中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.018 seconds)

    GENERATING ADVERSARIAL DRIVING SCENARIOS FOR AUTONOMOUS VEHICLES
    1.
    发明申请
    GENERATING ADVERSARIAL DRIVING SCENARIOS FOR AUTONOMOUS VEHICLES 有权

    公开(公告)号：US20250115278A1

    公开(公告)日：2025-04-10

    申请号：US18905695

    申请日：2024-10-03

    Applicant: NEC Laboratories America, Inc.

    Inventor： Francesco Pittaluga ,  Buyu Liu ,  Manmohan Chandraker ,  Kaiyuan Zhang

    IPC: B60W60/00

    Abstract: Systems and methods for generating adversarial driving scenarios for autonomous vehicles. An artificial intelligence model can compute an adversarial loss function by minimizing the distance between predicted adversarial perturbed trajectories and corresponding generated neighbor future trajectories from input data. A traffic violation loss function can be computed based on observed adversarial agents adhering to driving rules from the input data. A comfort loss function can be computed based on the predicted driving characteristics of adversarial vehicles relevant to comfort of hypothetical passengers from the input data. A planner module can be trained for autonomous vehicles based on a combined loss function of the adversarial loss function, the traffic violation loss function and the comfort loss function to generate adversarial driving scenarios. An autonomous vehicle can be controlled based on trajectories generated in the adversarial driving scenarios.

    DIVIDE-AND-CONQUER FOR LANE-AWARE DIVERSE TRAJECTORY PREDICTION
    2.
    发明申请
    DIVIDE-AND-CONQUER FOR LANE-AWARE DIVERSE TRAJECTORY PREDICTION 有权

    公开(公告)号：US20220144256A1

    公开(公告)日：2022-05-12

    申请号：US17521139

    申请日：2021-11-08

    Applicant: NEC Laboratories America, Inc.

    Inventor： Sriram Nochur Narayanan ,  Ramin Moslemi ,  Francesco Pittaluga ,  Buyu Liu ,  Manmohan Chandraker

    IPC: B60W30/09 ,  G06F16/29 ,  G06N3/08 ,  B60W30/095 ,  G08G1/16

    Abstract: A method for driving path prediction is provided. The method concatenates past trajectory features and lane centerline features in a channel dimension at an agent's respective location in a top view map to obtain concatenated features thereat. The method obtains convolutional features derived from the top view map, the concatenated features, and a single representation of the training scene the vehicle and agent interactions. The method extracts hypercolumn descriptor vectors which include the convolutional features from the agent's respective location in the top view map. The method obtains primary and auxiliary trajectory predictions from the hypercolumn descriptor vectors. The method generates a respective score for each of the primary and auxiliary trajectory predictions. The method trains a vehicle trajectory prediction neural network using a reconstruction loss, a regularization loss objective, and an IOC loss objective responsive to the respective score for each of the primary and auxiliary trajectory predictions.

    LEARNING PRIVACY-PRESERVING OPTICS VIA ADVERSARIAL TRAINING
    3.
    发明申请
    LEARNING PRIVACY-PRESERVING OPTICS VIA ADVERSARIAL TRAINING 有权

    公开(公告)号：US20220067457A1

    公开(公告)日：2022-03-03

    申请号：US17412704

    申请日：2021-08-26

    Applicant: NEC Laboratories America, Inc.

    Inventor： Francesco Pittaluga ,  Giovanni Milione ,  Xiang Yu ,  Manmohan Chandraker ,  Yi-Hsuan Tsai ,  Zaid Tasneem

    IPC: G06K9/62 ,  G06N3/04 ,  G06F21/60

    Abstract: A method for acquiring privacy-enhancing encodings in an optical domain before image capture is presented. The method includes feeding a differentiable sensing model with a plurality of images to obtain encoded images, the differentiable sensing model including parameters for sensor optics, integrating the differentiable sensing model into an adversarial learning framework where parameters of attack networks, parameters of utility networks, and the parameters of the sensor optics are concurrently updated, and, once adversarial training is complete, validating efficacy of a learned sensor design by fixing the parameters of the sensor optics and training the attack networks and the utility networks to learn to estimate private and public attributes, respectively, from a set of the encoded images.

