Patent · US12103162B2 · B2 · US
Robotic device having an image analysis system
- (11) Publication number
- US12103162B2
- (21) Application number
- 17/423,935
- (22) Filing date
- 2020-01-20
- (30) Priority date
- 2019-01-25
- (43) Publication date
- 2024-10-01
- (45) Date of grant
- 2024-10-01
- (51) IPC
- B25J 13/08; G06F 3/01; G06T 7/70
- (52) CPC
- (73) Assignee
- Sony Interactive Entertainment Inc
- (72) Inventors
- Masayoshi Mizuno; Toshiyuki Kurosaki
- (54) Title
- Robotic device having an image analysis system
- (57) Abstract
An application processor processes an application. A sensor processor acquires image data from an image sensor and analyzes the image data. The application processor acquires an image analysis result obtained by the sensor processor and posture information for specifying an orientation of the image sensor. The application processor acquires posture information obtained when the image sensor acquires image data to be analyzed by the sensor processor.
- Full text
- View on Google Patents
Claims (6)
- An apparatus comprising: a robotic device operable to move autonomously and in response to computer controlled instructions; and image analysis system disposed within the robotic device, and including: an application processor that processes an application, a sensor processor that acquires image data from an image sensor and analyzes the image data, a motion control processor that controls motion of the robotic device, where the motion control processor provides: (i) posture information to the sensor processor to identify an orientation of the image sensor when the image sensor acquires the image data to be analyzed, and (ii) the application processor with an image analysis result including position coordinates of a target object in a camera coordinate system having an origin located at the image sensor, and the posture information for specifying an orientation of the image sensor.
- The apparatus according to claim 1, wherein the sensor processor provides the image analysis result to the application processor.
- The apparatus according to claim 1, wherein the sensor processor adds the posture information as metadata to the image analysis result.
- The apparatus according to claim 1, wherein the sensor processor does not provide the image data used in the image analysis to the application processor.
- The apparatus according to claim 1, wherein the application processor designates an image analysis function to be carried out, according to the application to be processed, for the sensor processor.
- The apparatus according to claim 1, wherein the sensor processor is connected to an information sensor for detecting information relating to an imaging target included in image data and analyzes the image data by using the information acquired by the information sensor.
Description
The present invention relates to a system for analyzing image data.
Conventionally, research and development of various types of robots have been performed. PTL 1 discloses a learning method for walking control by a legged mobile robot of the humanoid type. PTL 1 discloses a method for reinforcement-learning of, when a robot cannot stably walk along a walking trajectory given at an initial stage, a stable walking trajectory along which the robot can walk.
[PTL 1] Japanese Patent Laid-Open No. 2005-96068
The robot technology is advancing day by day. Although pet-type robots of the four-legged walking type have been the mainstream of commercial models, in recent years, humanoid robots that perform complicated operations such as dancing are distributed. It is expected that, by increase of an arithmetic operation capacity and improvement of a learning model, a robot itself learns to improve existing functions and acquire new functions.
An action purpose and an action mode of an autonomous robot depend upon an application to be executed. An application for causing a robot to autonomously walk collects and analyzes environmental information around the robot and calculates rotational speeds for a plurality of motors configuring robot joints. A microcomputer for control is provided for each motor, and the plurality of microcomputers supply power according to the calculated rotational speeds to the motors in synchronism with one another.
