公开(公告)号：US20190311614A1

公开(公告)日：2019-10-10

申请号：US15946686

申请日：2018-04-05

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Hao Yang ,  Rui Guo ,  Kentaro Oguchi

IPC: G08G1/01 ,  G01C21/34 ,  G08G1/04 ,  G08G1/052 ,  G08G1/0968

Abstract: A connected vehicle includes a first sensor that captures first sensor data to identify one or more dynamics of the connected vehicle, and a second sensor that has a first perspective directed toward an external environment and captures second sensor data reflecting an unconnected vehicle and one or more roadside infrastructures. The second sensor data from the connected vehicle is processed to identify the unconnected vehicle and the one or more roadside infrastructures, and to determine one or more dynamics of the unconnected vehicle. A dynamic road map is generated based on the determined one or more dynamics of the connected vehicle, the one or more dynamics of the unconnected vehicle, and the one or more roadside infrastructures. The first vehicle platform, the second vehicle platform, and/or another vehicle platform relative to the first vehicle platform or the second vehicle platform may be navigated based on the dynamic road map.

公开(公告)号：US20190303686A1

公开(公告)日：2019-10-03

申请号：US15939308

申请日：2018-03-29

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Rui Guo ,  Kentaro Oguchi

IPC: G06K9/00 ,  G06K9/32 ,  G06K9/62 ,  G06T7/70

Abstract: A method extracts a region of interest (ROI) from an image depicting a roadway; executes a first object detector that detects, in the ROI, a first situation object matching a first object type; generates a first object confidence score for the first situation object; executes, in parallel with the first object detector, a second object detector that detects, in the ROI, a second situation object matching a second object type different from the first object type; generates a second object confidence score for the second situation object; determines that the first object type and the second object type are associated with a prospective situation category; combines the first object confidence score and the second object confidence score into a situation confidence score corresponding to the prospective situation category; evaluates the situation confidence score to determine that a traffic situation defined by the prospective situation category is depicted in the ROI.

公开(公告)号：US20190221121A1

公开(公告)日：2019-07-18

申请号：US15870874

申请日：2018-01-13

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Rui Guo ,  Kentaro Oguchi

IPC: G08G1/0967 ,  B60W40/04 ,  G08G1/01 ,  G06K9/00 ,  H04W4/46 ,  G08G1/00

CPC classification number: G08G1/096791 ,  B60W40/04 ,  B60W2550/20 ,  B60W2550/408 ,  G06K9/00791 ,  G06K9/00798 ,  G06K9/6293 ,  G08G1/0133 ,  G08G1/20 ,  H04W4/46

Abstract: In an example embodiment, a first vehicle platform includes a first sensor that has a first perspective directed toward an external environment and that captures first sensor data reflecting first objects, and a communication unit for receiving second sensor data from a second vehicle platform that reflects second objects included in the external environment. One or more computing devices extract a first set of multi-modal features from the first objects, and a second set of multi-modal features from the second objects in the second image, process the first set of multi-modal features and the second set of multi-modal features using separate machine learning logic to produce a first output and a second output, respectively, generate a similarity score using the first output and the second output; and associate the first and second perspectives using the similarity score.

公开(公告)号：US10248196B2

公开(公告)日：2019-04-02

申请号：US15244975

申请日：2016-08-23

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Emrah Akin Sisbot ,  Kentaro Oguchi

IPC: G06F3/01 ,  B60R1/00 ,  G02B27/01 ,  G06K9/00 ,  G06T7/20 ,  G06T19/00 ,  G06T19/20

Abstract: The disclosure includes embodiments for providing occlusion adjustment for an in-vehicle augmented reality system. A system may include a three-dimensional heads-up display unit (“3D HUD”) installed in a vehicle. The system may include a memory storing instructions that, when executed, cause the system to: display, on the 3D HUD, a first graphic that is viewable by a driver of the vehicle as overlaying the interested object when the driver is looking at the 3D HUD; determine that at least a portion of the interested object is occluded by an occluding object; turn off the first graphic so that the first graphic is not displayed on the 3D HUD; and display, on the 3D HUD, a second graphic that does not overlay the occluding object and visually indicates to the driver the location of the interested object behind the occluding object when the driver is looking at the 3D HUD.

