中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.015 seconds)

    Automatic Annotation of Object Trajectories in Multiple Dimensions
    2.
    发明申请
    Automatic Annotation of Object Trajectories in Multiple Dimensions 有权

    公开(公告)号：US20250002050A1

    公开(公告)日：2025-01-02

    申请号：US18883299

    申请日：2024-09-12

    Applicant: Aurora Operations, Inc.

    Inventor： Bin Yang ,  Ming Liang ,  Wenyuan Zeng ,  Min Bai ,  Raquel Urtasun

    IPC: B60W60/00 ,  G06N20/00

    Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.

    Systems and methods for generating synthetic sensor data via machine learning
    3.
    发明授权
    Systems and methods for generating synthetic sensor data via machine learning 有权

    公开(公告)号：US12222832B2

    公开(公告)日：2025-02-11

    申请号：US18466286

    申请日：2023-09-13

    Applicant: Aurora Operations, Inc.

    Inventor： Sivabalan Manivasagam ,  Shenlong Wang ,  Wei-Chiu Ma ,  Kelvin Ka Wing Wong ,  Wenyuan Zeng ,  Raquel Urtasun

    IPC: G06F11/263 ,  G06F17/18 ,  G06N3/047 ,  G06N20/00 ,  G06T15/06 ,  G06T17/20

    Abstract: The present disclosure provides systems and methods that combine physics-based systems with machine learning to generate synthetic LiDAR data that accurately mimics a real-world LiDAR sensor system. In particular, aspects of the present disclosure combine physics-based rendering with machine-learned models such as deep neural networks to simulate both the geometry and intensity of the LiDAR sensor. As one example, a physics-based ray casting approach can be used on a three-dimensional map of an environment to generate an initial three-dimensional point cloud that mimics LiDAR data. According to an aspect of the present disclosure, a machine-learned model can predict one or more dropout probabilities for one or more of the points in the initial three-dimensional point cloud, thereby generating an adjusted three-dimensional point cloud which more realistically simulates real-world LiDAR data.

    Systems and Methods for Generating Synthetic Sensor Data via Machine Learning
    4.
    发明申请
    Systems and Methods for Generating Synthetic Sensor Data via Machine Learning 有权

    公开(公告)号：US20250130909A1

    公开(公告)日：2025-04-24

    申请号：US19007149

    申请日：2024-12-31

    Applicant: Aurora Operations, Inc.

    Inventor： Sivabalan Manivasagam ,  Shenlong Wang ,  Wei-Chiu Ma ,  Kelvin Ka Wing Wong ,  Wenyuan Zeng ,  Raquel Urtasun

    IPC: G06F11/263 ,  G06F17/18 ,  G06N3/047 ,  G06N20/00 ,  G06T15/06 ,  G06T17/20

    Abstract: The present disclosure provides systems and methods that combine physics-based systems with machine learning to generate synthetic LiDAR data that accurately mimics a real-world LiDAR sensor system. In particular, aspects of the present disclosure combine physics-based rendering with machine-learned models such as deep neural networks to simulate both the geometry and intensity of the LiDAR sensor. As one example, a physics-based ray casting approach can be used on a three-dimensional map of an environment to generate an initial three-dimensional point cloud that mimics LiDAR data. According to an aspect of the present disclosure, a machine-learned model can predict one or more dropout probabilities for one or more of the points in the initial three-dimensional point cloud, thereby generating an adjusted three-dimensional point cloud which more realistically simulates real-world LiDAR data.

Patent Agency Ranking