阅读说明：本技术 一种基于PointNet的自主导航机器人及其导航方法 (Autonomous navigation robot based on PointNet and navigation method thereof ) 是由 孔令华 游通飞 刘文玉 殷江 练国富 杨金伟 邹诚 于 2019-11-25 设计创作，主要内容包括：本申请提供了一种基于PointNet的自主导航机器人及其导航方法,涉及自主导航领域。该自主导航机器人包括：底盘、设置在所述移动底盘上的供能装置、三维激光雷达、处理装置、移动装置,所述供能装置被配置为为整个自主导航机器人提供能量,所述三维激光雷达被配置为生成点云分割数据、并根据所述点云分割数据进行自主导航和避障,所述处理装置被配置为根据所述三维激光雷达的导航指令和避障指令驱动移动装置进行移动和避障。本申请可以很好的反映实际环境,提高了导航的准确率和避障的成功率。(The application provides an autonomous navigation robot based on PointNet and a navigation method thereof, and relates to the field of autonomous navigation. The autonomous navigation robot includes: the system comprises a chassis, an energy supply device, a three-dimensional laser radar, a processing device and a moving device, wherein the energy supply device is arranged on the moving chassis and is configured to provide energy for the whole autonomous navigation robot, the three-dimensional laser radar is configured to generate point cloud segmentation data and conduct autonomous navigation and obstacle avoidance according to the point cloud segmentation data, and the processing device is configured to drive the moving device to move and avoid an obstacle according to a navigation instruction and an obstacle avoidance instruction of the three-dimensional laser radar. The method and the device can well reflect the actual environment, and improve the accuracy of navigation and the success rate of obstacle avoidance.)

1. An autonomous navigation robot based on PointNet, comprising:

the robot comprises a chassis (7), an energy supply device (6), a three-dimensional laser radar (4), a processing device (3) and a moving device (1), wherein the energy supply device (6) is arranged on the moving chassis (7) and is configured to provide energy for the whole autonomous navigation robot, the three-dimensional laser radar (4) is configured to generate point cloud segmentation data and conduct autonomous navigation and obstacle avoidance according to the point cloud segmentation data, and the processing device (3) is configured to drive the moving device (1) to move and avoid obstacles according to a navigation instruction and an obstacle avoidance instruction of the three-dimensional laser radar (4).

2. The autonomous navigational robot of claim 1, wherein the three-dimensional lidar is to generate navigational instructions and/or obstacle avoidance instructions comprising:

acquiring surrounding environment data in real time;

converting the environmental data into three-dimensional point cloud data;

training the three-dimensional point cloud data into point cloud segmentation data through a PointNet framework;

and generating a navigation instruction and/or an obstacle avoidance instruction according to the point cloud segmentation data.

3. The autonomous navigation robot according to claim 1, further comprising an emergency stop device (2) provided on the chassis (7) for braking in case of an emergency of the autonomous navigation robot.

4. The autonomous navigation robot according to any of claims 1 to 3, further comprising a height bracket (5) disposed on the chassis (7), wherein the three-dimensional lidar (4) is disposed above the height bracket (5) to improve a field of view of the three-dimensional lidar.

5. The autonomous navigational robot of claim 4, wherein the height support is a telescoping support.

6. A navigation method of an autonomous navigation robot based on PointNet is characterized by comprising the following steps:

the three-dimensional laser radar generates point cloud segmentation data through a PointNet frame;

the three-dimensional laser radar generates a navigation instruction and/or an obstacle avoidance instruction according to the point cloud segmentation data, and sends the navigation instruction and/or the obstacle avoidance instruction to a processing device;

and the processing device controls the mobile device to move and/or avoid the obstacle according to the navigation instruction and/or the obstacle avoidance instruction.

7. The navigation method of claim 6, wherein the three-dimensional lidar generates point cloud segmentation data via a PointNet framework, comprising:

acquiring surrounding environment data in real time;

converting the environmental data into three-dimensional point cloud data;

and training the three-dimensional point cloud data into point cloud segmentation data through a PointNet framework.

8. The navigation method of claim 6, further comprising:

when the autonomous navigation robot has an emergency, the autonomous navigation robot brakes by arranging an emergency stop device on the chassis.

9. The navigation method according to any one of claims 6 to 8, further comprising:

and placing the three-dimensional laser radar on a height support arranged on the chassis, and increasing the height of the three-dimensional laser radar to improve the visual field of the three-dimensional laser radar.

