-
公开(公告)号：US20240062410A1
公开(公告)日：2024-02-22
申请号：US17891185
申请日：2022-08-19
Applicant: Honda Motor Co., Ltd.
Inventor： Alireza REZAZADEH , Nawid JAMALI , Soshi IBA
CPC classification number: G06T7/73 , G06T7/55 , G06T7/11 , G06V10/50 , G06T2207/20016 , G06T2207/10028 , G06T2207/10024 , G06T2207/20132 , G06T2207/20081
Abstract: A system and method for multimodal object-centric representation learning that include receiving data associated with an image and a depth map of an object. The system and method also include determining an object-surface point cloud based on the image and the depth map. The system and method additionally include determining multi-resolution receptive fields based on the object-surface point cloud. The system and method further include passing the multi-resolution receptive fields through convolutional encoders to learn an object centric representation of the object.
-
公开(公告)号：US20250162169A1
公开(公告)日：2025-05-22
申请号：US18517649
申请日：2023-11-22
Applicant: Honda Motor Co., Ltd.
Inventor： Nawid JAMALI , Hongyu LI , Soshi IBA
IPC: B25J13/08
Abstract: Systems and methods for taxel hyper-resolution output are provided. Tactile sensors contact an object and produce taxel data for each contact made. Taxel data from the tactile sensors is encoded and compared with detailed geometric data of a known object to generate a set of ranked poses. For each pose one or more substantially matching candidate poses from the stored geometric data are generated. Pairs of poses are iteratively compared with pairs of candidate poses to determine the most probable candidate pose for each pose. Taxel hyper-resolution data for determined poses is generated from the detailed geometric data and output for use by downstream systems.
-
公开(公告)号：US20200215685A1
公开(公告)日：2020-07-09
申请号：US16242856
申请日：2019-01-08
Applicant: HONDA MOTOR CO., LTD.
Inventor： Nawid JAMALI , Soshi Iba
Abstract: Methods, grasping systems, and computer-readable mediums storing computer executable code for grasping an object are provided. In an example, a depth image of the object may be obtained by a grasping system. A potential grasp point of the object may be determined by the grasping system based on the depth image. A tactile output corresponding to the potential grasp point may be estimated by the grasping system based on data from the depth image. The grasping system may be controlled to grasp the object at the potential grasp point based on the estimated tactile output.
-
公开(公告)号：US20240371022A1
公开(公告)日：2024-11-07
申请号：US18311024
申请日：2023-05-02
Applicant: Honda Motor Co., Ltd.
Inventor： Hongyu LI , Nawid JAMALI , Snehal DIKHALE , Soshi IBA
Abstract: Systems and methods for visuotactile object pose estimation and shape completion are provided. In one embodiment, a method includes transforming at least one point cloud representation of an object into an input voxel grid of the visualized area of the object. The input voxel grid is a volumetric representation. The method further includes encoding the input voxel grid into a partial latent vector that lies on a partial latent space. The method yet further includes determining a mapping between the partial latent space and a complete latent space based on the sensor data. The method includes predicting a complete latent vector based on the complete latent space. The method also includes estimating a complete shape of an object based on the complete latent space. The method further includes estimating a 6D pose of the object based on the complete latent vector.
-
公开(公告)号：US20230316734A1
公开(公告)日：2023-10-05
申请号：US17710922
申请日：2022-03-31
Applicant: Honda Motor Co., Ltd.
Inventor： Daksh DHINGRA , Nawid JAMALI , Snehal DIKHALE , Karankumar PATEL , Soshi IBA
CPC classification number: G06V10/803 , G06T7/10 , G06V10/82 , G06V20/56 , G06T2207/20084 , G06T2207/30252 , G06T2207/20072
Abstract: Pose fusion estimation may be achieved via a first and second set of sensors receiving a first and second set of data, passing the first and second set of data through a graph-based neural network to generate a set of geometric features to be passed through a pose fusion network to generate a first and second pose estimate. A second portion of the pose fusion network may receive the set of geometric features and generate a second set of geometric features and the second pose estimate based on the set of geometric features. A first portion of the pose fusion network may receive the first set of data and the second set of geometric features and generate the first pose estimate based on a fusion of the first set of data and the second set of geometric features.