公开(公告)号：US20190014446A1

公开(公告)日：2019-01-10

申请号：US15644197

申请日：2017-07-07

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Sharipad Gade ,  Lewis Tseng ,  Kentaro Oguchi

IPC: H04W4/04 ,  H04B7/26 ,  H04L29/08 ,  G08G1/0967

Abstract: The disclosure includes embodiments for providing a service to a vehicle via a macro-vehicular cloud. A method, according to some embodiments, is implemented by the vehicle which communicatively coupled to the macro-vehicular cloud via a non-infrastructure network. The macro-vehicular cloud includes a plurality of micro-vehicular clouds which each include a set of onboard vehicle computers that are operable to provide a set of computing resources to the macro-vehicular cloud via the non-infrastructure network. The method includes transmitting, via the non-infrastructure network, a wireless message requesting a merge service from the macro-vehicular cloud. The method includes receiving, via the non-infrastructure network, the merge service from the set of computing resources of the macro-vehicular cloud. The merge service includes the macro-vehicular cloud instructing the vehicle to merge into a lane of a roadway.

公开(公告)号：US20180146323A1

公开(公告)日：2018-05-24

申请号：US15358567

申请日：2016-11-22

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Lewis Tseng ,  Kentaro Oguchi

IPC: H04W4/00 ,  H04L29/08 ,  H04W68/00

CPC classification number: H04W4/80 ,  H04L67/1097 ,  H04L67/12 ,  H04W4/029 ,  H04W4/46 ,  H04W68/00 ,  H04W84/005

Abstract: The disclosure includes embodiments for providing a storage service for mobile nodes in a roadway area. A method may include a vehicle communicatively coupled to a mobile node via a non-infrastructure network, wherein the vehicle and the mobile node are present in a roadway area which is partitioned into a plurality of roadway regions which are predetermined and known to the vehicle and the mobile node. The method may include transmitting, by the vehicle via the non-infrastructure network, a wireless message to the mobile node, wherein the wireless message includes content including one or more of an instance of spatial key data describing a particular roadway region of the roadway environment and an identifier of a value stored in a memory present in the particular roadway region described by the spatial data. The method may include receiving, by the mobile node via the non-infrastructure network, the wireless message.

公开(公告)号：US20180053102A1

公开(公告)日：2018-02-22

申请号：US15362799

申请日：2016-11-28

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Eric Martinson ,  Oluwatobi Olabiyi ,  Kentaro Oguchi

IPC: G06N5/04 ,  B60R16/023 ,  G08G1/01 ,  G06N99/00

CPC classification number: G06N5/04 ,  B60R16/0232 ,  B60W40/09 ,  B60W50/0097 ,  B60W2050/0029 ,  B60W2540/00 ,  B60W2550/00 ,  G01C21/3626 ,  G06N20/00 ,  G08G1/0112 ,  G08G1/0116 ,  G08G1/0129 ,  G08G1/0137 ,  G08G1/0141 ,  G08G1/09623 ,  G08G1/096716 ,  G08G1/096741 ,  G08G1/096775

Abstract: By way of example, the technology disclosed by this document may be implemented in a method that includes aggregating local sensor data from vehicle system sensors, detecting a driver action using the local sensor data, and extracting features related to predicting driver action from the local sensor data during the operation of the vehicle. The method may include adapting a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. In some instances, the method may also include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features.

公开(公告)号：US09694496B2

公开(公告)日：2017-07-04

申请号：US14632165

申请日：2015-02-26

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Eric Martinson ,  Emrah Akin Sisbot ,  Veeraganesh Yalla ,  Kentaro Oguchi ,  Yusuke Nakano

IPC: G05B19/04 ,  G05B19/18 ,  B25J9/16 ,  G06F19/00 ,  B25J11/00

CPC classification number: B25J9/1674 ,  B25J9/163 ,  B25J11/009 ,  G06F19/00 ,  G16H10/60 ,  G16H40/63 ,  G16H50/50 ,  Y10S901/01 ,  Y10S901/03 ,  Y10S901/47

Abstract: The disclosure includes methods for determining a current location for a user in an environment; detecting obstacles within the environment; estimating one or more physical capabilities of the user based on an EHR associated with the user; generating, with a processor-based device that is programmed to perform the generating, instructions for a robot to perform a task based on the obstacles within the environment and one or more physical capabilities of the user; and instructing the robot to perform the task.

