Automatic driving wheelchair navigation method and system based on intelligent voice interaction

Abstract

The invention discloses an automatic driving wheelchair navigation method and system based on intelligent voice interaction, and the method comprises the steps: responding to a voice wake-up instruction, and starting a voice interaction system, a visual perception system and a navigation system of an automatic driving wheelchair; calling a voice interaction system to output a navigation destination inquiry instruction, and receiving navigation destination feedback information input by a user; calling a visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and an operation environment; calling a navigation system to mark target position information in the navigation destination feedback information in the three-dimensional semantic point cloud map model; generating a moving path according to the current position information of the automatic driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information; and controlling the automatic driving wheelchair to move according to the moving path. According to the scheme disclosed by the invention, the navigation instruction can be quickly adjusted according to real-time conditions and user requirements, so that the automatic driving wheelchair is flexibly controlled to move.

Description

Technical Field

[0001] The present invention relates to the field of intelligent hardware technology, and in particular to an automatic driving wheelchair navigation method and system based on intelligent voice interaction. Background Art

[0002] Autonomous driving wheelchairs are gradually being used in transportation station scenarios. Although the application technology of autonomous driving wheelchairs has made significant progress, most existing autonomous driving wheelchair navigation systems still rely on predefined navigation tasks and path planning.

[0003] The predefined navigation tasks and path planning have the defect of poor flexibility. In actual use, the autonomous driving wheelchair cannot quickly adjust the navigation instructions according to the real-time situation and user needs, which affects the user experience of the autonomous driving wheelchair. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide an autonomous driving wheelchair navigation method and system based on intelligent voice interaction, which can solve the problem in the prior art that the autonomous driving wheelchair cannot quickly adjust the navigation instructions according to the real-time situation and user needs.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An embodiment of the present invention provides an automatic driving wheelchair navigation method based on intelligent voice interaction, wherein the method comprises:

[0007] In response to the voice wake-up command, the voice interaction system, visual perception system and navigation system of the autonomous driving wheelchair are turned on;

[0008] Calling the voice interaction system to output a navigation destination inquiry instruction, and receiving navigation destination feedback information input by a user;

[0009] Invoking the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and operating environment during movement;

[0010] Marking the target location information in the navigation destination feedback information in the three-dimensional semantic point cloud map model;

[0011] Calling the navigation system to generate a moving path according to the current position information of the autonomous driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information;

[0012] The automatic driving wheelchair is controlled to move according to the moving path.

[0013] Optionally, the step of the voice interaction system outputting a navigation destination inquiry instruction and receiving navigation destination feedback information input by a user comprises:

[0014] a navigation destination inquiry instruction preset in the voice interaction system output, wherein the navigation destination inquiry instruction can guide the user to input navigation destination information conforming to a preset format;

[0015] Monitoring whether the navigation destination feedback information input by the user is received within a preset time;

[0016] If not, the navigation destination inquiry instruction is output again until the navigation destination feedback information input by the user is received.

[0017] Optionally, the step of calling the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and an operating environment during movement includes:

[0018] During the movement, the visual perception system is called to collect the environment perception video stream including the spatial depth information and image color information of the surrounding environment in real time;

[0019] Generating a three-dimensional point cloud map model of the operating environment according to the environment perception video stream;

[0020] An image semantic segmentation algorithm is used to perform semantic segmentation on each frame of the environment perception image in the environment perception video stream, and the segmentation result is rendered onto the three-dimensional point cloud map model of the operating environment to generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment.

[0021] Optionally, the step of generating a three-dimensional point cloud map model of the operating environment according to the environment perception video stream includes:

[0022] Dividing the environment perception video stream into a plurality of single-frame environment perception images;

[0023] For each frame of the environment perception image, construct a corresponding point cloud map according to the spatial depth information and image color information in the environment perception image;

[0024] The point cloud fusion algorithm is used to fuse the point cloud map corresponding to each frame of the environmental perception image to generate a three-dimensional point cloud map model of the operating environment.

[0025] Optionally, before the step of calling the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and an operating environment during movement, the method further includes:

[0026] After receiving the navigation destination feedback information, move at a first speed; wherein the first moving speed is less than the speed at which the automatic driving wheelchair is controlled to move according to the moving path.

[0027] The embodiment of the present invention further provides an autonomous driving wheelchair navigation system based on intelligent voice interaction, which is arranged in an autonomous driving wheelchair, wherein the autonomous driving wheelchair navigation system based on intelligent voice interaction includes: a control system, a voice interaction system, a visual perception system and a navigation system;

[0028] The control system is used to activate the voice interaction system, the visual perception system and the navigation system of the autonomous driving wheelchair in response to a voice wake-up command;

[0029] The voice interaction system is used to output a navigation destination inquiry instruction and receive navigation destination feedback information input by a user;

[0030] The visual perception system is used to generate a three-dimensional semantic point cloud map model containing semantic information and an operating environment during the movement of the autonomous driving wheelchair;

[0031] The navigation system is used to mark the target position information in the navigation destination feedback information sent by the voice interaction system in the three-dimensional semantic point cloud map model; generate a moving path according to the current position information of the autonomous driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information;

[0032] The control system is also used to control the movement of the automatic driving wheelchair according to the moving path sent by the navigation system.

