IP Library › Granted Patent US 12,585,291
Granted Patent B2
US 12,585,291 · App. 18/546,597 · Granted Mar 24, 2026

Information processing method, processing apparatus, and information processing system, and program

Inventors: Masahiko Toyoshi (Tokyo, JP); Kohei Urushido (Tokyo, JP); Shinichiro Abe (Tokyo, JP); Takuto Motoyama (Tokyo, JP); Masaki Handa (Tokyo, JP)
Assignee: Sony Group Corporation
G05D1/667B64D45/08B64U70/00G05D1/222G05D1/243G05D1/654G06V20/70B64U10/14B64U2101/00B64U2101/30B64U2101/64G05D1/244G05D2105/285G05D2109/254G06V10/25
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 12,585,291
App. No.
18/546,597
Granted
Mar 24, 2026
Kind
B2
Abstract

A configuration is described that is capable of determining a target landing position of a drone according to a sentence indicating a landing position generated by a user. Aspects including identifying an object type of an object contained in a captured image of a camera mounted on a mobile body; sentence analysis processing analyzes a sentence indicating a designated arrival position; word-corresponding subject selection processing collates results of the sentence analysis processing with the object identification processing and selecting a subject corresponding to a word included in the sentence indicating the designated arrival position from the captured image; and target arrival position determination processing extracts an area corresponding to the designated arrival position indicated by the sentence indicating the designated arrival position from the captured image on the basis of a result of word-corresponding subject selection processing, and area determination is made as target arrival position of mobile body.

Claims (95)

1 . An information processing method executed in an information processing apparatus, the information processing method, comprising:

object identification processing of analyzing a captured image captured by a camera mounted on a mobile body and identifying an object type of a subject included in the captured image;

sentence analysis processing of analyzing a sentence indicating a designated arrival position of the mobile body;

word-corresponding subject selection processing of collating a result of the sentence analysis processing with a result of the object identification processing and selecting a subject corresponding to a word included in the sentence indicating the designated arrival position from the captured image;

target arrival position determination processing of extracting an area corresponding to the designated arrival position indicated by the sentence indicating the designated arrival position from the captured image on a basis of a result of the word-corresponding subject selection processing, and determining the area extracted as a target arrival position of the mobile body; and

autonomously navigating to and landing at the target arrival position.

2 . The information processing method according to claim 1 ,

wherein the mobile body is a drone,

wherein the target arrival position of the mobile body is a target landing position of the drone, and

the method further comprising:

determining the target landing position of the drone in the target arrival position determination processing.

3 . The information processing method according to claim 1 ,

wherein the sentence indicating the designated arrival position is a sentence transmitted from an external terminal, and

the method further comprising:

executing analysis processing of the sentence indicating the designated arrival position transmitted from the external terminal in the sentence analysis processing.

4 . The information processing method according to claim 1 ,

wherein the sentence indicating the designated arrival position is a sentence transmitted from a user terminal when a user who requests movement of the mobile body inputs the sentence to the user terminal, and

the method further comprising:

executing analysis processing of the sentence indicating the designated arrival position transmitted from the user terminal in the sentence analysis processing.

5 . The information processing method according to claim 1 , further comprising:

executing morphological analysis of the sentence indicating the designated arrival position in the sentence analysis processing, and

selecting the subject corresponding to the word extracted by the morphological analysis from the captured image in the word-corresponding subject selection processing.

6 . The information processing method according to claim 5 , further comprising:

selecting a subject corresponding to a noun in words analyzed by the morphological analysis from the captured image.

7 . The information processing method according to claim 1 , further comprising:

determining a movement route of the mobile body and the target arrival position by inputting each data of (a) latitude and longitude information or address information of the designated arrival position, and (b) the sentence indicating the designated arrival position, transmitted from the user terminal.

8 . The information processing method according to claim 1 , further comprising:

executing semantic segmentation in the object identification processing.

9 . The information processing method according to claim 1 ,

wherein in the word-corresponding subject selection processing includes

in a case where the subject corresponding to the word included in the sentence indicating the designated arrival position cannot be selected from the captured image, executing processing of searching for a similar word similar to the word included in the sentence indicating the designated arrival position, and selecting a subject corresponding to the similar word from the captured image.

10 . The information processing method according to claim 1 ,

wherein the information processing apparatus is configured inside the mobile body, and

the method further comprising:

receiving the sentence to be analyzed in the sentence analysis processing from a user terminal or an external server.

11 . The information processing method according to claim 1 ,

wherein the information processing apparatus is configured inside the mobile body, and

the method further comprising

executing movement control of moving the mobile body toward the target arrival position determined in the target arrival position determination processing.

12 . The information processing method according to claim 1 ,

wherein the information processing apparatus is configured inside a server capable of communicating with the mobile body, and

the method further comprising

receiving the sentence to be analyzed in the sentence analysis processing from a user terminal.

13 . The information processing method according to claim 1 ,

wherein the information processing apparatus is configured inside a server capable of communicating with the mobile body, and

the method further comprising:

executing processing of transmitting the target arrival position determined in the target arrival position determination processing to the mobile body.

14 . An information processing apparatus, comprising:

processing circuitry configured to

analyze a captured image captured by a camera mounted on a mobile body and identify an object type of a subject included in the captured image;

analyze a sentence indicating a designated arrival position of the mobile body;

collate a result of the sentence analysis with a result of the captured image analysis and select a subject corresponding to a word included in the sentence indicating the designated arrival position from the captured image;

extract an area corresponding to the designated arrival position indicated by the sentence indicating the designated arrival position from the captured image based on a result of the collation, and determine the area extracted as a target arrival position of the mobile body; and

autonomously navigate to and land at the target arrival position.

