公开(公告)号：US20190205765A1

公开(公告)日：2019-07-04

申请号：US15858505

申请日：2017-12-29

Applicant: Micron Technology, Inc.

Inventor： Antonino Mondello ,  Alberto Troia

IPC: G06N3/08 ,  G06N3/04 ,  G05D1/00 ,  G05D1/02

CPC classification number: G06N3/088 ,  G05D1/0088 ,  G05D1/0221 ,  G05D1/0223 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0246 ,  G05D1/0255 ,  G05D1/0257 ,  G05D1/0287 ,  G05D2201/0213 ,  G06N3/0454

Abstract: A vehicle having the first ANN model initially installed therein to generate outputs from inputs generated by one or more sensors of the vehicle. The vehicle selects an input based on an output generated from the input using the first ANN model. The vehicle has a module to incrementally train the first ANN model through unsupervised machine learning from sensor data that includes the input selected by the vehicle. Optionally, the sensor data used for the unsupervised learning may further include inputs selected by other vehicles in a population. Sensor inputs selected by vehicles are transmitted to a centralized computer server, which trains the first ANN model through supervised machine learning from sensor received inputs from the vehicles in the population and generates a second ANN model as replacement of the first ANN model previously incrementally improved via unsupervised machine learning in the population.

公开(公告)号：US20180373260A1

公开(公告)日：2018-12-27

申请号：US15634070

申请日：2017-06-27

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Ariel Lipson ,  Michael Slutsky ,  Oded Bialer

IPC: G05D1/02 ,  G01S7/486 ,  G01S17/93 ,  G01S17/10

CPC classification number: G05D1/0231 ,  G01S7/4865 ,  G01S17/10 ,  G01S17/42 ,  G01S17/58 ,  G01S17/936 ,  G05D1/0223 ,  G05D1/024 ,  G05D2201/0213

Abstract: The present application generally relates communications and hazard avoidance within a monitored driving environment. More specifically, the application teaches a system and method for improved target object detection in a vehicle equipped with a laser detection and ranging LIDAR system by transmitting a light pulse for a known duration and comparing a duration of the received pulse to the transmitted pulse in order to determine an orientation of a surface of a target.

公开(公告)号：US20180357601A1

公开(公告)日：2018-12-13

申请号：US16106583

申请日：2018-08-21

Applicant: Cybernet Systems Corp.

Inventor： Charles J. Jacobus ,  Glenn J. Beach ,  Steve Rowe

IPC: G06Q10/08 ,  B66F9/075 ,  G05D1/02 ,  B66F9/24 ,  B66F9/06

CPC classification number: G06Q10/087 ,  B66F9/063 ,  B66F9/0755 ,  B66F9/24 ,  G05D1/024 ,  G05D1/0246 ,  G05D1/0274 ,  G05D1/0278 ,  G05D2201/0216

Abstract: A system for automated inventory management and material handling removes the requirement to operate fully automatically or all-manual using conventional vertical storage and retrieval (S&R) machines. Inventory requests to place palletized material into storage at a specified lot location or retrieve palletized material from a specified lot are resolved into missions for autonomous fork trucks, equivalent mobile platforms, or manual fork truck drivers (and their equipment) that are autonomously or manually executed to effect the request. Automated trucks plan their own movements to execute the mission over the warehouse aisles or roadways sharing this space with manually driven trucks. Automated units drive to planned speed limits, manage their loads (stability control), stop, go, and merge at intersections according human driving rules, use on-board sensors to identify static and dynamic obstacles, and human traffic, and either avoid them or stop until potential collision risk is removed.

公开(公告)号：US20180284786A1

公开(公告)日：2018-10-04

申请号：US15475983

申请日：2017-03-31

Applicant: Neato Robotics, Inc.