Citations (116)
- US4163183A
- US4370721A
- US4543639A
- JPS62232006A
- US4833624A
- US5579444A
- JPH024504A
- JPH0212504A
- US4969108A
- EP0528054A1
- US5319443A
- JPH08150581A
- JPH08202679A
- US20140267123A1
- US6584377B2
- US6442451B1
- US20020087232A1
- JP2009238233A
- JP2002239952A
- US20030139848A1
- US7076332B2
- KR20030073447A
- JP2003291084A
- US7076322B2
- US20030230998A1
- US20050119791A1
- US20050232467A1
- US20040122557A1
- JP2004201085A
- US20040199290A1
- US20050113973A1
- JP2005096068A
- US7657345B2
- US20050240412A1
- CN101053953A
- US20070168082A1
- JP2009523623A
- JP2008183690A
- US20090254217A1
- JP5241626B2
- JP2011201007A
- US20110218675A1
- US8326460B2
- JP2011230257A
- US20110288684A1
- US20150158182A1
- US9014848B2
- US9208395B2
- JP2014505934A
- EP2659321B1
- JP2013151045A
- US20150022446A1
- US9306434B2
- US20150190200A1
- US20140336818A1
- US9278454B2
- JP2015013329A
- CN104275698A
- US20150012137A1
- CN105917385A
- US20160332075A1
- US10130883B2
- JP2014097572A
- WO2015145543A1
- US20170017839A1
- US9931753B1
- JP2016063309A
- US10332275B2
- US10631941B2
- WO2017033355A1
- US20180243897A1
- US10796151B2
- JP2018529175A
- CN108369743A
- US20180189565A1
- US10976343B2
- US20180203034A1
- CN107923740A
- US10857672B2
- JP2018535468A
- US20180229367A1
- US20180281187A1
- US20170136626A1
- US20170154453A1
- JP2017156242A
- US20170255181A1
- US20190171210A1
- US20180079076A1
- JP2018043338A
- US10410087B2
- US20180140923A1
- US10881937B2
- CN108079547A
- CN108161931A
- JP2018126796A
- US20180222048A1
- WO2018159177A1
- US20180304467A1
- US10621751B2
- CN109146965A
- US20180365853A1
- DE112018004507T5
- US20200241549A1
- CN108607819A
- US20190366558A1
- US11392103B2
- US11300939B2
- US11314217B2
- US20220080599A1
- US20220130066A1
- US20210283783A1
- US11498211B2
- US20220013090A1
- US20230372014A1
- US20230028793A1
- US20230046365A1
Record as JSON
{
"publication_number": "US12103162B2",
"country": "US",
"kind": "B2",
"title": "Robotic device having an image analysis system",
"abstract": "An application processor processes an application. A sensor processor acquires image data from an image sensor and analyzes the image data. The application processor acquires an image analysis result obtained by the sensor processor and posture information for specifying an orientation of the image sensor. The application processor acquires posture information obtained when the image sensor acquires image data to be analyzed by the sensor processor.",
"claims": [
"1. An apparatus comprising: a robotic device operable to move autonomously and in response to computer controlled instructions; and image analysis system disposed within the robotic device, and including: an application processor that processes an application, a sensor processor that acquires image data from an image sensor and analyzes the image data, a motion control processor that controls motion of the robotic device, where the motion control processor provides: (i) posture information to the sensor processor to identify an orientation of the image sensor when the image sensor acquires the image data to be analyzed, and (ii) the application processor with an image analysis result including position coordinates of a target object in a camera coordinate system having an origin located at the image sensor, and the posture information for specifying an orientation of the image sensor.",
"2. The apparatus according to claim 1, wherein the sensor processor provides the image analysis result to the application processor.",
"3. The apparatus according to claim 1, wherein the sensor processor adds the posture information as metadata to the image analysis result.",
"4. The apparatus according to claim 1, wherein the sensor processor does not provide the image data used in the image analysis to the application processor.",
"5. The apparatus according to claim 1, wherein the application processor designates an image analysis function to be carried out, according to the application to be processed, for the sensor processor.",
"6. The apparatus according to claim 1, wherein the sensor processor is connected to an information sensor for detecting information relating to an imaging target included in image data and analyzes the image data by using the information acquired by the information sensor."
