-
公开(公告)号：US11600078B2
公开(公告)日：2023-03-07
申请号：US17198773
申请日：2021-03-11
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui
Abstract: An information processing apparatus recognizes a target within an actual image by executing processing of a neural network. The information processing apparatus obtains intermediate outputs which correspond to the actual image and a computer graphics (CG) image and which are from a hidden layer when each of the actual image and the CG image has been separately input to the neural network, and causes the neural network to perform learning with use of an evaluation values based on a first evaluation function and a second evaluation function, the first evaluation function causing the evaluation value to decrease as a difference between a recognition result and training data decreases, the second evaluation function causing the evaluation value to decrease as a difference between the intermediate outputs corresponding to the actual image and the CG image decreases.
-
公开(公告)号：US11541908B2
公开(公告)日：2023-01-03
申请号：US16620906
申请日：2018-06-15
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui , Kentaro Ishisaka , Nobuyuki Watanabe , Kovi Ahego , Christopher Lang , Liyan Liu , Yo Ito , Hirotaka Uchitomi
IPC: G01C22/00 , G05D1/00 , B60W60/00 , B60H1/00 , B60R25/01 , B60R25/24 , G01C21/34 , G06Q10/04 , G06Q30/02 , G06Q50/30
Abstract: An information processing system includes an acquirer configured to acquire a boarding request, a deriver configured to derive, when an action schedule of an automatic driving vehicle includes a standby state based on a boarding request acquired by the acquirer, a usage charge of the automatic driving vehicle reflecting a cost generated in a traveling state in which the automatic driving vehicle carries a user and travels and a cost generated in the standby state, and an output configured to output information including the usage charge derived by the deriver.
-
公开(公告)号：US11518383B2
公开(公告)日：2022-12-06
申请号：US16250533
申请日：2019-01-17
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui
Abstract: There is provided a travel reference line determination system and an automatic driving system capable of determining a travel reference line of a vehicle appropriately even under conditions where information representing the track environment of the vehicle is hard to get. An ECU of an automatic driving system calculates a model y coordinate value ymw_i using a map in FIG. 4 (Step 12), calculates an estimated y coordinate value y_i using track environment data D_info (Step 11), calculates curvature C so that an error between the model y coordinate value ymw_i and the estimated y coordinate value y_i may be minimized (Step 18), calculates a travel trajectory Xf using the curvature C (Step 4), and executes automatic driving control using the travel trajectory Xf (Steps 31 to 33).
-
公开(公告)号：US20220318972A1
公开(公告)日：2022-10-06
申请号：US17703282
申请日：2022-03-24
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui
Abstract: An information processing apparatus is provided. The apparatus comprises an image acquisition unit that acquires time-series images by an imaging unit; and a processing unit that performs image processing, generates a plurality of shifted images obtained by shifting a reference image acquired before a target image among the time-series images in an up-down direction by a plurality of types of different shift amounts, and specifies a correction amount by a pitch of the imaging unit on the basis of a difference between each of the plurality of shifted images and the target image.
-
公开(公告)号：US20220283636A1
公开(公告)日：2022-09-08
申请号：US17684050
申请日：2022-03-01
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui , Masamitsu Tsuchiya , Yutaka Nishizaki
Abstract: A calibration device for calibrating line-of-sight detection processing based on an image of a face of a user includes an instruction unit configured to instruct the user to look at each of a plurality of positions, and an acquisition unit configured to acquire, for each of the plurality of positions, the image of the face of the user looking at each position. The instruction unit is configured to, when giving an instruction to look at a position that is not in front of the user of the plurality of positions without moving the face, give an instruction to look in front of the user each time a position at which the user is instructed to look switches from one position that is not in front of the user to another position that is not in front of the user.
-
Patent Agency Ranking
公开(公告)号：US20220242363A1
公开(公告)日：2022-08-04
申请号：US17585617
申请日：2022-01-27
Applicant: HONDA MOTOR CO., LTD.