Inventor： Lilia Moshkina-Martinson ,  Kristen Holtz

IPC: G05D1/02 ,  A47L5/12 ,  A47L9/00 ,  A47L9/28 ,  A47L9/04 ,  G05D1/00

CPC classification number: G05D1/024 ,  A47L9/2826 ,  A47L9/2831 ,  A47L9/2847 ,  A47L9/2852 ,  A47L9/2857 ,  A47L9/2894 ,  A47L2201/04 ,  A47L2201/06 ,  G05D1/0217 ,  G05D1/0219 ,  G05D1/0274 ,  G05D2201/0215

Abstract: Embodiments provide a plurality of personalized, user selectable styles. Each style is determined by a combination of dimensions. Each style, except the default balanced style, prioritizes one of the dimensions over the other cleaning dimensions. In one embodiment, the styles are cleaning styles and the cleaning dimensions are cleaning time, coverage and obstacle avoidance. The cleaning styles are gentle, fast, thorough and balanced. The gentle style protects expensive furniture, with obstacle avoidance prioritized over cleaning time and coverage. The fast style cleans quickly, prioritizing cleaning time over coverage and obstacle avoidance. The thorough style prioritizes coverage over cleaning time and obstacle avoidance. The balanced style prioritizes all three cleaning dimensions substantially the same. The prioritization is achieved through adjustments to the autonomous robot navigation. User selection of a style can be achieved directly or automatically based on various mechanisms, such as user history.

公开(公告)号：US20180284243A1

公开(公告)日：2018-10-04

申请号：US15475934

申请日：2017-03-31

Applicant: Uber Technologies, Inc.

Inventor： Matthew Shaw Wood

IPC: G01S7/497 ,  G07C5/00 ,  G01S17/93

CPC classification number: G01S17/936 ,  G01S7/4972 ,  G05D1/0234 ,  G05D1/024 ,  G05D2201/0213

Abstract: Systems and methods for automatically calibrating autonomous vehicle sensors are provided. In one example embodiment, a computer implemented method includes obtaining data associated with one or more targets located onboard an autonomous vehicle. The data associated with the targets is acquired via one or more first sensors located onboard a first portion of the autonomous vehicle. The targets are located onboard a second portion of the autonomous vehicle. The method includes determining a movement associated with the second portion of the autonomous vehicle based at least in part on the data associated with the targets. The method includes determining a sensor correction action associated with one or more second sensors located onboard the second portion of the autonomous vehicle based at least in part on the movement. The method includes implementing the sensor correction action for the second sensors located onboard the second portion of the autonomous vehicle.

公开(公告)号：US20180267172A1

公开(公告)日：2018-09-20

申请号：US15717064

申请日：2017-09-27

Applicant: HYUNDAI MOTOR COMPANY ,  KIA MOTORS CORPORATION

Inventor： Young Chul OH ,  Ki Cheol SHIN ,  Byung Yong YOU ,  Myung Seon HEO ,  Ha Yong WOO

IPC: G01S19/45 ,  G01C21/36 ,  G01S17/02 ,  G06K9/00

CPC classification number: G01S19/45 ,  G01C21/30 ,  G01C21/3602 ,  G01C21/3658 ,  G01S17/023 ,  G01S17/42 ,  G01S17/936 ,  G01S19/48 ,  G05D1/0236 ,  G05D1/024 ,  G05D1/0246 ,  G05D1/0278 ,  G05D2201/0213 ,  G06K9/00798

Abstract: The present disclosure provides a system for recognizing a position of a vehicle including: a lane-based position recognition device configured to extract correction information about a heading angle and a lateral position of the vehicle by comparing measured lane information with lane information on an accurate map; a LiDAR-based position recognition device that extracts correction information about a position of the vehicle by detecting an area in consideration of surrounding vehicles and obstacles measured through a LiDAR sensor; and a position assemble device configured to assemble a position based on the correction information about the heading angle and the lateral position of the vehicle, correction information about a heading angle, a longitudinal position and a lateral position of the vehicle from the LiDAR sensor, and correction information about a heading angle, a longitudinal position and a lateral position of the vehicle from GPS.

公开(公告)号：US10077054B2

公开(公告)日：2018-09-18

申请号：US15487184

申请日：2017-04-13

Applicant: Ford Global Technologies, LLC.

Inventor： Bibhrajit Halder ,  Scott Varnhagen

IPC: B60W40/04 ,  G05D1/02 ,  B60W50/00 ,  B60W30/08 ,  B60W30/095

CPC classification number: B60W40/04 ,  B60W30/08 ,  B60W30/0953 ,  B60W30/0956 ,  B60W50/0097 ,  B60W2050/0089 ,  B60W2550/10 ,  B60W2550/30 ,  G05D1/024 ,  G05D1/0246 ,  G05D1/0257 ,  G05D1/027 ,  G05D1/0274

Abstract: The present invention extends to methods, systems, and computer program products for tracking objects within a dynamic environment for improved localization. Sensing devices are utilized to gather data about a vehicle's environment. In cases where the sensor data has become degraded, such as data indicating that lane lines have become degraded, obscured, or nonexistent, the vehicle computer system uses previously detected sensor data to estimate the speed and direction of travel of moving objects. The computer system then estimates the location of the moving objects after a specified period of time based on the estimated speed and direction of the moving object. The computer system utilizes this information to localize the vehicle within the dynamic environment and to control the configuration of the vehicle.

