-
公开(公告)号:US20250044790A1
公开(公告)日:2025-02-06
申请号:US18364824
申请日:2023-08-03
Applicant: Kodiak Robotics, Inc.
Inventor: Andreas Wendel , Felix Duvallet
Abstract: Systems and methods for controlling a vehicle is provided. The system may comprise a vehicle, one or more sensors, coupled to the vehicle, configured to generate one or more data points, one or more actuation controls configured to enable the vehicle to perform one or more driving actions, and an automatic trajectory control system, comprising a processor, configured to perform automatic trajectory control. The automatic trajectory control system may be configured to receive one or more data points generated by the one or more sensors, automatically generate an automatic trajectory command, generate one or more driving actions, and cause the vehicle, via the one or more actuation controls, to perform the one or more driving actions in accordance with the automatic trajectory command. The system may comprise a switch configured to switch command of the vehicle between automatic trajectory control and a remote station system control.
-
2.
公开(公告)号:US20240203130A1
公开(公告)日:2024-06-20
申请号:US18065711
申请日:2022-12-14
Applicant: Kodiak Robotics, Inc.
Inventor: Suchir Gupta , Collin C. Otis , Cole M. Miles , Philip C. Du Toit , Andreas Wendel
Abstract: This disclosure provides methods and systems for detecting and tracking objects in an environment of an autonomous vehicle. The method may include: receiving sensor data from at least one sensor of the autonomous vehicle, the sensor data representative of one or more portions of an object in the environment of the autonomous vehicle; determining a highest confidence portion of the object, wherein the highest confidence portion of the object comprises a portion of the object that is observed and estimated with highest accuracy and confidence; determining features of the highest confidence portion of the object; training a machine learning model based at least in part on the features of the highest confidence portion of the object and an error metric that measures difference between the highest confidence portion of the object and a corresponding portion of the object in a ground truth; and detecting or tracking one or more objects in the environment of the autonomous vehicle using the trained machine learning model.
-
公开(公告)号:US20230068067A1
公开(公告)日:2023-03-02
申请号:US17977561
申请日:2022-10-31
Applicant: Kodiak Robotics, Inc.
Inventor: Donald Burnette , Court Hinricher , Jay Kuvelker , Andreas Wendel , John Zinn , Laura Shane
IPC: B60R11/04 , G01S17/931 , G01S17/86 , B60R1/06 , B60R1/12 , G01S13/86 , G01S13/931 , G03B37/04 , H04N5/247
Abstract: A sensor assembly for autonomous vehicles includes a side mirror assembly configured to mount to a vehicle. The side mirror assembly includes a first camera having a field of view in a direction opposite a direction of forward travel of the vehicle; a second camera having a field of view in the direction of forward travel of the vehicle; and a third camera having a field of view in a direction substantially perpendicular to the direction of forward travel of the vehicle. The first camera, the second camera, and the third camera are oriented to provide, in combination with a fourth camera configured to be mounted on a roof of the vehicle, an uninterrupted camera field of view from the direction of forward travel of the vehicle to a direction opposite the direction of forward travel of the vehicle.
-
公开(公告)号:US20220144185A1
公开(公告)日:2022-05-12
申请号:US17435368
申请日:2020-02-28
Applicant: Kodiak Robotics, Inc.
Inventor: Donald Burnette , Court Hinricher , Jay Kuvelker , Andreas Wendel , John Zinn , Laura Shane
IPC: B60R11/04 , B60R1/12 , B60R1/06 , G03B37/04 , H04N5/247 , G01S13/931 , G01S17/931 , G01S13/86 , G01S17/86
Abstract: A sensor assembly for autonomous vehicles includes a side mirror assembly configured to mount to a vehicle. The side mirror assembly includes a first camera having a field of view in a direction opposite a direction of forward travel of the vehicle; a second camera having a field of view in the direction of forward travel of the vehicle; and a third camera having a field of view in a direction substantially perpendicular to the direction of forward travel of the vehicle. The first camera, the second camera, and the third camera are oriented to provide, in combination with a fourth camera configured to be mounted on a roof of the vehicle, an uninterrupted camera field of view from the direction of forward travel of the vehicle to a direction opposite the direction of forward travel of the vehicle.
-
5.
公开(公告)号:US12258041B2
公开(公告)日:2025-03-25
申请号:US18065419
申请日:2022-12-13
Applicant: Kodiak Robotics, Inc.
Inventor: Derek J. Phillips , Collin C. Otis , Andreas Wendel , Jackson P. Rusch
Abstract: This disclosure provides systems and methods for controlling a vehicle. The method comprises receiving data from a set of sensors, wherein the data represents objects or obstacles in an environment of the autonomous vehicle; identifying objects or obstacles from the received data; determining multiple sets of attributes of the objects or obstacles, wherein each set of attributes of the objects or obstacles are determined based on data received by an individual sensor; determining a candidate trajectory for the autonomous vehicle based on the multiple sets of attributes of the objects or obstacles; and controlling the autonomous vehicle according to the candidate trajectory.
