公开(公告)号：US11926346B2

公开(公告)日：2024-03-12

申请号：US17395318

申请日：2021-08-05

Applicant: NVIDIA Corporation

Inventor： Fangkai Yang ,  David Nister ,  Yizhou Wang ,  Rotem Aviv ,  Julia Ng ,  Birgit Henke ,  Hon Leung Lee ,  Yunfei Shi

IPC: B60W60/00 ,  B60W30/18 ,  G08G1/0967

CPC classification number: B60W60/0027 ,  B60W30/18154 ,  B60W30/18159 ,  G08G1/096725 ,  B60W2420/42 ,  B60W2420/52 ,  B60W2552/05

Abstract: In various examples, a yield scenario may be identified for a first vehicle. A wait element is received that encodes a first path for the first vehicle to traverse a yield area and a second path for a second vehicle to traverse the yield area. The first path is employed to determine a first trajectory in the yield area for the first vehicle based at least on a first location of the first vehicle at a time and the second path is employed to determine a second trajectory in the yield area for the second vehicle based at least on a second location of the second vehicle at the time. To operate the first vehicle in accordance with a wait state, it may be determined whether there is a conflict between the first trajectory and the second trajectory, where the wait state defines a yielding behavior for the first vehicle.

公开(公告)号：US20210295171A1

公开(公告)日：2021-09-23

申请号：US16824199

申请日：2020-03-19

Applicant: NVIDIA Corporation

Inventor： Alexey Kamenev ,  Nikolai Smolyanskiy ,  Ishwar Kulkarni ,  Ollin Boer Bohan ,  Fangkai Yang ,  Alperen Degirmenci ,  Ruchi Bhargava ,  Urs Muller ,  David Nister ,  Rotem Aviv

IPC: G06N3/08 ,  G06N3/04

Abstract: In various examples, past location information corresponding to actors in an environment and map information may be applied to a deep neural network (DNN)—such as a recurrent neural network (RNN)—trained to compute information corresponding to future trajectories of the actors. The output of the DNN may include, for each future time slice the DNN is trained to predict, a confidence map representing a confidence for each pixel that an actor is present and a vector field representing locations of actors in confidence maps for prior time slices. The vector fields may thus be used to track an object through confidence maps for each future time slice to generate a predicted future trajectory for each actor. The predicted future trajectories, in addition to tracked past trajectories, may be used to generate full trajectories for the actors that may aid an ego-vehicle in navigating the environment.

公开(公告)号：US20240217557A1

公开(公告)日：2024-07-04

申请号：US18602802

申请日：2024-03-12

Applicant: NVIDIA Corporation

Inventor： Fangkai Yang ,  David Nister ,  Yizhou Wang ,  Rotem Aviv ,  Julia Ng ,  Birgit Henke ,  Hon Leung Lee ,  Yunfei Shi

IPC: B60W60/00 ,  B60W30/18 ,  G08G1/0967

CPC classification number: B60W60/0027 ,  B60W30/18154 ,  B60W30/18159 ,  G08G1/096725 ,  B60W2420/403 ,  B60W2420/408 ,  B60W2552/05

Abstract: In various examples, a yield scenario may be identified for a first vehicle. A wait element is received that encodes a first path for the first vehicle to traverse a yield area and a second path for a second vehicle to traverse the yield area. The first path is employed to determine a first trajectory in the yield area for the first vehicle based at least on a first location of the first vehicle at a time and the second path is employed to determine a second trajectory in the yield area for the second vehicle based at least on a second location of the second vehicle at the time. To operate the first vehicle in accordance with a wait state, it may be determined whether there is a conflict between the first trajectory and the second trajectory, where the wait state defines a yielding behavior for the first vehicle.