    IMAGE FEATURE MATCHING WITH FORMAL PRIVACY GUARANTEES
    5.
    发明公开
    IMAGE FEATURE MATCHING WITH FORMAL PRIVACY GUARANTEES 审中-公开

    公开(公告)号：US20240303365A1

    公开(公告)日：2024-09-12

    申请号：US18598198

    申请日：2024-03-07

    Applicant: NEC Laboratories America, Inc.

    Inventor： Francesco Pittaluga ,  Bingbing Zhuang ,  Xiang Yu

    IPC: G06F21/62 ,  G06V10/75

    CPC classification number: G06F21/6227 ,  G06V10/751

    Abstract: Systems and methods are provided for privacy-preserving image feature matching in computer vision applications, including receiving a raw image descriptor, and perturbing the raw image descriptor using a subset selection mechanism to generate a perturbed descriptor set that includes the raw image descriptor and additional descriptors. Each descriptor in the perturbed descriptor set is replaced with its nearest neighbor in a predefined descriptor database to reduce the output domain size of the subset selection mechanism. Local differential privacy (LDP) protocols are employed to further perturb the descriptor set, ensuring formal privacy guarantees, and the perturbed descriptor set is matched against a second set of descriptors for image feature matching.

    VOTING-BASED APPROACH FOR DIFFERENTIALLY PRIVATE FEDERATED LEARNING
    9.
    发明申请
    VOTING-BASED APPROACH FOR DIFFERENTIALLY PRIVATE FEDERATED LEARNING 有权

    公开(公告)号：US20220108226A1

    公开(公告)日：2022-04-07

    申请号：US17491663

    申请日：2021-10-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xiang Yu ,  Yi-Hsuan Tsai ,  Francesco Pittaluga ,  Masoud Faraki ,  Manmohan Chandraker ,  Yuqing Zhu

    IPC: G06N20/20 ,  G06N5/02 ,  G06N5/04

    Abstract: A method for employing a general label space voting-based differentially private federated learning (DPFL) framework is presented. The method includes labeling a first subset of unlabeled data from a first global server, to generate first pseudo-labeled data, by employing a first voting-based DPFL computation where each agent trains a local agent model by using private local data associated with the agent, labeling a second subset of unlabeled data from a second global server, to generate second pseudo-labeled data, by employing a second voting-based DPFL computation where each agent maintains a data-independent feature extractor, and training a global model by using the first and second pseudo-labeled data to provide provable differential privacy (DP) guarantees for both instance-level and agent-level privacy regimes.

    HYBRID MOTION PLANNER FOR AUTONOMOUS VEHICLES
    10.
    发明申请
    HYBRID MOTION PLANNER FOR AUTONOMOUS VEHICLES 有权

    公开(公告)号：US20250115254A1

    公开(公告)日：2025-04-10

    申请号：US18905738

    申请日：2024-10-03

    Applicant: NEC Laboratories America, Inc.

    Inventor： Buyu Liu ,  Francesco Pittaluga ,  Bingbing Zhuang ,  Manmohan Chandraker ,  Samuel Sohn

    IPC: B60W50/00 ,  B60W60/00 ,  G05B13/02

    Abstract: Systems and methods for a hybrid motion planner for autonomous vehicles. A multi-lane intelligent driver model (MIDM) can predict trajectory predictions from collected data by considering adjacent lanes of an ego vehicle. A multi-lane hybrid planning driver model (MPDM) can be trained using open-loop ground truth data and close-loop simulations to obtain a trained MPDM. The trained MPDM can predict planned trajectories with collected data and the trajectory predictions to generate final trajectories for the autonomous vehicles. The final trajectories can be employed to control the autonomous vehicles.

Patent Agency Ranking