IP Library › Granted Patent US 12,607,479
Granted Patent B2
US 12,607,479 · App. 18/238,867 · Granted Apr 21, 2026

Moving object, control method of moving object, non-transitory computer-readable storage medium, and moving object control system

Inventor: Ryoji Wakayama (Wako, JP)
Assignee: HONDA MOTOR CO., LTD.
G01C21/3837G01C21/3691G06T7/60G06T7/73G06T2207/10012G06T2207/10028G06T2207/30261
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 12,607,479
App. No.
18/238,867
Granted
Apr 21, 2026
Kind
B2
Abstract

A moving object acquires three-dimensional point cloud data in surroundings of the moving object; and generates a grid map based on the three-dimensional point cloud data, the moving object maps point clouds of the three-dimensional point cloud data to a grid on a horizontal plane parallel to a road surface on which the moving object travels and generates the grid map in which each grid indicates whether a three-dimensional object having a predetermined height or a step exists. The moving object determines, for each grid of the grid map, whether the three-dimensional object exists based on a point density when a point cloud corresponding to each grid of the three-dimensional point cloud data is projected on the horizontal plane.

Claims (43)

1 . A moving object comprising:

one or more processors; and

a memory storing instructions which, when the instructions are executed by the one or more processors, cause the moving object to:

acquire three-dimensional point cloud data in surroundings of the moving object;

generate a grid map based on the three-dimensional point cloud data, wherein causing the moving object to generate the grid map includes mapping point clouds of the three-dimensional point cloud data to a grid on a horizontal plane parallel to a road surface on which the moving object travels and generating the grid map in which each grid indicates whether a three-dimensional object having a predetermined height or a step exists; and

control traveling of the moving object based on the generated grid map, wherein

the instructions cause the moving object to determine, for each grid of the grid map, whether the three-dimensional object exists based on a point density when a point cloud corresponding to each grid of the three-dimensional point cloud data is projected on the horizontal plane,

wherein the instructions cause the moving object to determine whether the three-dimensional object exists on the grid according to a result of counting presence or absence of point clouds having a point density exceeding a predetermined threshold in a first direction in the horizontal plane when the point cloud corresponding to each grid is projected on the horizontal plane, and

wherein the instructions cause the moving object to determine that the three-dimensional object exists on the grid if a difference between a maximum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction and a minimum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction at other positions in a second direction orthogonal to the first direction is greater than a threshold when the point cloud corresponding to each grid is projected on the horizontal plane.

2 . The moving object according to claim 1 , wherein the instructions cause the moving object to determine that the three-dimensional object exists on the grid if a difference between a total of a predetermined number of higher counts obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction at different positions in a second direction orthogonal to the first direction and a total of a predetermined number of lower counts obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction at different positions in the second direction is greater than a threshold when the point cloud corresponding to each grid is projected on the horizontal plane.

3 . The moving object according to claim 1 , wherein the instructions cause the moving object to determine that the three-dimensional object exists on the grid if the difference between a variance value of a position of a point cloud in a specific direction in which a variance of the position of the point cloud is greatest and a variance value of a position of the point cloud in a direction orthogonal to the specific direction is greater than a threshold when the point cloud corresponding to the grid is projected on the horizontal plane.

4 . The moving object according to claim 1 , wherein the instructions cause the moving object to calculate a plurality of eigenvalues by a principal component analysis with respect to a position of a point cloud when the point cloud corresponding to each grid is projected on the horizontal plane, and determine whether the three-dimensional object exists on the grid based on a magnitude relationship between the calculated eigenvalues.

5 . The moving object according to claim 4 , wherein the instructions cause the moving object to determine that the three-dimensional object exists on the grid when at least one or more of the calculated eigenvalues are equal to or less than a predetermined threshold.

6 . The moving object according to claim 1 , wherein the instructions cause the moving object to calculate a variance of the point cloud corresponding to each grid in a height direction orthogonal to the horizontal plane, and further determine whether the three-dimensional object exists based on whether the calculated variance is greater than a predetermined variance threshold.