公开(公告)号：US12001958B2

公开(公告)日：2024-06-04

申请号：US16824199

申请日：2020-03-19

Applicant: NVIDIA Corporation

Inventor： Alexey Kamenev ,  Nikolai Smolyanskiy ,  Ishwar Kulkarni ,  Ollin Boer Bohan ,  Fangkai Yang ,  Alperen Degirmenci ,  Ruchi Bhargava ,  Urs Muller ,  David Nister ,  Rotem Aviv

IPC: G06N3/088 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06N3/088 ,  G06N3/044 ,  G06N3/045

Abstract: In various examples, past location information corresponding to actors in an environment and map information may be applied to a deep neural network (DNN)—such as a recurrent neural network (RNN)—trained to compute information corresponding to future trajectories of the actors. The output of the DNN may include, for each future time slice the DNN is trained to predict, a confidence map representing a confidence for each pixel that an actor is present and a vector field representing locations of actors in confidence maps for prior time slices. The vector fields may thus be used to track an object through confidence maps for each future time slice to generate a predicted future trajectory for each actor. The predicted future trajectories, in addition to tracked past trajectories, may be used to generate full trajectories for the actors that may aid an ego-vehicle in navigating the environment.

公开(公告)号：US20240059285A1

公开(公告)日：2024-02-22

申请号：US17891587

申请日：2022-08-19

Applicant: NVIDIA Corporation

Inventor： Julia Ng ,  Jian Wei Leong ,  Nikolai Smolyanskiy ,  Yizhou Wang ,  Fangkai Yang ,  Nianfeng Wan ,  Chang Liu

IPC: B60W30/14 ,  B60W60/00 ,  B60W50/00

CPC classification number: B60W30/14 ,  B60W60/001 ,  B60W50/0097 ,  B60W2520/00 ,  B60W2556/00

Abstract: In various examples, techniques for using future trajectory predictions for adaptive cruise control (ACC) are described. For instance, a vehicle may determine a future path(s) of the vehicle and a future path(s) of an object(s). The vehicle may then use a speed profile(s) and the future path(s) to determine a trajectory(ies) for the vehicle. The vehicle may then select a trajectory, such as based on the future path(s) of the object(s). Based on the trajectory, ACC of the vehicle may cause the vehicle to navigate at a speed or a velocity. This way, the vehicle is able to continue using ACC even when the driver makes a maneuver(s) or the system determined to make a maneuver, such as switching lanes or choosing a lane when a road splits.

公开(公告)号：US20230037767A1

公开(公告)日：2023-02-09

申请号：US17395318

申请日：2021-08-05

Applicant: NVIDIA Corporation

Inventor： Fangkai Yang ,  David Nister ,  Yizhou Wang ,  Rotem Aviv ,  Julia Ng ,  Birgit Henke ,  Hon Leung Lee ,  Yunfei Shi

IPC: B60W60/00 ,  G08G1/0967 ,  B60W30/18

Abstract: In various examples, a yield scenario may be identified for a first vehicle. A wait element is received that encodes a first path for the first vehicle to traverse a yield area and a second path for a second vehicle to traverse the yield area. The first path is employed to determine a first trajectory in the yield area for the first vehicle based at least on a first location of the first vehicle at a time and the second path is employed to determine a second trajectory in the yield area for the second vehicle based at least on a second location of the second vehicle at the time. To operate the first vehicle in accordance with a wait state, it may be determined whether there is a conflict between the first trajectory and the second trajectory, where the wait state defines a yielding behavior for the first vehicle.

公开(公告)号：US20220138568A1

公开(公告)日：2022-05-05

申请号：US17453055

申请日：2021-11-01

Applicant: NVIDIA Corporation

Inventor： Nikolai Smolyanskiy ,  Alexey Kamenev ,  Lirui Wang ,  David Nister ,  Ollin Boer Bohan ,  Ishwar Kulkarni ,  Fangkai Yang ,  Julia Ng ,  Alperen Degirmenci ,  Ruchi Bhargava ,  Rotem Aviv

IPC: G06N3/08 ,  G06N3/04

Abstract: In various examples, reinforcement learning is used to train at least one machine learning model (MLM) to control a vehicle by leveraging a deep neural network (DNN) trained on real-world data by using imitation learning to predict movements of one or more actors to define a world model. The DNN may be trained from real-world data to predict attributes of actors, such as locations and/or movements, from input attributes. The predictions may define states of the environment in a simulator, and one or more attributes of one or more actors input into the DNN may be modified or controlled by the simulator to simulate conditions that may otherwise be unfeasible. The MLM(s) may leverage predictions made by the DNN to predict one or more actions for the vehicle.