10. The navigation method of claim 9, wherein the height stand is a telescoping stand.

Technical Field

The application belongs to the field of autonomous navigation, and particularly relates to an autonomous navigation robot based on PointNet and a navigation method thereof.

Background

With the continuous development of technology, people's life is more and more convenient, and the self-contained navigation robot is a very obvious example, such as: the sweeping robot can automatically sweep dust at all positions of a family, saves fatigue of bending over for people, but the existing autonomous navigation robot usually uses a single-line laser radar, and a map scanned in the working process lacks environment semantic information.

Disclosure of Invention

The embodiment of the invention mainly aims to provide the autonomous navigation robot based on the PointNet and the navigation method thereof.

In a first aspect, an autonomous navigation robot based on PointNet is provided, which includes:

the system comprises a chassis 7, an energy supply device 6 arranged on the moving chassis 7, a three-dimensional laser radar 4, a processing device 3 and a moving device 1, wherein the energy supply device 6 is configured to provide energy for the whole autonomous navigation robot, the three-dimensional laser radar 4 is configured to generate point cloud segmentation data and conduct autonomous navigation and obstacle avoidance according to the point cloud segmentation data, and the processing device 3 is configured to drive the moving device 1 to move and avoid obstacles according to navigation instructions and obstacle avoidance instructions of the three-dimensional laser radar 4.

In one possible implementation manner, the three-dimensional lidar generates a navigation instruction and/or an obstacle avoidance instruction, and includes:

acquiring surrounding environment data in real time;

converting the environmental data into three-dimensional point cloud data;

training the three-dimensional point cloud data into point cloud segmentation data through a PointNet framework;

and generating a navigation instruction and/or an obstacle avoidance instruction according to the point cloud segmentation data.

In another possible implementation manner, the autonomous navigation robot further comprises an emergency stop device 2, which is arranged on the chassis 7 and is used for braking when an emergency situation occurs in the autonomous navigation robot.

In yet another possible implementation manner, the autonomous navigation robot further includes a height bracket 5 disposed on the chassis 7, and the three-dimensional laser radar 4 may be disposed on the height bracket 5 to improve the field of view of the three-dimensional laser radar.

In yet another possible implementation, the height bracket is a telescoping bracket.

In a second aspect, a navigation method of an autonomous navigation robot based on PointNet is provided, the navigation method comprising:

the three-dimensional laser radar generates point cloud segmentation data through a PointNet frame;

the three-dimensional laser radar generates a navigation instruction and/or an obstacle avoidance instruction according to the point cloud segmentation data, and sends the navigation instruction and/or the obstacle avoidance instruction to a processing device;

and the processing device controls the mobile device to move and/or avoid the obstacle according to the navigation instruction and/or the obstacle avoidance instruction.

In one possible implementation, the generating of the point cloud segmentation data by the three-dimensional laser radar through a PointNet framework includes:

acquiring surrounding environment data in real time;

converting the environmental data into three-dimensional point cloud data;

and training the three-dimensional point cloud data into point cloud segmentation data through a PointNet framework.

In yet another possible implementation manner, the navigation method further includes:

when the autonomous navigation robot has an emergency, the autonomous navigation robot brakes by arranging an emergency stop device on the chassis.

In yet another possible implementation, the method further includes:

and placing the three-dimensional laser radar on a height support arranged on the chassis, and increasing the height of the three-dimensional laser radar to improve the visual field of the three-dimensional laser radar.

In yet another possible implementation, the height bracket is a telescoping bracket.

The beneficial effect that technical scheme that this application provided brought is: the method can well reflect the actual environment, and improve the accuracy of navigation and the success rate of obstacle avoidance.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.

Fig. 1 is a structural diagram of an autonomous navigation robot based on PointNet according to an embodiment of the present invention;

in the figure: 1-a mobile device; 2-emergency stop device; 3-a processing device; 4-three-dimensional laser radar; 5-height support; 6-energy supply device; 7-chassis.

Fig. 2 is a flowchart of a navigation method of an autonomous navigation robot based on PointNet according to an embodiment of the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar modules or modules having the same or similar functionality throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present invention.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, modules, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, modules, components, and/or groups thereof. It will be understood that when a module is referred to as being "connected" or "coupled" to another module, it can be directly connected or coupled to the other module or intervening modules may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

The technical solutions of the present application and the technical solutions of the present application, for example, to solve the above technical problems, will be described in detail with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.