7 . The moving object according to claim 1 , wherein the instructions cause the moving object to set a height of the moving object as a reference height and removes in advance a point cloud at a predetermined height from the reference height from the point clouds of the three-dimensional point cloud data.

8 . The moving object according to claim 7 , wherein the instructions cause the moving object to add, to the reference height, a height according to a predetermined gradient at which the moving object is travelable and a distance between each grid and the moving object and remove in advance a point cloud at or above the reference height after the addition.

9 . The moving object according to claim 1 , wherein the instructions cause the moving object to acquire the three-dimensional point cloud data using an image captured by an imaging device of the moving object.

10 . The moving object according to claim 1 , wherein the instructions further cause the moving object to determine, for the grid on which the three-dimensional object is determined to exist by mapping the point clouds of the three-dimensional point cloud data to the grid on the horizontal plane and performing predetermined processing, whether the three-dimensional object exists based on a point density when the point cloud corresponding to each grid of the three-dimensional point cloud data is projected on the horizontal plane.

11 . The moving object according to claim 1 , wherein the instructions further cause the moving object to generate a route being a traveling trajectory to avoid an obstacle, using the grid map.

12 . The moving object according to claim 1 , wherein the moving object is a micro mobility vehicle that allows a person to get on.

13 . A control method of a moving object, the control method comprising:

an acquisition step of acquiring three-dimensional point cloud data in surroundings of the moving object; and

a generation step of generating a grid map based on the three-dimensional point cloud data, the generation step including mapping point clouds of the three-dimensional point cloud data to a grid on a horizontal plane parallel to a road surface on which the moving object travels and generating the grid map in which each grid indicates whether a three-dimensional object having a predetermined height or a step exists; and

a controlling step of controlling traveling of the moving object based on the generated grid map, wherein

the generation step includes determining, for each grid of the grid map, whether the three-dimensional object exists based on a point density when a point cloud corresponding to each grid of the three-dimensional point cloud data is projected on the horizontal plane,

wherein the generation step includes determining whether the three-dimensional object exists on the grid according to a result of counting presence or absence of point clouds having a point density exceeding a predetermined threshold in a first direction in the horizontal plane when the point cloud corresponding to each grid is projected on the horizontal plane, and

wherein the generation step includes to determining that the three-dimensional object exists on the grid if a difference between a maximum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction and a minimum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction at other positions in a second direction orthogonal to the first direction is greater than a threshold when the point cloud corresponding to each grid is projected on the horizontal plane.

14 . A non-transitory computer-readable storage medium storing instructions causing the moving object to:

acquire three-dimensional point cloud data in surroundings of the moving object;

generate a grid map based on the three-dimensional point cloud data, wherein causing the moving object to generate the grid map includes mapping point clouds of the three-dimensional point cloud data to a grid on a horizontal plane parallel to a road surface on which the moving object travels and generating the grid map in which each grid indicates whether a three-dimensional object having a predetermined height or a step exists; and

control traveling of the moving object based on the generated grid map, wherein

the instructions cause the moving object to determine, for each grid of the grid map, whether the three-dimensional object exists based on a point density when a point cloud corresponding to each grid of the three-dimensional point cloud data is projected on the horizontal plane,

wherein the instructions cause the moving object to determine whether the three-dimensional object exists on the grid according to a result of counting presence or absence of point clouds having a point density exceeding a predetermined threshold in a first direction in the horizontal plane when the point cloud corresponding to each grid is projected on the horizontal plane, and

wherein the instructions cause the moving object to determine that the three-dimensional object exists on the grid if a difference between a maximum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction and a minimum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction at other positions in a second direction orthogonal to the first direction is greater than a threshold when the point cloud corresponding to each grid is projected on the horizontal plane.