15 . An information processing system, comprising:

a mobile body,

a user terminal, and

a mobile body management server,

wherein the user terminal transmits a sentence indicating a designated arrival position of the mobile body to the mobile body management server,

the mobile body management server transfers the sentence indicating the designated arrival position received from the user terminal to the mobile body, and

the mobile body including processing circuitry configured to

analyze a captured image captured by a camera mounted on the mobile body and identifying an object type of a subject included in the captured image;

analyze the sentence indicating the designated arrival position received from the mobile body management server;

collate a result of the sentence analysis with a result of the captured image analysis and select a subject corresponding to a word included in the sentence indicating the designated arrival position from the captured image;

extract an area corresponding to the designated arrival position indicated by the sentence indicating the designated arrival position from the captured image based on a result of the collation, and determine the area extracted as a target arrival position of the mobile body; and

autonomously navigate to and land at the target arrival position.

16 . An information processing system, comprising:

a mobile body,

a user terminal, and

a drone management server,

wherein the user terminal transmits a sentence indicating a designated arrival position of the mobile body to the drone management server,

the mobile body transmits a captured image captured by a camera mounted on the mobile body to the drone management server, and

the drone management server includes processing circuitry configured to

analyze the captured image received from the mobile body and identify an object type of a subject included in the captured image;

analyze the sentence indicating the designated arrival position received from the user terminal;

collate a result of the sentence analysis with a result of the captured image analysis and select a subject corresponding to a word included in the sentence indicating the designated arrival position from the captured image;

extract an area corresponding to the designated arrival position indicated by the sentence indicating the designated arrival position from the captured image based on a result of the collation, and determine the area extracted as a target arrival position of the mobile body; and

transmit the determined target arrival position to the mobile body; and

the mobile body autonomously navigates to and lands at the target arrival position.

17 . An information processing system, comprising:

a mobile body, and

a user terminal,

wherein a user terminal transmits a sentence indicating a designated arrival position of the mobile body to the mobile body, and

the mobile body includes processing circuitry configured to

analyze a captured image captured by a camera mounted on a mobile body and identify an object type of a subject included in the captured image;

analyze a sentence indicating a designated arrival position of the mobile body;

collate a result of the sentence analysis with a result of the captured image analysis and select a subject corresponding to a word included in the sentence indicating the designated arrival position from the captured image;

extract an area corresponding to the designated arrival position indicated by the sentence indicating the designated arrival position from the captured image based on a result of the collation, and determine the area extracted as a target arrival position of the mobile body; and

autonomously navigate to and land at the target arrival position.

18 . A non-transitory computer-readable storage medium storing computer-readable instructions thereon which, when executed by an information processing apparatus, causes the information processing apparatus to perform a method, the method comprising:

object identification processing of analyzing a captured image captured by a camera mounted on a mobile body and identifying an object type of a subject included in the captured image;

sentence analysis processing of analyzing a sentence indicating a designated arrival position of the mobile body;

word-corresponding subject selection processing of collating a result of the sentence analysis processing with a result of the object identification processing and selecting a subject corresponding to a word included in the sentence indicating the designated arrival position from the captured image;

target arrival position determination processing of extracting an area corresponding to the designated arrival position indicated by the sentence indicating the designated arrival position from the captured image on a basis of a result of the word-corresponding subject selection processing, and determining the area extracted as a target arrival position of the mobile body; and

autonomously navigating to and landing at the target arrival position.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 16, 2023
From: TOYOSHI, MASAHIKO; URUSHIDO, KOHEI; ABE, SHINICHIRO; MOTOYAMA, TAKUTO; HANDA, MASAKI
To: SONY GROUP CORPORATION
Reel/Frame 064601/0473 →
Priority Claims (1)
JP 2021-030399 · Feb 26, 2021 · national
Continuity (1)
Related Publication 20240142995A1 · May 2, 2024
References Cited (13)
US 20170045894A1 · Canoy et al. · 2017 [cited by applicant]
CN 118506102A · 2024 [cited by examiner]
JP 2018506475A · 2018 [cited by applicant]
JP 2020057225A · 2020 [cited by applicant]
JP 2020108981A · 2020 [cited by applicant]
JP 2020138618A · 2020 [cited by applicant]
JP 2020138681A · 2020 [cited by applicant]
KR 1020190057824A · 2019 [cited by applicant]
KR 102167745B1 · 2020 [cited by applicant]
Stefanie Tellex, Thomas Kollar, Steven Dickerson, Matthew R. Walter, Ashis Gopal Banerjee, Seth Teller, and Nicholas Roy. Understanding natural language commands for robotic navigation and mobile manipulation. In AAAI C… [cited by examiner]
Siddharth Karamcheti, Edward C. Williams, Dilip Arumugam, Mina Rhee, Nakul Gopalan, Lawson L.S. Wong, and Stefanie Tellex. A tale of two DRAGGNs: A hybrid approach for interpreting action-oriented and goal-oriented inst… [cited by examiner]
B. Huang, D. Bayazit, D. Ullman, N. Gopalan and S. Tellex, “Flight, Camera, Action! Using Natural Language and Mixed Reality to Control a Drone,” 2019 International Conference on Robotics and Automation (ICRA), Montreal… [cited by examiner]
International Search Report and Written Opinion mailed on Mar. 1, 2022, received for PCT Application PCT/JP2022/001991, filed on Jan. 20, 2022, 8 pages including English Translation. [cited by applicant]