公开(公告)号：US09517175B1

公开(公告)日：2016-12-13

申请号：US14012170

申请日：2013-08-28

Applicant: Toyota Jidosha Kabushiki Kaisha

Inventor： Emrah Akin Sisbot ,  Kentaro Oguchi ,  Akansel Cosgun

IPC: G09B21/00 ,  A61H3/06

CPC classification number: A61H3/061 ,  G01C1/00 ,  G01C21/20 ,  G06K9/00201 ,  G06K9/00335 ,  G06K9/00362 ,  G06K9/00369 ,  G06K9/4638 ,  G08B6/00

Abstract: The disclosure includes a system and method for providing navigation guidance. The system includes a tracking application and a user. The tracking application determines a location of a user, determines a position of at least one object in proximity to the user, determines a path for the user to avoid the at least one object, generates linear and angular velocities that correspond to the path and generates directions that correspond to the linear and angular velocities. The user can receive the directions as audio instructions or via a tactile belt with motors that vibrate to convey the directions.

Abstract translation: 本公开包括用于提供导航指导的系统和方法。 该系统包括跟踪应用程序和用户。 跟踪应用程序确定用户的位置，确定邻近用户的至少一个对象的位置，确定用户的路径以避免至少一个对象，生成对应于路径并生成的线性和角速度 对应于线性和角速度的方向。 用户可以接收作为音频指令的指示，或者经由具有振动以传送方向的电动机的触觉带。

公开(公告)号：US20160267331A1

公开(公告)日：2016-09-15

申请号：US14645936

申请日：2015-03-12

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Preeti Jayagopi Pillai ,  Veeraganesh Yalla ,  Kentaro Oguchi ,  Hirokazu Nomoto

IPC: G06K9/00 ,  G06T15/06 ,  G06T7/00 ,  G06K9/46 ,  G06K9/62

CPC classification number: G06K9/00791 ,  B60T2201/08 ,  G01C21/26 ,  G06F17/30321 ,  G06K9/00624 ,  G06K9/00798 ,  G06K9/00805 ,  G06K9/4642 ,  G06K2209/23 ,  G06T15/06 ,  G06T2200/04 ,  G06T2207/30252 ,  G06T2207/30256 ,  G06T2207/30261 ,  G06T2210/12 ,  G06T2210/61 ,  G08G1/166

Abstract: The disclosure includes a method that receives a real-time image of a road from a camera sensor communicatively coupled to an onboard computer of a vehicle. The method includes dividing the real-time image into superpixels. The method includes merging the superpixels to form superpixel regions. The method includes generating prior maps from a dataset of road scene images. The method includes drawing a set of bounding boxes where each bounding box surrounds one of the superpixel regions. The method includes comparing the bounding boxes in the set of bounding boxes to a road prior map to identify a road region in the real-time image. The method includes pruning bounding boxes from the set of bounding boxes to reduce the set to remaining bounding boxes. The method may include using a categorization module that identifies the presence of a road scene object in the remaining bounding boxes.

Abstract translation: 本公开包括一种从通信地耦合到车辆的车载计算机的相机传感器接收道路的实时图像的方法。 该方法包括将实时图像划分为超像素。 该方法包括合并超像素以形成超像素区域。 该方法包括从道路场景图像的数据集生成先验地图。 该方法包括绘制一组边界框，其中每个边界框围绕超像素区域中的一个。 该方法包括将所述一组边界框中的边界框与道路先验地图进行比较，以识别实时图像中的道路区域。 该方法包括从边界框组修剪边界框以将集合减少为剩余边界框。 该方法可以包括使用识别剩余边界框中的道路场景对象的存在的分类模块。