Mobile body, method of controlling mobile body, and program

Patent metadata

Field	Value
Publication number	US-12411013-B2
Application number	US-201917299366-A
Country	US
Kind code	B2
Filing date	Dec 3, 2019
Priority date	Dec 10, 2018
Publication date	Sep 9, 2025
Grant date	Sep 9, 2025

Abstract

A mobile body controller according to the present disclosure includes circuitry configured to recognize an environment surrounding a mobile body to be controlled, and change parameters used for self-position estimation by the mobile body based on the recognized environment.

First claim

The invention claimed is:

1. A mobile body controller comprising:
circuitry configured to
recognize an environment surrounding a mobile body to be controlled, and
change one or more parameters to determine a weight of each sensor used for self-position estimation by the mobile body based on a determined class at each point along a planned path of the mobile body through the recognized environment,

wherein the class is determined based on an input image used to recognize the environment,
wherein the determined class of the recognized environment is determined based on a degree of slip associated with a recognized ground surface condition at each point along the planned path of the mobile body, and
wherein the circuitry changes at least one parameter to determine a weight of wheel odometry used for the self-position estimation according to the degree of slip associated with the recognized ground surface condition at each point along the planned path of the mobile body.

2. The mobile body controller according to claim 1 ,
wherein the circuitry recognizes the environment surrounding the mobile body by recognizing a traveling environment in which the mobile body travels.

3. The mobile body controller according to claim 2 ,
wherein the traveling environment includes the planned path from a current position of the mobile body to a target position of the mobile body.

4. The mobile body controller according to claim 1 ,
wherein the determined class of the recognized environment is further determined by recognizing at least one of a presence of buildings around the mobile body or a presence of materials that transmit, reflect, or diffract light around the mobile body.

5. The mobile body controller according to claim 1 ,
wherein the circuitry recognizes the environment surrounding the mobile body by recognizing whether wheels of the mobile body are likely to slip.

6. The mobile body controller according to claim 1 ,
wherein the one or more changed parameters used for self-position estimation further relate to at least one of simultaneous localization and mapping (SLAM), map matching, a laser scanner, or a global positioning system (GPS) used to estimate a position of the mobile body.

7. The mobile body controller according to claim 1 ,
wherein the one or more changed parameters used for self-position estimation relate to a localization profile.

8. The mobile body controller according to claim 1 ,
wherein the environment surrounding the mobile body is recognized using one or more sensors included in the mobile body.

9. A mobile body comprising:
one or more sensors; and
a mobile body controller, the mobile body controller including circuitry configured to
recognize an environment surrounding the mobile body controlled by the mobile body controller, and
change one or more parameters to determine a weight of each sensor used for self-position estimation by the mobile body based on a determined class at each point along a planned path of the mobile body through the recognized environment,
wherein the class is determined based on an input image used to recognize the environment,
wherein the determined class of the recognized environment is determined based on a degree of slip associated with a recognized ground surface condition at each point along the planned path of the mobile body, and
wherein at least one parameter is changed to determine a weight of wheel odometry used for the self-position estimation according to the degree of slip associated with the recognized ground surface condition at each point along the planned path of the mobile body.

10. A mobile body control method comprising:
recognizing an environment surrounding a mobile body to be controlled; and
changing one or more parameters to determine a weight of each sensor used for self-position estimation by the mobile body based on a determined class at each point along a planned path of the mobile body through the recognized environment,
wherein the class is determined based on an input image used to recognize the environment,
wherein the determined class of the recognized environment is determined based on a degree of slip associated with a recognized ground surface condition at each point along the planned path of the mobile body, and
wherein at least one parameter is changed to determine a weight of wheel odometry used for the self-position estimation according to the degree of slip associated with the recognized ground surface condition at each point along the planned path of the mobile body.

11. The mobile body controller according to claim 1 ,
wherein the circuitry is further configured to acquire the input image.

12. The mobile body controller according to claim 1 ,
wherein the circuitry changes the at least one parameter to determine the weight of the wheel odometry used for the self-position estimation such that a covariance of the wheel odometry with the self-position estimation is smaller as the degree of slip decreases.

Assignees

• Sony Group Corp

Inventors

• Takahashi Yusuke
• Watanabe Ryo
• Saito Yukihiro
• Nabeta Masaomi

Classifications

• G05D1/243

  Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals (using passive navigation aids external to the vehicle G05D1/244; using signals from positioning sensors located off-board the vehicle G05D1/249) · CPC title

• G05D1/43

  Control of position or course in two dimensions [2D] · CPC title

• G05D2111/50

  Internal signals, i.e. from sensors located in the vehicle, e.g. from compasses or angular sensors · CPC title

• G05D1/2462

  using feature-based mapping · CPC title

• G05D1/248

  generated by satellites, e.g. GPS · CPC title