AUTONOMOUS VEHICLE TRAJECTORY PLANNING USING NEURAL NETWORK TRAINED BASED ON KNOWLEDGE DISTILLATION

    公开(公告)号:US20250026368A1

    公开(公告)日:2025-01-23

    申请号:US18531510

    申请日:2023-12-06

    Abstract: An electronic device and a method for AV trajectory planning using neural networks trained based on knowledge distillation is provided. A set of updated values of a set of variables of an objective function for trajectory planning of an ego AV are determined. A first prediction network is applied on an updated value of the set of updated values, a states of the ego AV and a set of AVs over a past time interval. Based on the application, an output is determined. The output includes states of the ego AV and set of AVs over a future time interval. The electronic device determines a set of optimal values based on the updated value and the determined output satisfying a safety constraint associated with the objective function. Further, the electronic device controls a trajectory of the ego AV based on the set of optimal values of the set of variables.

    System and method for providing support to user of autonomous vehicle (AV) based on sentiment analysis

    公开(公告)号:US12206822B2

    公开(公告)日:2025-01-21

    申请号:US17859725

    申请日:2022-07-07

    Abstract: Assistance can be provided to users of AVs based on user sentiments. A system may receive a request for assistance from a user of an AV (e.g., a passenger of the AV). The system may also receive sensor data that is captured by a sensor suite of the AV from detecting the user, the AV, or another object. The system determines a sentiment of the user based on the sensor data. The system may input the sensor data into a machine learning model and the model outputs information indicating the user's sentiment. The system can determine who, when, or how to service the user's request based on the user's sentiment. The system may assign the user's request to an agent who can provide the assistance. The system can further provide guidance (e.g., suggested content of a conversation with the user) to the agent based on the user's sentiment.

    Information processing apparatus, moving apparatus, method and program

    公开(公告)号:US12202528B2

    公开(公告)日:2025-01-21

    申请号:US17420126

    申请日:2019-12-25

    Abstract: A configuration that decides whether or not a driver has alertness sufficient for manual driving by analyzing eye behaviors of the driver trying to solve a problem displayed on the display section is realized. It is made possible to decide whether or not the driver of a moving apparatus that can be driven in a driving mode that can be switched to automated driving and manual driving has alertness sufficient to return to manual driving on the basis of eye behaviors of the driver. An eye-behavior analyzing section that analyzes an eye behavior of the driver who observes a problem displayed on a display section and an alertness deciding section that decides alertness of the driver on the basis of a result of the analysis by the eye-behavior analyzing section are included. The alertness deciding section analyzes whether or not the driver executes an eye behavior such as a fixation or a microsaccade for solving the problem, and decides whether or not the driver has alertness sufficient to return to manual driving.

    Vehicle control system and vehicle control method

    公开(公告)号:US12202526B2

    公开(公告)日:2025-01-21

    申请号:US17684857

    申请日:2022-03-02

    Abstract: A processor of a vehicle determines whether remote assistance from a remote facility is necessary during autonomous driving control. When determination is made that the remote assistance is necessary, the processor generates a target trajectory of the vehicle that includes an expected waiting position. The expected waiting position is a position where the vehicle is expected to wait for reception of an assistance signal from the remote facility. The processor calculates a traveling efficiency level indicating a level of traveling efficiency required in the vehicle, and calculates, based on the traveling efficiency level, a request timing to transmit a request signal for the remote assistance to the remote facility. When the traveling efficiency level is low in calculation of the request timing, the processor outputs a late timing.

    Movement control system, movement control method, non-transitory computer-readable storage medium storing control program, and control device

    公开(公告)号:US12202525B2

    公开(公告)日:2025-01-21

    申请号:US17678464

    申请日:2022-02-23

    Abstract: A movement control system includes: a moving object; a first control device capable of communicating with the moving object; and a second control device configured to relay the communication between the moving object and the first control device. When communication between the first control device and the second control device is not restricted, the first control device performs first automatic movement control on the moving object via the second control device, and when the communication between the first control device and the second control device is restricted, the second control device performs second automatic movement control on the moving object. The first automatic movement control has fewer tasks assigned to a user of the moving object than the second automatic movement control.

    System and method for connected vehicle risk detection

    公开(公告)号:US12202517B2

    公开(公告)日:2025-01-21

    申请号:US17060910

    申请日:2020-10-01

    Abstract: A system and method for connected vehicle risk detection are presented. The includes computing risk scores for a plurality of behaviors detected with respect to a connected vehicle, wherein each of the detected plurality of behaviors is associated with the connected vehicle based on a contextual vehicle state of the connected vehicle; aggregating the computed risk scores to determine an aggregated risk score; determining a risk level for the connected vehicle based on the aggregated risk score; and causing execution of at least one mitigation action based on the determined risk level.

Patent Agency Ranking