[0033] Optionally, the voice interaction system includes:

[0034] an output module, used for outputting a preset navigation destination inquiry instruction, wherein the navigation destination inquiry instruction can guide the user to input navigation destination information conforming to a preset format;

[0035] The monitoring module is used to monitor whether the navigation destination feedback information input by the user is received within a preset time; if not, the output module is called again to output the navigation destination inquiry instruction until the navigation destination feedback information input by the user is received.

[0036] Optionally, the visual perception system includes:

[0037] A startup module, used to start a preset device to collect an environment perception video stream including spatial depth information and image color information of the surrounding environment in real time;

[0038] A first generating module, used for generating a three-dimensional point cloud map model of the operating environment according to the environment perception video stream;

[0039] The second generation module is used to perform semantic segmentation on each frame of the environment perception image in the environment perception video stream using an image semantic segmentation algorithm, render the segmentation result onto the three-dimensional point cloud map model of the operating environment, and generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment.

[0040] Optionally, the first generating module is specifically used for:

[0041] Dividing the environment perception video stream into a plurality of single-frame environment perception images;

[0042] For each frame of the environment perception image, construct a corresponding point cloud map according to the spatial depth information and image color information in the environment perception image;

[0043] The point cloud fusion algorithm is used to fuse the point cloud map corresponding to each frame of the environmental perception image to generate a three-dimensional point cloud map model of the operating environment.

[0044] Optionally, the control system is further used for:

[0045] After receiving the navigation destination feedback information, the automatic driving wheelchair is controlled to move at a first speed; wherein the first moving speed is less than a speed of moving according to the moving path.

[0046] The embodiment of the present invention also provides an automatic driving wheelchair navigation device based on intelligent voice interaction,

[0047] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of any one of the above-mentioned methods for autonomous driving wheelchair navigation based on intelligent voice interaction are implemented.

[0048] An embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of any one of the above-mentioned methods for navigating an autonomous driving wheelchair based on intelligent voice interaction are implemented.

[0049] The automatic driving wheelchair navigation solution based on intelligent voice interaction provided by the embodiment of the present invention responds to the voice wake-up command, turns on the voice interaction system, visual perception system and navigation system of the automatic driving wheelchair; calls the voice interaction system to output the navigation destination inquiry command, and receives the navigation destination feedback information input by the user; calls the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment during the movement; marks the target position information in the navigation destination feedback information in the three-dimensional semantic point cloud map model; calls the navigation system to generate a moving path based on the current position information of the automatic driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information; and controls the movement of the automatic driving wheelchair according to the moving path. The navigation solution provided by the embodiment of the present invention receives the navigation destination information input by the user in real time according to the voice interaction system, and generates a three-dimensional semantic point cloud map model according to the visual perception system, so that the automatic driving wheelchair can quickly adjust the navigation instructions and plan the navigation path according to the real-time situation and user needs during actual use, so as to realize the flexible control of the automatic driving wheelchair. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flowchart showing a method for navigating an autonomous driving wheelchair based on intelligent voice interaction according to an embodiment of the present application;

[0051] Figure 2 It is a structural block diagram of an automatic driving wheelchair navigation system based on intelligent voice interaction according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0053] The following, in conjunction with the accompanying drawings, describes in detail the autonomous driving wheelchair navigation solution based on intelligent voice interaction provided by the embodiment of the present application through specific embodiments and their application scenarios.

[0054] The automatic driving wheelchair navigation method based on intelligent voice interaction of the embodiment of the present application includes the following steps:

[0055] Step 101: In response to a voice wake-up command, the voice interaction system, visual perception system and navigation system of the autonomous driving wheelchair are turned on.

[0056] The autonomous driving wheelchair navigation method based on intelligent voice interaction in the embodiment of the present application is applied to an autonomous driving wheelchair, in which a control system is provided. The control system can be regarded as an electronic device having the functions of analyzing and scheduling other systems in the autonomous driving wheelchair.

[0057] The voice interaction system is used to interact with the user and obtain the user's navigation destination information; the visual perception system is used to collect environmental information to generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment; the navigation system is used to plan the navigation path based on the navigation destination information and the three-dimensional semantic point cloud map model.

[0058] Step 102: Invoke the voice interaction system to output a navigation destination inquiry instruction, and receive navigation destination feedback information input by the user.

