IP Library Granted Patent US 12,228,933
Granted Patent B2
US 12,228,933 · App. 17/575,606 · Granted Feb 18, 2025

Autonomous work machine, control device, autonomous work machine control method, control device operation method, and storage medium

Inventors: Takamasa Udagawa (Wako, JP); Makoto Yamamura (Wako, JP); Hiroto Takahashi (Wako, JP); Masaya Honji (Wako, JP)
Assignee: HONDA MOTOR CO., LTD.
G05D1/0214G05D1/0234G05D1/0246G05D1/2295G06T1/0007G06T7/70G06T2207/30204
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,228,933
App. No.
17/575,606
Granted
Feb 18, 2025
Kind
B2
Abstract

An autonomous work machine that works in a work area, the autonomous work machine comprising: a storage unit that stores past captured images including one or more markers arranged to define the work area; a specifying unit that specifies a past captured image stored in the storage unit and similar to a current captured image captured by an image capturing unit; and a control unit that controls the autonomous work machine based on the past captured image specified by the specifying unit.

Claims (49)

1. An autonomous work machine that works in a work area, the autonomous work machine comprising:

at least one processor circuit with a memory;

a plurality of past captured images including one or more markers arranged to define the work area stored in the memory;

instructions that, when executed by the processor circuit, cause the at least one processor circuit to at least:

specify a past captured image of the past captured images stored in the memory and similar to a current captured image captured by an image capturing unit;

detect a marker in the current captured image and the specified past captured image; and

determine whether the marker is missing in the current captured image with respect to the specified past captured image based on a detection result from the current captured image and a detection result from the specified past captured image similar to the current captured image, and

when it is determined that the marker is missing, superimpose, on the current captured image and as a virtual marker, a corresponding marker in the specified past captured image,

wherein the instructions, when executed by the processor circuit, further cause the at least one processor circuit to at least:

stop, move backward, or turn the autonomous work machine when a distance from the autonomous work machine to a virtual line connecting a plurality of markers detected from the current captured image becomes equal to or less than a first threshold, and

stop, move backward, or turn the autonomous work machine when a distance from the autonomous work machine to a virtual line connecting a marker of the plurality of markers detected from the current captured image and the virtual marker is equal to or less than a second threshold larger than the first threshold.

2. The autonomous work machine according to claim 1 , wherein the instructions, when executed by the processor circuit, further cause the at least one processor circuit to at least, in a case where a plurality of markers have been detected from the specified past captured image, set a virtual line connecting the plurality of markers, wherein the autonomous work machine is controlled such that the autonomous work machine does not deviate to a region beyond the virtual line set.

3. The autonomous work machine according to claim 2 , wherein

a marker included in the specified past captured image and distance information from the autonomous work machine is stored in association with the marker, and

the virtual line is set based on distance information of each of the plurality of detected markers.

4. The autonomous work machine according to claim 2 , wherein

the past captured image and another past captured image having parallax with respect to the past captured image are stored in the memory in association with each other, and

the instructions, when executed by the processor circuit, further cause the at least one processor circuit to at least,

calculate, based on the past captured image and the other past captured image having parallax with respect to the past captured image, distance information from the autonomous work machine to each of the plurality of detected markers, and

set the virtual line based on the calculated distance information.

5. The autonomous work machine according to claim 2 , wherein

the past captured image and information of a position and orientation of the autonomous work machine at a time of capturing the past captured image are stored in the memory in association with each other, and

the instructions, when executed by the processor circuit, further cause the at least one processor circuit to at least,

acquire the information on the position and orientation of the autonomous work machine corresponding to the specified past captured image; and

acquire, based on the information on the position and orientation of the autonomous work machine and map information including an arrangement position of the marker, distance information to the detected marker from the specified past captured image, and

when a plurality of markers have been detected, the virtual line is set based on the distance information acquired for each of the plurality of markers.

6. The autonomous work machine according to claim 1 , wherein the instructions, when executed by the processor circuit, further cause the at least one processor circuit to at least control the autonomous work machine to stop, move backward, or turn in a case where a distance from the autonomous work machine to the virtual line becomes equal to or less than a threshold.

7. The autonomous work machine according to claim 1 , wherein the instructions, when executed by the processor circuit, further cause the at least one processor circuit to at least:

update information stored in the memory; update the specified past captured image based on a captured image including the one or more markers captured by the image capturing unit.

8. The autonomous work machine according to claim 7 , wherein the information of the specified past captured image is periodically updated.

9. The autonomous work machine according to claim 7 , wherein the information of the specified past captured image is updated for each season or each month.

10. The autonomous work machine according to claim 7 , wherein:

the instructions, when executed by the processor circuit, further cause the at least one processor circuit to at least: set a plurality of virtual line connecting markers,

set the virtual line based on distance information of each of a marker detected from the current captured image and the virtual marker superimposed and arranged on the current captured image, and

wherein the autonomous work machine is controlled so that the autonomous work machine does not deviate to a region beyond the set virtual line.

