公开(公告)号：US20190096256A1

公开(公告)日：2019-03-28

申请号：US15883176

申请日：2018-01-30

Applicant: Toyota Research Institute, Inc.

Inventor： Todd J. Rowell

IPC: G08G1/16 ,  G06T7/246 ,  G06K9/00 ,  G06K9/62 ,  G01S17/93 ,  G01S15/93 ,  G01S15/58 ,  G01S17/58

Abstract: Vehicles systems for predicting a trajectory of an object proximate to vehicles are disclosed. A vehicle system includes one or more sensors, one or more processors communicatively coupled to the one or more sensors, a memory module communicatively coupled to the one or more processors, and machine readable instructions stored in the memory module. The machine readable instructions, when executed by the processor, cause the system to: detect an object based on one or more signals output by the one or more sensors; classify the object into an object classification; predict a trajectory of the object based on at least one behavior characteristic of the object determined from a model corresponding to the object classification; predict a trajectory of the vehicle; and provide a warning when the detected object is likely to move from a non-obstacle position to an obstacle position based on the predicted trajectories of the object and the vehicle.

公开(公告)号：US20180370567A1

公开(公告)日：2018-12-27

申请号：US15629046

申请日：2017-06-21

Applicant: Toyota Research Institute, Inc.

Inventor： Todd J. Rowell

IPC: B62D15/02 ,  B60W30/12 ,  G06T19/00

Abstract: A method and device are disclosed. Vehicle sensor data may be compared with a threshold value. When the vehicle sensor data exceeds the threshold value, selecting an appearance mode of a plurality of appearance modes, and applying the first appearance mode to virtual lane marker data to produce enhanced virtual marker data. The enhanced virtual marker data may be transmitted for display by a vehicle graphical user interface.