[0059] An optional method in which the voice interaction system outputs a navigation destination query instruction and receives navigation destination feedback information input by the user may include the following sub-steps:

[0060] Sub-step 1: the navigation destination inquiry command preset in the voice interaction system output;

[0061] The navigation destination inquiry instruction can guide the user to input navigation destination information that conforms to a preset format. The navigation destination inquiry instruction is a preset instruction in the voice interaction system. The preset format is a format that can be recognized by the voice interaction system. The specific format can be flexibly set by those skilled in the art, and is not specifically limited in the embodiments of the present application. Sub-step 2: monitoring whether the navigation destination feedback information input by the user is received within a preset time;

[0062] The specific duration indicated by the preset time can be flexibly set by a person skilled in the art, and there is no specific limitation on this in the embodiment of the present application. For example, it can be set to 3 seconds, 5 seconds or 10 seconds.

[0063] Sub-step 3: If not, output the navigation destination inquiry instruction again until the navigation destination feedback information input by the user is received.

[0064] If so, the navigation destination feedback information input by the user is parsed to determine the user's pre-navigation destination.

[0065] If not, it is equivalent to returning to execute sub-step 1 and sub-step 2, and repeating until the navigation destination feedback information input by the user is received (that is, the navigation destination feedback information of the user is effectively obtained), or until the cumulative number of outputting the navigation destination inquiry instruction reaches a preset number.

[0066] Step 103: During the movement, the visual perception system is called to generate a three-dimensional semantic point cloud map model containing semantic information and operating environment.

[0067] After obtaining the user's navigation destination feedback information through the voice interaction system, it is also necessary to build a three-dimensional semantic point cloud map model, which is generated by the visual perception system.

[0068] An optional method of calling the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and operating environment during movement may include the following sub-steps:

[0069] Sub-step 1: During the movement, the visual perception system is called to collect the environment perception video stream including the spatial depth information and image color information of the surrounding environment in real time;

[0070] In the actual implementation process, the visual perception system can use the equipped depth camera and binocular camera devices to obtain the environmental perception video stream including the spatial depth information and image color information of the surrounding environment in real time.

[0071] Sub-step 2: Generate a three-dimensional point cloud map model of the operating environment based on the environment perception video stream;

[0072] An exemplary method of generating a three-dimensional point cloud map model of an operating environment based on an environment perception video stream may be as follows:

[0073] The environment perception video stream is divided into multiple single-frame environment perception images. For each frame of the environment perception image, a corresponding point cloud map is constructed based on the spatial depth information and image color information in the environment perception image. The point cloud map corresponding to each frame of the environment perception image is fused using a point cloud fusion algorithm to generate a three-dimensional point cloud map model of the operating environment.

[0074] The point cloud fusion algorithm used may be any existing appropriate algorithm, and the point cloud fusion algorithm is not specifically limited in the embodiments of the present application.

[0075] Sub-step 3: Use the image semantic segmentation algorithm to perform semantic segmentation on each frame of the environment perception image in the environment perception video stream, render the segmentation result onto the three-dimensional point cloud map model of the operating environment, and generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment.

[0076] Step 104: calling the navigation system to mark the target location information in the navigation destination feedback information in the three-dimensional semantic point cloud map model.

[0077] The voice interaction system of the autonomous driving wheelchair will obtain the user's navigation destination feedback information and send it to the navigation system of the autonomous driving wheelchair. The large language model preset in the navigation system of the autonomous driving wheelchair will process the user's navigation destination feedback information and output the moving target position information of the autonomous driving wheelchair (that is, the navigation destination information of this time).

[0078] Step 105: Call the navigation system to generate a moving path based on the current position information of the autonomous driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information.

[0079] The navigation system of the autonomous driving wheelchair marks the moving target position information of the autonomous driving wheelchair and the current position information of the autonomous driving wheelchair onto the three-dimensional semantic point cloud map model.

[0080] Step 106: Control the automatic driving wheelchair to move according to the moving path.

[0081] The navigation system of the autonomous driving wheelchair plans the moving path information of the autonomous driving wheelchair based on the current position information of the autonomous driving wheelchair, the three-dimensional semantic point cloud map model and the moving target position information, and then sends the moving path information of the autonomous driving wheelchair to the control system of the autonomous driving wheelchair. The control system of the autonomous driving wheelchair controls the autonomous driving wheelchair to complete the entire moving path.

[0082] Steps 101 to 106 are a process for planning a navigation path based on user needs. In the actual implementation process, the user can adjust the navigation destination again during the process of planning a navigation path and moving along the planned navigation path. The autonomous driving wheelchair then returns to execute steps 101 to 106 to replan the moving path of the autonomous driving wheelchair.