Inventor： Shinsuke Odai , Yuji Yasui , Kenji Komori , Yosuke Sakamoto , Yosuke Koike , Kenshi Torikai
Abstract: A vehicle seatbelt device of an embodiment includes a recognizer that recognizes circumstances around a vehicle, a determiner that determines the state of the vehicle, a seatbelt that restrains a portion of the body of a driver of the vehicle, a tension adjustment mechanism that is able to adjust the tension of the seatbelt, a determiner that determines whether or not driving of the driver is a preferable method of driving on the basis of the circumstances recognized by the recognizer and the state determined by the determiner, and a controller that controls the tension adjustment mechanism such that a tension of the seatbelt varies when the determiner determines that driving of the driver is the preferable method of driving.
-
公开(公告)号：US11370420B2
公开(公告)日：2022-06-28
申请号：US16822050
申请日：2020-03-18
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui , Umiaki Matsubara
Abstract: A vehicle control device comprising a processor configured to recognize a surrounding environment of a vehicle and perform driving control according to speed control and steering control of the vehicle on the basis of a recognition result of the recognizer. The processor is configured to recognize a physical object present on a route of the vehicle on the basis of an image representing a space in a traveling direction of the vehicle and determine whether or not the physical object is a specific obstacle that hinders traveling in a lane where the vehicle is currently traveling. The processor is further configured to start a lane change execution possibility determination before determining whether the specific obstacle hinders travel or simultaneously with a start of the determining in a case where the physical object and the vehicle is allowed to make the lane change.
-
公开(公告)号：US11338803B2
公开(公告)日：2022-05-24
申请号：US16711634
申请日：2019-12-12
Applicant: HONDA MOTOR CO., LTD.
Inventor： Kosuke Nakanishi , Yuji Yasui , Hideki Matsunaga , Takeru Goto , Yuki Ichino
Abstract: An ECU of an automated drive device determines a future traveling track for a vehicle using a first straight line that extends in a forward direction of the vehicle, a second straight line that extends along a second course, and a curved track that extends between a first predetermined point on the first straight line and a second predetermined point on the second straight line. After determination of the future traveling track, the vehicle turns to the right in an intersection during actual traveling on the traveling track, if a median strip is present in a course of the vehicle, a changed track is calculated so as to avoid interference of the vehicle with the median strip.
-
公开(公告)号：US11138756B2
公开(公告)日：2021-10-05
申请号：US16837483
申请日：2020-04-01
Applicant: SENSETIME GROUP LIMITED , HONDA MOTOR CO. LTD.
Inventor： Yingjie Cai , Shinan Liu , Xingyu Zeng , Junjie Yan , Xiaogang Wang , Atsushi Kawamura , Yuji Yasui , Tokitomo Ariyoshi , Yuji Kaneda , Yuhi Goto
Abstract: A 3D object detection method includes: obtaining two-dimensional (2D) coordinates of at least one predetermined key point of a target object in an image to be processed; constructing a pseudo 3D detection body of the target object in a 2D space according to the 2D coordinates of the at least one predetermined key point; obtaining depth information of a plurality of vertices of the pseudo 3D detection body; and determining a 3D detection body of the target object in a 3D space according to the depth information of the plurality of vertices of the pseudo 3D detection body.
-
公开(公告)号：US20210295063A1
公开(公告)日：2021-09-23
申请号：US17198773
申请日：2021-03-11
Applicant: HONDA MOTOR CO., LTD.
Inventor： Yuji Yasui
Abstract: An information processing apparatus recognizes a target within an actual image by executing processing of a neural network. The information processing apparatus obtains intermediate outputs which correspond to the actual image and a computer graphics (CG) image and which are from a hidden layer when each of the actual image and the CG image has been separately input to the neural network, and causes the neural network to perform learning with use of an evaluation values based on a first evaluation function and a second evaluation function, the first evaluation function causing the evaluation value to decrease as a difference between a recognition result and training data decreases, the second evaluation function causing the evaluation value to decrease as a difference between the intermediate outputs corresponding to the actual image and the CG image decreases.
-
-
-
-
-
-
-
-
-
Search Results
151
records
(took 0.029 seconds)
