SYSTEMS AND METHODS FOR PROVIDING DRIVING RECOMMENDATIONS

    公开(公告)号:US20210150899A1

    公开(公告)日:2021-05-20

    申请号:US16689255

    申请日:2019-11-20

    摘要: Systems and methods for providing driving recommendations are disclosed herein. One embodiment receives, at an ego vehicle, first vehicle data and first encoded information from one or more other vehicles; constructs, from the first vehicle data, graph data representing how the ego vehicle and the one or more other vehicles are spatially related; inputs the graph data, the first vehicle data, second vehicle data pertaining to the ego vehicle, and the first encoded information to a graph convolutional network that outputs second encoded information; inputs the second encoded information and previously stored encoded information to a recurrent neural network that outputs a set of parameters to a mixture model; predicts acceleration of the one or more other vehicles using the mixture model; and generates a driving recommendation for the ego vehicle based, at least in part, on the predicted acceleration of the one or more other vehicles.

    COOPERATIVE TRAFFIC CONGESTION DETECTION FOR CONNECTED VEHICULAR PLATFORM

    公开(公告)号:US20230230471A1

    公开(公告)日:2023-07-20

    申请号:US17576082

    申请日:2022-01-14

    IPC分类号: G08G1/01 G08G1/0965 B60W60/00

    摘要: Systems and methods are provided to implement cooperative traffic congestion detection, and enhance the accuracy of detection of traffic congestion for enhanced routing and maneuvering vehicles along a travel route. A vehicle is configured to receive vehicle data from an ad-hoc network of a plurality of vehicles that are communicatively connected (and proximately located). A subset of the plurality of vehicles can be sensor-rich vehicles that are equipped with ranging sensors (e.g., cameras, LIDAR, radar, ultrasonic sensors), which enables real-time detection of the multiple traffic parameters, such as the presence of other vehicles, vehicle speed, vehicle movement, traffic, and the like, within the vicinity along the route. The vehicle employs cooperative traffic congestion detection, and fuses data from the plurality of vehicles, including sensor-rich vehicles and legacy vehicles, and applies a learning-based algorithm, such as a machine-learning (ML) algorithm, to generate a real-time and more accurate estimate of traffic congestion.

    SYSTEMS AND METHODS FOR MATCHING OBJECTS IN COLLABORATIVE PERCEPTION MESSAGES

    公开(公告)号:US20230110132A1

    公开(公告)日:2023-04-13

    申请号:US17498201

    申请日:2021-10-11

    IPC分类号: H04W4/46 H04W4/12

    摘要: A method of matching objects in collaborative perception messages is provided. The method includes obtaining a first collaborative perception message (CPM) message from a first node, obtaining a second CPM from a second node, calculating an adaptive threshold based on uncertainty of the first CPM and uncertainty of the second CPM, calculating scores for pairs of objects, each of the pairs of objects including one object in the first CPM and one object in the second CPM, filtering out one or more pairs whose score is greater than the adaptive threshold to obtain a filtered matrix; and implementing a fusion algorithm on the filtered matrix to obtain correspondence identification among objects.

    Vehicular cooperative perception for identifying a connected vehicle to aid a pedestrian

    公开(公告)号:US11485377B2

    公开(公告)日:2022-11-01

    申请号:US16784084

    申请日:2020-02-06

    发明人: Hongsheng Lu Rui Guo

    摘要: The disclosure includes embodiments for vehicular cooperative perception for identifying a subset of connected vehicles from a plurality to aid a pedestrian. In some embodiments, a method includes analyzing pedestrian data to determine a scenario depicted by the pedestrian data and a subset of the connected vehicles from the plurality that have a clearest line of the pedestrian. The method includes identifying a group of conflicted vehicles from the subset whose driving paths conflict with a walking path of the pedestrian. The method includes determining, based on the scenario, digital twin data describing a digital twin simulation that corresponds to the scenario. The method includes determining, based on the digital twin data and the pedestrian data, a group of modified driving paths for the group of conflicted vehicles. The method includes causing the group of conflicted vehicles to travel in accordance with the group of modified driving paths.

    ADAPTIVE SENSOR DATA SHARING FOR A CONNECTED VEHICLE

    公开(公告)号:US20220038872A1

    公开(公告)日:2022-02-03

    申请号:US16943421

    申请日:2020-07-30

    发明人: Hongsheng Lu Rui Guo

    摘要: The disclosure includes embodiments for adaptive sensor data sharing by a connected vehicle. A method includes calculating, by a processor of an ego vehicle, a view angle overlap between a first sensor of the ego vehicle and a second sensor of a roadway device, wherein the view angle overlap is an amount of sensor view overlap shared by first sensor and the second sensor. The method includes determining an amount of ego sensor data to share with the roadway device based on the view angle overlap. The method includes building a sharing message that includes the amount of ego sensor data in a payload of the sharing message. The method includes transmitting, by a communication unit of the ego vehicle, the sharing message to the roadway device.

    VEHICLE SENSOR DATA SHARING
    49.
    发明申请

    公开(公告)号:US20220036098A1

    公开(公告)日:2022-02-03

    申请号:US16944891

    申请日:2020-07-31

    IPC分类号: G06K9/00 G06K9/62 G06T5/50

    摘要: Two vehicles—an ego vehicle and an other vehicle—can share sensor data in a streamlined manner. One or more sensors can be configured to acquire first environment data of an external environment of the ego vehicle. A data summary based on second environment data of an external environment of the other vehicle can be received. Whether there is a common region of sensor coverage between the ego vehicle and the other vehicle can be determined. In response to there being a common region, the first environment data that is located within the common region can be identified and the resolution level of the identified first environment data can be reduced. The first environment data that has the reduced resolution level and a remainder of the first environment data excluding the identified first environment data can be transmitted to the other vehicle.

    Adaptive vehicle identifier generation

    公开(公告)号:US11240707B2

    公开(公告)日:2022-02-01

    申请号:US16886553

    申请日:2020-05-28

    发明人: Rui Guo Hongsheng Lu

    摘要: The disclosure includes embodiments for providing adaptive vehicle ID generation. A method includes determining a set of channel loads for a V2X network. The method includes analyzing the set of channel loads to determine if a threshold is satisfied by broadcasting a V2X message including a standard vehicle identifier. Satisfying the threshold is indicative of a channel congestion. The method includes activating a digital switching decision that switches the connected vehicle from broadcasting the standard vehicle identifier to broadcasting a compressed vehicle identifier. The method includes inputting vehicle feature data describing the connected vehicle to a compression module. The compression module analyzes the vehicle feature data and outputs compressed vehicle identifier data describing the compressed vehicle identifier so that the compressed vehicle identifier is determined independently of the standard vehicle identifier. The method includes broadcasting a V2X message including the compressed vehicle identifier data which identifies the connected vehicle.