-
公开(公告)号：US20240262386A1
公开(公告)日：2024-08-08
申请号：US18163708
申请日：2023-02-02
Applicant: Motional AD LLC
Inventor： Akankshya Kar , Apoorv Singh , Varun Kumar Reddy Bankiti
IPC: B60W60/00 , G06T7/50 , G06V10/764 , G06V10/82
CPC classification number: B60W60/0011 , G06T7/50 , G06V10/764 , G06V10/82
Abstract: Provided are methods for image depth estimation, which can include obtaining image associated with a scene of an autonomous vehicle, determining a first estimated depth for a plurality of points in the image, and generating a plurality of groups of points based on the first estimated depth for the plurality of points. Some methods described also include determining a second estimated depth for at least one point using a range specific depth estimation head, determining at least one object classification for the at least one point, and causing the autonomous vehicle to be navigated based on the second estimated depth for the at least one point and the at least one object classification for the at least one point. Systems and computer program products are also provided.
-
公开(公告)号：US12045058B2
公开(公告)日：2024-07-23
申请号：US18074770
申请日：2022-12-05
Applicant: UATC, LLC
Inventor： David McAllister Bradley , Chenggang Liu , Daoyuan Jia
CPC classification number: G05D1/0212 , B60W60/0011 , G05D1/0088
Abstract: Systems and methods for vehicle spatial path sampling are provided. The method includes obtaining an initial travel path for an autonomous vehicle from a first location to a second location and vehicle configuration data indicative of one or more physical constraints of the autonomous vehicle. The method includes determining one or more secondary travel paths for the autonomous vehicle from the first location to the second location based on the initial travel path and the vehicle configuration data. The method includes generating a spatial envelope based on the one or more secondary travel paths that indicates a plurality of lateral offsets from the initial travel path. And, the method includes generating a plurality of trajectories for the autonomous vehicle to travel from the first location to the second location such that each of the plurality of trajectories include one or more lateral offsets identified by the spatial envelope.
-
公开(公告)号：US20240227854A9
公开(公告)日：2024-07-11
申请号：US18381784
申请日：2023-10-19
Inventor： Samuel WOO
IPC: B60W60/00
CPC classification number: B60W60/0011 , B60W2556/50
Abstract: A system for providing autonomous driving safety map service according to an embodiment includes an autonomous vehicle which transmits anomaly information of an autonomous driving system acquired during the driving of the vehicle, and a server for providing safety map service, which receives the anomaly information of the autonomous driving system from one or more of the autonomous vehicles driving within a specific area, generates autonomous driving danger zone information based on one or more of the location of occurrence of the anomaly information or identification information of the autonomous vehicle, and provides the generated autonomous driving danger zone information in conjunction with a map of the specific area.
-
公开(公告)号：US20240220682A1
公开(公告)日：2024-07-04
申请号：US18092901
申请日：2023-01-03
Applicant: GM Cruise Holdings LLC
Inventor： Hariprasad Govardhanam , Luke Murchison , Lynn Sarcione , Jean David Margulici
CPC classification number: G06F30/27 , B60W60/0011
Abstract: The disclosed technology provides solutions for improving simulation generation, and in particular for diagnosing problems with a simulation renderer configured to generate simulated (or synthetic) environments for use in autonomous vehicle (AV) testing and training. In some aspects, a process of the disclosed technology includes steps for receiving a set of divergence metrics, wherein the divergence metrics comprise performance statistics for one or more components of a simulation renderer, providing the divergence metrics to a machine-learning model, and identifying, using an attribution tool, one or more components of the simulation renderer that contributed to the AV pose divergence based on one or more weights of the machine-learning model. Systems and machine-readable media are also provided.
-
公开(公告)号：US20240217548A1
公开(公告)日：2024-07-04
申请号：US18093256
申请日：2023-01-04
Applicant: Zoox, Inc.
Inventor： Ethan Miller Pronovost
CPC classification number: B60W60/0011 , B60W50/0097 , B60W60/00274 , G06N20/00 , B60W2554/20 , B60W2554/4041 , B60W2554/4045
Abstract: Techniques are discussed herein for using a machine learning attention mechanism to predict movements, states, and/or trajectories of agents in various environments. In various examples, a prediction component of an autonomous vehicle may analyze sensor data to determine, for individual agents in the environment, unique sets of additional objects that are relevant to predicting the subsequent movements of the individual agents. For a particular agent, the prediction component may determine the relative positions and/or states between the agent and the associated set of relevant objects for the agent, and may use an attention mechanism to determine an object interaction vector including weighted attention scores for each additional object relative to the agent. Object interaction vectors may be generated for any number of agents and/or any number of timesteps to determine predicted agent movements and to forecast subsequent driving scenes within the environment.