15 . A control system of a moving object, the control system comprising:

one or more processors; and

a memory storing instructions which, when the instructions are executed by the one or more processors, cause the control system to:

acquire three-dimensional point cloud data in surroundings of the moving object;

generate a grid map based on the three-dimensional point cloud data, wherein causing the control system to generate the grid map includes mapping point clouds of the three-dimensional point cloud data to a grid on a horizontal plane parallel to a road surface on which the moving object travels and generating the grid map in which each grid indicates whether a three-dimensional object having a predetermined height or a step exists; and

control traveling of the moving object based on the generated grid map, wherein

the instructions cause the control system to determine, for each grid of the grid map, whether the three-dimensional object exists based on a point density when a point cloud corresponding to each grid of the three-dimensional point cloud data is projected on the horizontal plane,

wherein the instructions cause the control system to determine whether the three-dimensional object exists on the grid according to a result of counting presence or absence of point clouds having a point density exceeding a predetermined threshold in a first direction in the horizontal plane when the point cloud corresponding to each grid is projected on the horizontal plane, and

wherein the instructions cause the control system to determine that the three-dimensional object exists on the grid if a difference between a maximum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction and a minimum value obtained by counting presence or absence of point clouds having a point density exceeding the predetermined threshold in the first direction at other positions in a second direction orthogonal to the first direction is greater than a threshold when the point cloud corresponding to each grid is projected on the horizontal plane.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 15, 2024
From: WAKAYAMA, RYOJI
To: HONDA MOTOR CO., LTD.
Reel/Frame 066785/0693 →
Priority Claims (1)
JP 2022-153977 · Sep 27, 2022 · national
Continuity (1)
Related Publication 20240102824A1 · Mar 28, 2024
References Cited (21)
US 11077847B2 · Takayanagi et al. · 2021 [cited by applicant]
US 20200202107A1 · Ozkucur · 2020 [cited by examiner]
US 20220289237A1 · Vu · 2022 [cited by examiner]
CN 114397654B · 2022 [cited by examiner]
JP 2014006588A · 2014 [cited by applicant]
JP 2014174275A · 2014 [cited by applicant]
JP 2018031753A · 2018 [cited by applicant]
JP 2019079375A · 2019 [cited by applicant]
JP 2022541656A · 2022 [cited by applicant]
WO 2018038257A1 · 2018 [cited by applicant]
WO 2021021672A2 · 2021 [cited by applicant]
Fan, H., Yao, W., & Tang, L. (2013). Identifying man-made objects along urban road corridors from mobile LiDAR data. IEEE Geoscience and Remote Sensing Letters, 11(5), 950-954. (Year: 2013). [cited by examiner]
Börcs, A., Nagy, B., & Benedek, C. (2017). Instant object detection in lidar point clouds. IEEE Geoscience and Remote Sensing Letters, 14(7), 992-996. (Year: 2017). [cited by examiner]
Agarwal, P., Husain, A., & Ranjan, R. K. (Nov. 2021). Pole Like Object Detection using PCA inTerrestrial LiDAR System. In Journal of Physics: Conference Series (vol. 2089, No. 1, p. 012004). IOP Publishing. (Year: 2021). [cited by examiner]
Press, T. U. (May 27, 2022). Exploring the limits of shared autonomous micro-mobility. Techxplore.com; Tech Xplore. (Year: 2022). [cited by examiner]
Phetcharat, S., Nagai, M., & Tipdecho, T. (2014). Influence of surface height variance on distribution of ground control points. Journal of Applied Remote Sensing, 8(1), 083684-083684. (Year: 2014). [cited by examiner]
(2014). PCA for 3-dimensional Point Cloud. Algosome.com. (Year: 2014). [cited by examiner]
Oniga, F., & Nedevschi, S. (2009). Processing dense stereo data using elevation maps: Road surface, traffic isle, and obstacle detection. IEEE Transactions on Vehicular Technology, 59(3), 1172-1182. (Year: 2009). [cited by examiner]
Zhou, Y., & Tuzel, O. (2018). Voxelnet: End-to-end learning for point cloud based 3d object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4490-4499). (Year: 2018). [cited by examiner]
Ahmed, S. M., & Chew, C. M. (2020). Density-based clustering for 3d object detection in point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10608-10617). (Year: 2020). [cited by examiner]
Japanese Office Action for Japanese Patent Application No. 2022-153977 mailed Jul. 14, 2025 (partially translated). [cited by applicant]