-
Patent Agency Ranking
公开(公告)号：US20250137859A1
公开(公告)日：2025-05-01
申请号：US18385541
申请日：2023-10-31
Applicant: Honda Motor Co., Ltd.
Inventor： Hongyu LI , Nawid JAMALI , Soshi IBA
Abstract: A method for a taxel-based tactile sensor system includes receiving a set of taxel data having a subset of tactile data for an object and a subset of contact surface data for the object. The method also includes encoding the tactile data into a tactile embedding with a tactile encoder, and encoding the contact surface data into a surface embedding with a surface encoder. The method also includes computing a matrix of proximity values based on the tactile data encoded in the tactile embedding and contact surface data encoded in the surface embedding, and generating a tactile representation for the taxel data based on the proximity values.
-
公开(公告)号：US20240326256A1
公开(公告)日：2024-10-03
申请号：US18194856
申请日：2023-04-03
Applicant: Honda Motor Co., Ltd.
Inventor： Hifza JAVED , Nawid JAMALI
CPC classification number: B25J11/0015 , B25J11/001 , G06N3/091
Abstract: According to one aspect, behavior generation for situationally-aware social robots may include generating a synthesized behavior based on a latent space representation indicative of a situational context including a situationally-aware social robot and one or more individuals, performing behavior retargeting on the synthesized behavior based on a real behavior from an initial latent space input to generate a retargeted behavior, and performing the retargeted behavior. The generating the synthesized behavior and the performing behavior retargeting may be implemented based on a generative adversarial network (GAN) based network. The GAN based network may be trained using a multimodal human behavioral dataset.
-
公开(公告)号：US20240331279A1
公开(公告)日：2024-10-03
申请号：US18194793
申请日：2023-04-03
Applicant: Honda Motor Co., Ltd.
Inventor： Kunal NANDANWAR , Nawid JAMALI , Hifza JAVED
CPC classification number: G06T17/00 , G06V40/168
Abstract: A system and method for completing three dimensional face reconstruction that includes receiving image data associated with multiple two dimensional non-frontal face images. The system and method also includes analyzing the image data and extracting two dimensional facial features. The system and method additionally includes constructing sparse three dimensional facial feature point clouds based on the two dimensional facial features. The system and method further includes inputting the sparse three dimensional facial feature point clouds into an encoder-decoder architecture to generate a three dimensional facial feature point cloud of complete facial features.
-
公开(公告)号：US20240185052A1
公开(公告)日：2024-06-06
申请号：US17972854
申请日：2022-10-25
Applicant: Honda Motor Co., Ltd.
Inventor： Alireza REZAZADEH , Nawid JAMALI , Soshi IBA
CPC classification number: G06N3/08 , G06K9/6232 , G06K9/6296
Abstract: According to one aspect, a robot for proprioceptive learning may include a set of sensors, a memory, and a processor. The processor may perform receiving a set of sensor reading data from the set of sensors, receiving a set of sensor position data associated with the set of sensors, constructing a first graph representation based on the set of sensor reading data, constructing a second graph representation based on the set of sensor position data, performing message passing operation between nodes of the first graph representation and the second graph representation to update the first graph representation and the second graph representation, and executing a task based on readouts from the updated first graph representation and the updated second graph representation.
-
公开(公告)号：US20220084241A1
公开(公告)日：2022-03-17
申请号：US17372869
申请日：2021-07-12
Applicant: Honda Motor Co., Ltd.
Inventor： Snehal DIKHALE , Karankumar PATEL , Daksh DHINGRA , Soshi IBA , Nawid JAMALI
Abstract: Systems and methods for visuo-tactile object pose estimation are provided. In one embodiment, a computer implemented method includes receiving image data, depth data, and tactile data about the object in the environment. The computer implemented method also includes generating a visual estimate of the object that includes an object point cloud. The computer implemented method further includes generating a tactile estimate of the object that includes a surface point cloud based on the tactile data. The computer implemented method yet further includes estimating a pose of the object based on the visual estimate and the tactile estimate by fusing the object point cloud and the surface point cloud in a 3D space. The pose is a six-dimensional pose.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.014 seconds)
