasks are not performed within given distance thresholds or time limits, then one or more secondary tasks are initiated by the computing device of the vehicle. In another instance, potential driver fatigue, driver distraction or overreliance on an automated driving system is detected based on gaze direction or pattern of a driver. For example, a detected gaze direction or pattern may be compared to an expected gaze direction or pattern given the surrounding environment in a vicinity of the vehicle.

    Systems And Methods For Detecting And Dynamically Mitigating Driver Fatigue

    公开(公告)号:US20210001865A1

    公开(公告)日:2021-01-07

    申请号:US17025048

    申请日:2020-09-18

    Applicant: Waymo LLC

    Abstract: This technology relates to dynamically detecting, managing and mitigating driver fatigue in autonomous systems. For instance, interactions of a driver in a vehicle may be monitored to determine a distance or time when primary tasks associated with operation of the vehicle or secondary tasks issued by the vehicle computing were last performed. If primary tasks or secondary tasks are not performed within given distance thresholds or time limits, then one or more secondary tasks are initiated by the computing device of the vehicle. In another instance, potential driver fatigue, driver distraction or overreliance on an automated driving system is detected based on gaze direction or pattern of a driver. For example, a detected gaze direction or pattern may be compared to an expected gaze direction or pattern given the surrounding environment in a vicinity of the vehicle

    ASSESSING SURPRISE FOR AUTONOMOUS VEHICLES
    13.
    发明公开

    公开(公告)号:US20240308551A1

    公开(公告)日:2024-09-19

    申请号:US18672812

    申请日:2024-05-23

    Applicant: Waymo LLC

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a backward looking surprise metric for autonomously driven vehicles. One of the methods includes obtaining first data representing one or more previously predicted states of an agent along one or more predicted trajectories of the agent at a first time step. Second data representing one or more states of the agent at a subsequent time step is obtained. A surprise score is computed from a measure of a difference between the first data computed for the one or more predicted trajectories for the prior time step and the second data computed for the one or more predicted states for the subsequent time step.

    Probabilistic simulation sampling from agent data

    公开(公告)号:US11834070B2

    公开(公告)日:2023-12-05

    申请号:US17370924

    申请日:2021-07-08

    Applicant: Waymo LLC

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining the likelihood that a particular event would occur during a navigation interaction using simulations generated by sampling from agent data. In one aspect, a method comprises: identifying an instance of a navigation interaction that includes an autonomous vehicle and agents navigating in an environment; generating multiple simulated interactions corresponding to the instance, comprising, for each simulated interaction: identifying one or more agents; for each identified agent and for each property that characterizes behavior of the identified agent, obtaining a probability distribution for the property; sampling a respective value from each of the probability distributions; and simulating the navigation interaction in accordance with the sampled values; and determining a likelihood that the particular event would occur during the navigation interaction based on whether the particular event occurred during each of the simulated interactions.

Patent Agency Ranking