-
公开(公告)号：US12024194B2
公开(公告)日：2024-07-02
申请号：US17210566
申请日：2021-03-24
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui
IPC: B60W60/00 , B60W30/095 , B60W40/04 , B60W40/105 , G06N20/00 , G06V20/58
CPC classification number: B60W60/0011 , B60W30/0956 , B60W40/04 , B60W40/105 , B60W60/00274 , G06N20/00 , G06V20/58 , B60W2520/105 , B60W2554/80
Abstract: A vehicle control method includes recognizing an object, generating plurality of target trajectories which the vehicle travels using a plurality of models, and automatically controlling driving of the vehicle based on the target trajectory, the plurality of models include a first model which is a rule based model or a model based model, and a second model which is a machine learning based model, and the second target trajectory is selected, when the vehicle accelerates after a speed of the vehicle has been equal to or smaller than a predetermined value, under a condition in which driving of the vehicle is controlled based on a first target trajectory output by the first model and under a condition in which driving of the vehicle is controlled based on a second target trajectory output by the second model.
-
公开(公告)号：US12024170B2
公开(公告)日：2024-07-02
申请号：US17121086
申请日：2020-12-14
Applicant: Zoox, Inc.
Inventor： Akash Arora , Lichao Ma
CPC classification number: B60W30/18163 , B60W30/0956 , B60W30/162 , B60W50/0097 , B60W60/0011 , B60W60/0027 , G01C21/3453 , G08G1/167 , B60W30/09 , B60W2554/80 , B60W2555/60
Abstract: Techniques for determining gaps for performing lane change operations are described. A first region in an environment of a vehicle can be determined. The first region can be associated with a first time period through which the vehicle is unable to travel and can correspond to a constraint space. A second region of the environment can be determined. The second region can be associated with a second time period and can correspond to a configuration space. A gap in the environment can be determined based on a portion of the configuration space that is exclusive of the constraint space. A trajectory can be determined based on the gap. The trajectory can be associated with performing a lane change operation and can be associated with a cost. The vehicle can be controlled to perform the lane change operation based at least in part on the trajectory and the cost.
-
公开(公告)号：US20240199076A1
公开(公告)日：2024-06-20
申请号：US18543669
申请日：2023-12-18
Applicant: Volvo Autonomous Solutions AB
Inventor： Wilhelm WIBERG , Oskar Ljungqvist , Calle Skillsäter , Johan Sjöberg
IPC: B60W60/00
CPC classification number: B60W60/0011 , B60W2530/10 , B60W2552/35
Abstract: A computer system comprising a processor device configured to determine at least one travelling path for at least one vehicle is provided. The processor device is further configured to obtain an indication of wear of a drivable surface. The drivable surface comprising a set of surface areas. The indication of wear is indicative of a wear of each respective surface area in the set of surface areas. The processor device is further configured to, based on the indicated wear of the set of surface areas of the drivable surface, determine the at least one travelling path for the at least one vehicle.
-
公开(公告)号：US11999381B2
公开(公告)日：2024-06-04
申请号：US18084512
申请日：2022-12-19
Applicant: TOYOTA MOTOR NORTH AMERICA, INC.
Inventor： Lucas Smith , Jay Bartholomew
CPC classification number: B60W60/0015 , B60W30/08 , B60W60/0011 , B60W60/0025 , G06V20/593 , G06V20/597
Abstract: An example operation includes one or more of determining, by a transport, a number of items in the transport, determining, by the transport, a position of each of the items, and in response to a dangerous situation associated with the transport occurring, providing, by the transport, a safety notification associated with at least one of the items.
-
公开(公告)号：US11999380B1
公开(公告)日：2024-06-04
申请号：US17554693
申请日：2021-12-17
Applicant: Zoox, Inc.
Inventor： Joseph Funke , Steven Cheng Qian , Kazuhide Okamoto , Jacob Patrick Thalman , Sriram Narayanan
IPC: B60W60/00
CPC classification number: B60W60/0011 , B60W2520/06 , B60W2520/10 , B60W2520/12
Abstract: Techniques are discussed for generating and optimizing trajectories for controlling autonomous vehicles in performing on-route and off-route actions within a driving environment. A planning component of an autonomous vehicle can receive or generate time-discretized (or temporal) trajectories for the autonomous vehicle to traverse an environment. Trajectories can be optimized, for example, based on the lateral and longitudinal dynamics of the vehicle, using loss functions and/or costs. In some examples, the temporal optimization of a trajectory may include resampling a previous trajectory based on the differences in the time sequences of the temporal trajectories, to ensure temporal consistency of trajectories across planning cycles. Constraints also may be applied during temporal optimization in some examples, to control or restrict driving maneuvers that are not supported by the autonomous vehicle.