-
公开(公告)号:US20250044793A1
公开(公告)日:2025-02-06
申请号:US18364819
申请日:2023-08-03
Applicant: Kodiak Robotics, Inc.
Inventor: Andreas Wendel , Felix Duvallet
Abstract: Systems and methods for controlling a vehicle are provided. The method may comprise generating one or more data points from one or more sensors coupled to a vehicle and performing remote station system control of the vehicle using a remote station system. The performing the remote station system control of the vehicle may comprise, using the remote station system, receiving the one or more data points generated by the one or more sensors and generating a remote trajectory command, and generating, based on the one or more trajectory plot points, one or more driving actions. The method may comprise transmitting the trajectory command to the vehicle and performing a fallback function. Performing the fallback function may comprise determining whether command of the vehicle should fall back to one or more secondary control modes and switching, using a switch, control of the vehicle to the one or more secondary control modes.
-
公开(公告)号:US20240294124A1
公开(公告)日:2024-09-05
申请号:US18117330
申请日:2023-03-03
Applicant: Kodiak Robotics, Inc.
Inventor: Andreas Wendel
CPC classification number: B60R11/04 , B60W60/001 , B60R2011/004 , B60W2420/403 , B60W2420/408
Abstract: An autonomous vehicle includes a sensor pod having a mirror, a connecting assembly extending between the sensor pod and the autonomous vehicle, and a user interface provided on the sensor pod. The user interface is configured to provide two-way communication between a local user and a remote user.
-
8.
公开(公告)号:US20240219565A1
公开(公告)日:2024-07-04
申请号:US18147439
申请日:2022-12-28
Applicant: Kodiak Robotics, Inc.
Inventor: Andreas Wendel
IPC: G01S17/58 , G01S7/481 , G01S17/89 , G01S17/931
CPC classification number: G01S17/58 , G01S7/4817 , G01S17/89 , G01S17/931
Abstract: Systems and methods for detecting and measuring object velocity are provided. The method comprises, using a spinning Light Detection and Ranging (LiDAR) system, generating a first LiDAR point cloud of an environment surrounding a vehicle, using a scanning LiDAR system, generating a second LiDAR point cloud of the environment surrounding the vehicle, and, using a processor, identifying points within the first LiDAR point cloud coinciding with a position of an object and points within the second LiDAR point cloud coinciding with a position of the object, determining whether the points within the second LiDAR point cloud line up with the points within the first LiDAR point cloud, and, when the points within the second LiDAR point cloud do not line up with the points within the first LiDAR point cloud, determining that the object is moving.
-
9.
公开(公告)号:US20240190466A1
公开(公告)日:2024-06-13
申请号:US18065419
申请日:2022-12-13
Applicant: Kodiak Robotics, Inc.
Inventor: Derek J. Phillips , Collin C. Otis , Andreas Wendel , Jackson P. Rusch
CPC classification number: B60W60/0011 , G01S13/862 , G01S13/865 , B60W2420/42 , B60W2420/52 , B60W2420/54 , B60W2420/62
Abstract: This disclosure provides systems and methods for controlling a vehicle. The method comprises receiving data from a set of sensors, wherein the data represents objects or obstacles in an environment of the autonomous vehicle; identifying objects or obstacles from the received data; determining multiple sets of attributes of the objects or obstacles, wherein each set of attributes of the objects or obstacles are determined based on data received by an individual sensor; determining a candidate trajectory for the autonomous vehicle based on the multiple sets of attributes of the objects or obstacles; and controlling the autonomous vehicle according to the candidate trajectory.
-
10.
公开(公告)号:US20240190424A1
公开(公告)日:2024-06-13
申请号:US18147906
申请日:2022-12-29
Applicant: Kodiak Robotics, Inc.
Inventor: Derek J. Phillips , Collin C. Otis , Andreas Wendel , Jackson P. Rusch
IPC: B60W30/095 , B60W50/06 , B60W60/00
CPC classification number: B60W30/0956 , B60W50/06 , B60W60/001 , B60W30/09
Abstract: This disclosure provides systems and methods for detecting and tracking objects or obstacles in an environment of an autonomous vehicle. The method may include receiving data from a set of sensors, wherein the data represents objects or obstacles in an environment of the autonomous vehicle; and using a processor: generating high precision detection data based on the received data; identifying, from the high precision detection data, a set of objects that are classifiable by at least one known classifier; generating high recall detection data based on the received data; identifying from the high recall detection data a set of obstacles; and performing an operation on the high precision detection data of the objects and the high recall detection data of the obstacles, based on a status of the autonomous vehicle or based on one or more characteristics of the objects or the obstacles.
-
-
-
-
-
-
-
-
-