],
"description_excerpt": "The present invention relates to a system for analyzing image data.\n\nConventionally, research and development of various types of robots have been performed. PTL 1 discloses a learning method for walking control by a legged mobile robot of the humanoid type. PTL 1 discloses a method for reinforcement-learning of, when a robot cannot stably walk along a walking trajectory given at an initial stage, a stable walking trajectory along which the robot can walk.\n\n[PTL 1] Japanese Patent Laid-Open No. 2005-96068\n\nThe robot technology is advancing day by day. Although pet-type robots of the four-legged walking type have been the mainstream of commercial models, in recent years, humanoid robots that perform complicated operations such as dancing are distributed. It is expected that, by increase of an arithmetic operation capacity and improvement of a learning model, a robot itself learns to improve existing functions and acquire new functions.\n\nAn action purpose and an action mode of an autonomous robot depend upon an application to be executed. An application for causing a robot to autonomously walk collects and analyzes environmental information around the robot and calculates rotational speeds for a plurality of motors configuring robot joints. A microcomputer for control is provided for each motor, and the plurality of microcomputers supply power according to the calculated rotational speeds to the motors in synchronism with one another.",
"cpc": [
"B25J 13/08",
"B25J 11/00",
"G06F 3/017",
"G06F 3/0346",
"G06T 2200/04",
"G06T 2207/10016",
"G06T 2207/10024",
"G06T 2207/10028",
"G06T 2207/20081",
"G06T 2207/20084",
"G06T 2207/30244",
"G06T 7/246",
"G06T 7/70"
],
"ipc": [
"B25J 13/08",
"G06F 3/01",
"G06T 7/70"
],
"assignees": [
"Sony Interactive Entertainment Inc"
],
"inventors": [
"Masayoshi Mizuno",
"Toshiyuki Kurosaki"
],
"filing_date": "2020-01-20",
"publication_date": "2024-10-01",
"grant_date": "2024-10-01",
"priority_date": "2019-01-25",
"application_number": "US-202017423935-A",
"family_id": "71735584",
"cited_by_count": 1,
"citations": [
"US4163183A",
"US4370721A",
"US4543639A",
"JPS62232006A",
"US4833624A",
"US5579444A",
"JPH024504A",
"JPH0212504A",
"US4969108A",
"EP0528054A1",
"US5319443A",
"JPH08150581A",
"JPH08202679A",
"US20140267123A1",
"US6584377B2",
"US6442451B1",
"US20020087232A1",
"JP2009238233A",
"JP2002239952A",
"US20030139848A1",
"US7076332B2",
"KR20030073447A",
"JP2003291084A",
"US7076322B2",
"US20030230998A1",
"US20050119791A1",
"US20050232467A1",
"US20040122557A1",
"JP2004201085A",
"US20040199290A1",
"US20050113973A1",
"JP2005096068A",
"US7657345B2",
"US20050240412A1",
"CN101053953A",
"US20070168082A1",
"JP2009523623A",
"JP2008183690A",
"US20090254217A1",
"JP5241626B2",
"JP2011201007A",
"US20110218675A1",
"US8326460B2",
"JP2011230257A",
"US20110288684A1",
"US20150158182A1",
"US9014848B2",
"US9208395B2",
"JP2014505934A",
"EP2659321B1",
"JP2013151045A",
"US20150022446A1",
"US9306434B2",
"US20150190200A1",
"US20140336818A1",
"US9278454B2",
"JP2015013329A",
"CN104275698A",
"US20150012137A1",
"CN105917385A",
"US20160332075A1",
"US10130883B2",
"JP2014097572A",
"WO2015145543A1",
"US20170017839A1",
"US9931753B1",
"JP2016063309A",
"US10332275B2",
"US10631941B2",
"WO2017033355A1",
"US20180243897A1",
"US10796151B2",
"JP2018529175A",
"CN108369743A",
"US20180189565A1",
"US10976343B2",
"US20180203034A1",
"CN107923740A",
"US10857672B2",
"JP2018535468A",
"US20180229367A1",
"US20180281187A1",
"US20170136626A1",
"US20170154453A1",
"JP2017156242A",
"US20170255181A1",
"US20190171210A1",
"US20180079076A1",
"JP2018043338A",
"US10410087B2",
"US20180140923A1",
"US10881937B2",
"CN108079547A",
"CN108161931A",
"JP2018126796A",
"US20180222048A1",
"WO2018159177A1",
"US20180304467A1",
"US10621751B2",
"CN109146965A",
"US20180365853A1",
"DE112018004507T5",
"US20200241549A1",
"CN108607819A",
"US20190366558A1",
"US11392103B2",
"US11300939B2",
"US11314217B2",
"US20220080599A1",
"US20220130066A1",
"US20210283783A1",
"US11498211B2",
"US20220013090A1",
"US20230372014A1",
"US20230028793A1",
"US20230046365A1"
]
}
Record 357 of 8,000 in Patents full text (MLC-0201). Request the full dataset.