公开(公告)号：US20180210448A1

公开(公告)日：2018-07-26

申请号：US15875235

申请日：2018-01-19

Applicant: LG ELECTRONICS INC.

Inventor： Changhyeon LEE ,  Han Shin KIM ,  Kyuchun CHOI

IPC: G05D1/02 ,  B25J5/00 ,  B25J11/00 ,  B25J15/00 ,  A47L11/40 ,  G06T7/50

CPC classification number: G05D1/0214 ,  A47L11/4052 ,  A47L11/4061 ,  A47L2201/04 ,  B25J5/007 ,  B25J11/0085 ,  B25J15/0019 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0255 ,  G05D1/0274 ,  G05D1/0291 ,  G05D2201/0203 ,  G06T7/50 ,  G06T2207/10028 ,  Y10S901/01 ,  Y10S901/41 ,  Y10S901/49

Abstract: The present disclosure relates to a method of identifying a functional region in a 3-dimensional space and a robot implementing the method, and the robot comprises a sensing module that senses a protrusion located outside a robot and provides height and depth information of the sensed protrusion; a functional unit that provides a predetermined function to the outside; a moving unit that moves the robot; a map storage unit that stores a map required for movement of the robot; and a control unit that controls these components.

公开(公告)号：US20180192845A1

公开(公告)日：2018-07-12

申请号：US15527483

申请日：2016-11-14

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Yu Gu ,  Kai Zhao ,  Yifei Zhang ,  Hongli Ding ,  Ying Zhang

IPC: A47L11/40 ,  A47L11/24 ,  B25J13/08 ,  G05D1/00 ,  G05D1/02 ,  B25J9/16

CPC classification number: A47L11/4091 ,  A47L11/24 ,  A47L11/40 ,  A47L11/4002 ,  A47L11/4005 ,  A47L11/4011 ,  A47L11/4061 ,  A47L2201/022 ,  A47L2201/04 ,  B25J9/1682 ,  B25J13/086 ,  B25J13/089 ,  G05D1/0088 ,  G05D1/0227 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0246 ,  G05D1/0255 ,  G05D1/0257 ,  G05D1/0268 ,  G05D2201/0203

Abstract: The present application discloses a cleaning robot including a primary robot having a first controller configured to control a plurality of first sensors, a first communication module, a first moving apparatus, and a first cleaning assembly; and at least one secondary robot having a second controller configured to control a plurality of second sensors, a second communication module, a second moving apparatus, and a second cleaning assembly.

公开(公告)号：US20180188733A1

公开(公告)日：2018-07-05

申请号：US15855749

申请日：2017-12-27

Applicant: DeepScale, Inc.

Inventor： Forrest Nelson Iandola ,  Donald Benton MacMillen ,  Anting Shen ,  Harsimran Singh Sidhu ,  Daniel Paden Tomasello ,  Rohan Nandkumar Phadte ,  Paras Jagdish Jain

IPC: G05D1/02 ,  G06F17/50

CPC classification number: G05D1/024 ,  G05D1/0246 ,  G05D1/0255 ,  G05D1/0257 ,  G06F17/5009 ,  G06F17/5095 ,  G06N3/0454 ,  G06N3/084 ,  G06N20/00

Abstract: An autonomous control system combines sensor data from multiple sensors to simulate sensor data from high-capacity sensors. The sensor data contains information related to physical environments surrounding vehicles for autonomous guidance. For example, the sensor data may be in the form of images that visually capture scenes of the surrounding environment, geo-location of the vehicles, and the like. The autonomous control system simulates high-capacity sensor data of the physical environment from replacement sensors that may each have lower capacity than high-capacity sensors. The high-capacity sensor data may be simulated via one or more neural network models. The autonomous control system performs various detection and control algorithms on the simulated sensor data to guide the vehicle autonomously.