公开(公告)号：US20250117709A1

公开(公告)日：2025-04-10

申请号：US18982461

申请日：2024-12-16

Applicant: Aurora Operations, Inc.

Inventor： Sergio Casas ,  Cole Christian Gulino ,  Shun Da Suo ,  Raquel Urtasun

IPC: G06N20/00 ,  G05B13/02 ,  G06N7/01

Abstract: The present disclosure provides systems and methods for training probabilistic object motion prediction models using non-differentiable representations of prior knowledge. As one example, object motion prediction models can be used by autonomous vehicles to probabilistically predict the future location(s) of observed objects (e.g., other vehicles, bicyclists, pedestrians, etc.). For example, such models can output a probability distribution that provides a distribution of probabilities for the future location(s) of each object at one or more future times. Aspects of the present disclosure enable these models to be trained using non-differentiable prior knowledge about motion of objects within the autonomous vehicle's environment such as, for example, prior knowledge about lane or road geometry or topology and/or traffic information such as current traffic control states (e.g., traffic light status).

公开(公告)号：US12131487B2

公开(公告)日：2024-10-29

申请号：US17725879

申请日：2022-04-21

Applicant: Aurora Operations, Inc.

Inventor： Shivam Gautam ,  Brian C. Becker ,  Carlos Vallespi-Gonzalez ,  Cole Christian Gulino

IPC: G06T7/70 ,  G05D1/00 ,  G06T7/20 ,  G06T7/246 ,  G06V10/764 ,  G06V10/82 ,  G06V20/58 ,  G06V40/10

CPC classification number: G06T7/246 ,  G05D1/0088 ,  G05D1/0231 ,  G06T7/20 ,  G06V10/764 ,  G06V10/82 ,  G06V20/58 ,  G06V40/10 ,  G06T2207/30261

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with object association and tracking are provided. Input data can be obtained. The input data can be indicative of a detected object within a surrounding environment of an autonomous vehicle and an initial object classification of the detected object at an initial time interval and object tracks at time intervals preceding the initial time interval. Association data can be generated based on the input data and a machine-learned model. The association data can indicate whether the detected object is associated with at least one of the object tracks. An object classification probability distribution can be determined based on the association data. The object classification probability distribution can indicate a probability that the detected object is associated with each respective object classification. The association data and the object classification probability distribution for the detected object can be outputted.

公开(公告)号：US12205004B2

公开(公告)日：2025-01-21

申请号：US18495434

申请日：2023-10-26

Applicant: Aurora Operations, Inc.

Inventor： Sergio Casas ,  Cole Christian Gulino ,  Shun Da Suo ,  Raquel Urtasun

IPC: G06N20/00 ,  G05B13/02 ,  G05D1/00 ,  G06N7/01

Abstract: The present disclosure provides systems and methods for training probabilistic object motion prediction models using non-differentiable representations of prior knowledge. As one example, object motion prediction models can be used by autonomous vehicles to probabilistically predict the future location(s) of observed objects (e.g., other vehicles, bicyclists, pedestrians, etc.). For example, such models can output a probability distribution that provides a distribution of probabilities for the future location(s) of each object at one or more future times. Aspects of the present disclosure enable these models to be trained using non-differentiable prior knowledge about motion of objects within the autonomous vehicle's environment such as, for example, prior knowledge about lane or road geometry or topology and/or traffic information such as current traffic control states (e.g., traffic light status).