11. A control method for an autonomous work machine that works in a work area and includes a storage unit that stores past captured images including one or more markers arranged to define the work area, the control method comprising:

specifying a past captured image stored in the storage unit and similar to a current captured image captured by an image capturing unit;

detecting a marker in the current captured image and the specified past captured image;

determining whether the marker is missing in the current captured image with respect to the specified past captured image based on a detection result from the current captured image and a detection result from the specified past captured image similar to the current captured image,

when it is determined that the marker is missing, superimposing, on the current captured image and as a virtual marker, a corresponding marker in the specified past captured image,

stopping, moving backward, or turning the autonomous work machine when a distance from the autonomous work machine to a virtual line connecting a plurality of markers detected from the current captured image becomes equal to or less than a first threshold, and

stopping, moving backward, or turning the autonomous work machine when a distance from the autonomous work machine to a virtual line connecting a marker of the plurality of markers detected from the current captured image and the virtual marker is equal to or less than a second threshold larger than the first threshold.

12. A non-transitory computer readable storage medium storing a program for causing a computer to execute a control method for an autonomous work machine that works in a work area and includes a storage unit that stores past captured images including one or more markers arranged to define the work area, the control method comprising:

specifying a past captured image stored in the storage unit and similar to a current captured image captured by an image capturing unit;

detecting a marker in the current captured image and the specified past captured image;

determining whether the marker is missing in the current captured image with respect to the specified past captured image based on a detection result from the current captured image and a detection result from the specified past captured image similar to the current captured image,

when it is determined that the marker is missing, superimposing, on the current captured image and as a virtual marker, a corresponding marker in the specified past captured image,

stopping, moving backward, or turning the autonomous work machine when a distance from the autonomous work machine to a virtual line connecting a plurality of markers detected from the current captured image becomes equal to or less than a first threshold, and

stopping, moving backward, or turning the autonomous work machine when a distance from the autonomous work machine to a virtual line connecting a marker of the plurality of markers detected from the current captured image and the virtual marker is equal to or less than a second threshold larger than the first threshold.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 10, 2022
From: UDAGAWA, TAKAMASA; YAMAMURA, MAKOTO; TAKAHASHI, HIROTO; HONJI, MASAYA
To: HONDA MOTOR CO., LTD.
Reel/Frame 061726/0094 →
Continuity (2)
Continuation PCTJP2019028901 · Jul 23, 2019
Related Publication 20220137631A1 · May 5, 2022
References Cited (49)
US 8239084B2 · Yamamoto et al. · 2012 [cited by applicant]
US 8385600B2 · Nara et al. · 2013 [cited by applicant]
US 9497901B2 · Willgert · 2016 [cited by applicant]
US 9603300B2 · Pettersson · 2017 [cited by applicant]
US 10054952B2 · Shiromizu et al. · 2018 [cited by applicant]
US 10222797B2 · Yamamura et al. · 2019 [cited by applicant]
US 10315306B2 · Abramson · 2019 [cited by applicant]
US 10872246B2 · Sattar et al. · 2020 [cited by applicant]
US 11164455B2 · Oba · 2021 [cited by applicant]
US 20090028387A1 · Jeong et al. · 2009 [cited by applicant]
US 20100235033A1 · Yamamoto et al. · 2010 [cited by applicant]
US 20100246889A1 · Nara et al. · 2010 [cited by applicant]
US 20140214237A1 · Kini · 2014 [cited by examiner]
US 20150163993A1 · Pettersson · 2015 [cited by applicant]
US 20150201555A1 · Willgert · 2015 [cited by applicant]
US 20160282866A1 · Yamamura et al. · 2016 [cited by applicant]
US 20170113342A1 · Abramson · 2017 [cited by applicant]
US 20170262734A1 · Nakata · 2017 [cited by examiner]
US 20170269603A1 · Shiromizu et al. · 2017 [cited by applicant]
US 20170364088A1 · Grufman · 2017 [cited by examiner]
US 20180151066A1 · Oba · 2018 [cited by applicant]
US 20190073542A1 · Sattar et al. · 2019 [cited by applicant]
US 20190098468A1 · Yamamoto · 2019 [cited by examiner]
US 20190275666A1 · Abramson · 2019 [cited by applicant]
US 20200121888A1 · Haneda et al. · 2020 [cited by applicant]
US 20210027489A1 · Shimamura · 2021 [cited by examiner]
US 20210407290A1 · Oba · 2021 [cited by applicant]
CN 107924617A · 2018 [cited by applicant]
EP 3168705A1 · 2017 [cited by applicant]
EP 3223102A1 · 2017 [cited by applicant]
JP H03071313A · 1991 [cited by applicant]
JP 2007094743A · 2007 [cited by applicant]
JP 2007213293A · 2007 [cited by applicant]
JP 2008065755A · 2008 [cited by applicant]
JP 2009184059A · 2009 [cited by applicant]
JP 2010221859A · 2010 [cited by applicant]
JP 2016186748A · 2016 [cited by applicant]
JP 2017091246A · 2017 [cited by applicant]
JP 2017107456A · 2017 [cited by applicant]
JP 2017158532A · 2017 [cited by applicant]
JP 2019004792A · 2019 [cited by applicant]
WO 2018123598A1 · 2018 [cited by applicant]
WO 2019009164A1 · 2019 [cited by applicant]
WO 2019124225A1 · 2019 [cited by applicant]
WO 2021014585A1 · 2021 [cited by applicant]
Japanese Office Action for Japanese Patent Application No. 2021-534462 mailed Jul. 18, 2023 (partially translated). [cited by applicant]
Japanese Office Action for Japanese Patent Application No. 2021534462 mailed Dec. 1, 2023. [cited by applicant]
Extended European Search Report for European Patent Application No. 19938129.4 mailed Oct. 13, 2022. [cited by applicant]
International Search Report and Written Opinion for PCT/JP2019/028901 mailed Oct. 15, 2019. [cited by applicant]