Obstacle monitoring system, obstacle monitoring apparatus, obstacle monitoring method

Patent metadata

Field	Value
Publication number	US-2025091623-A1
Application number	US-202418820903-A
Country	US
Kind code	A1
Filing date	Aug 30, 2024
Priority date	Sep 15, 2023
Publication date	Mar 20, 2025
Grant date	—

Abstract

An obstacle monitoring system includes: a sensing means; a first obstacle detection means; and a control means for selectively executing a plurality of control modes including a first control mode in which a moving speed of a moving body is a first moving speed and a sensing field of view of the sensing means is a first field of view, and a second control mode in which a moving speed of the moving body is a second moving speed and a sensing field of view of the sensing means is a second field of view. When the first obstacle detection means detects the obstacle while the control means is executing the first control mode, the control means executes the second control mode in such a way as to capture the obstacle within the second field of view.

First claim

What is claimed is:

1 . An obstacle monitoring system comprising
at least one memory storing computer-executable instructions, and at least one processor configured to access the at least one memory and execute the computer-executable instructions to:
detect an obstacle, based on a sensing result from sensing means for sensing an area ahead in a moving direction of a moving body;
selectively execute a plurality of control modes including a first control mode in which a moving speed of the moving body is a first moving speed and a sensing field of view of the sensing means is a first field of view, and a second control mode in which a moving speed of the moving body is a second moving speed being lower than the first moving speed and a sensing field of view of the sensing means is a second field of view being narrower than the first field of view; and
execute the second control mode in such a way as to capture the obstacle within the second field of view, when the obstacle is detected while the first control mode is being executed.

2 . The obstacle monitoring system according to claim 1 , wherein the at least one processor is further configured to execute the instructions to, when the second control mode is being executed, provide a sensing result of the sensing means to a trained neural network, and obtain a detection score for each class of the detected obstacle from the trained neural network.

3 . The obstacle monitoring system according to claim 2 , wherein
a score threshold value is set for each class, and, the at least one processor is further configured to execute the instructions to, when the detection score exceeds the score threshold value in any of the classes, decelerate or stop the moving body.

4 . The obstacle monitoring system according to claim 3 , wherein
a first score threshold value is set as the score threshold value for a class in which movement of the moving body is hindered, and a second score threshold value being higher than the first score threshold value is set as the score threshold value for a class in which movement of the moving body is not hindered.

5 . The obstacle monitoring system according to claim 3 , wherein, in each class, a score threshold value in a case of a bad weather is set lower than a score threshold value in a case of a good weather.

6 . The obstacle monitoring system according to claim 3 , wherein, in each class, a score threshold value when a movement track on which the moving body is currently moving is a curved line is set lower than a score threshold value when the movement track is a straight line.

7 . The obstacle monitoring system according to claim 1 , wherein the control mode is not switched when the detected obstacle is off of a movement track of the moving body.

8 . An obstacle monitoring apparatus comprising
at least one memory storing computer-executable instructions, and at least one processor configured to access the at least one memory and execute the computer-executable instructions to:
perform sensing of an area ahead in a moving direction of a moving body;
detect an obstacle, based on a sensing result;
selectively execute a plurality of control modes including a first control mode in which a moving speed of the moving body is a first moving speed and a sensing field of view is a first field of view, and a second control mode in which a moving speed of the moving body is a second moving speed being lower than the first moving speed and a sensing field of view of the sensing means is a second field of view being narrower than the first field of view; and
execute the second control mode in such a way as to capture the obstacle within the second field of view, when the obstacle is detected while the control means is executing the first control mode.

9 . An obstacle monitoring method comprising, by a computer:
detecting an obstacle, based on a sensing result of sensing means for sensing an area ahead in a moving direction of a moving body; selectively executing a plurality of control modes including a first control mode in which a moving speed of the moving body is a first moving speed and a sensing field of view of the sensing means is a first field of view, and a second control mode in which a moving speed of the moving body is a second moving speed being lower than the first moving speed and a sensing field of view of the sensing means is a second field of view being narrower than the first field of view; and executing the second control mode in such a way as to capture the obstacle within the second field of view, when the obstacle is detected while the first control mode is being executed.

10 . A non-transitory computer readable medium storing a program causing a computer to execute the obstacle monitoring method according to claim 9 .

Assignees

• Nec Corp

Inventors

• Yamanouchi Shingo
• Nomura Toshiyuki
• Abe Junichi
• Noguchi Hidemi
• Ono Yoshimasa
• Fujimoto Tatsuya

Classifications

• B61L23/041

  Obstacle detection · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06V10/82 Primary

  using neural networks · CPC title

• B61L15/0062 Primary

  On-board target speed calculation or supervision · CPC title