[0083] In an optional embodiment, before calling the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and an operating environment during the movement, the method further includes:

[0084] After receiving the navigation destination feedback information, the vehicle moves at a first speed; wherein the first moving speed is less than the speed at which the autonomous driving wheelchair is controlled to move according to the moving path.

[0085] The setting moves at a slower speed in the initial stage of determining the navigation destination feedback information makes it easier for the visual perception system to obtain a more comprehensive environmental perception video stream. Not only that, it can also avoid problems such as blindly moving quickly and causing the autonomous driving wheelchair to collide with obstacles.

[0086] The automatic driving wheelchair navigation method based on intelligent voice interaction provided in the embodiment of the present application responds to the voice wake-up command, turns on the voice interaction system, visual perception system and navigation system of the automatic driving wheelchair; calls the voice interaction system to output the navigation destination inquiry command, and receives the navigation destination feedback information input by the user; calls the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment during the movement; marks the target position information in the navigation destination feedback information in the three-dimensional semantic point cloud map model; calls the navigation system to generate a moving path based on the current position information of the automatic driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information; and controls the movement of the automatic driving wheelchair according to the moving path. The navigation method provided in the embodiment of the present application receives the navigation destination information input by the user in real time based on the voice interaction system, and generates a three-dimensional semantic point cloud map model based on the visual perception system, so that the automatic driving wheelchair can quickly adjust the navigation instructions and plan the navigation path according to the real-time situation and user needs during actual use, thereby realizing flexible control of the automatic driving wheelchair.

[0087] Figure 2 A structural block diagram of a charging path planning device for an autonomous driving wheelchair to implement an embodiment of the present application.

[0088] The automatic driving wheelchair navigation system 20 based on intelligent voice interaction provided in the embodiment of the present application includes: a control system 201, a voice interaction system 202, a visual perception system 203 and a navigation system 204;

[0089] The control system 201 is used to activate the voice interaction system, the visual perception system and the navigation system of the automatic driving wheelchair in response to the voice wake-up command;

[0090] The voice interaction system 202 is used to output a navigation destination inquiry instruction and receive navigation destination feedback information input by the user;

[0091] The visual perception system 203 is used to generate a three-dimensional semantic point cloud map model containing semantic information and operating environment during the movement of the autonomous driving wheelchair;

[0092] The navigation system 204 is used to mark the target position information in the navigation destination feedback information sent by the voice interaction system in the three-dimensional semantic point cloud map model; generate a moving path according to the current position information of the autonomous driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information;

[0093] The control system 201 is also used to control the movement of the automatic driving wheelchair according to the moving path sent by the navigation system.

[0094] Optionally, the voice interaction system includes:

[0095] an output module, used for outputting a preset navigation destination inquiry instruction, wherein the navigation destination inquiry instruction can guide the user to input navigation destination information conforming to a preset format;

[0096] The monitoring module is used to monitor whether the navigation destination feedback information input by the user is received within a preset time; if not, the output module is called again to output the navigation destination inquiry instruction until the navigation destination feedback information input by the user is received.

[0097] Optionally, the visual perception system includes:

[0098] A startup module, used to start a preset device to collect an environment perception video stream including spatial depth information and image color information of the surrounding environment in real time;

[0099] A first generating module, used for generating a three-dimensional point cloud map model of the operating environment according to the environment perception video stream;

[0100] The second generation module is used to perform semantic segmentation on each frame of the environment perception image in the environment perception video stream using an image semantic segmentation algorithm, render the segmentation result onto the three-dimensional point cloud map model of the operating environment, and generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment.

[0101] Optionally, the first generating module is specifically used for:

[0102] Dividing the environment perception video stream into a plurality of single-frame environment perception images;

[0103] For each frame of the environment perception image, construct a corresponding point cloud map according to the spatial depth information and image color information in the environment perception image;

[0104] The point cloud fusion algorithm is used to fuse the point cloud map corresponding to each frame of the environmental perception image to generate a three-dimensional point cloud map model of the operating environment.

[0105] Optionally, the control system is further used for:

[0106] After receiving the navigation destination feedback information, the automatic driving wheelchair is controlled to move at a first speed; wherein the first moving speed is less than a speed of moving according to the moving path.

[0107] The autonomous driving wheelchair navigation system based on intelligent voice interaction provided in the embodiment of the present application receives navigation destination information input by the user in real time according to the voice interaction system, and generates a three-dimensional semantic point cloud map model according to the visual perception system, so that the autonomous driving wheelchair can quickly adjust navigation instructions and plan navigation paths according to real-time conditions and user needs during actual use, thereby achieving flexible control of the autonomous driving wheelchair.

[0108] In the embodiments of this application Figure 2 The shown automatic driving wheelchair navigation system based on intelligent voice interaction may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0109] The embodiments of the present application provide Figure 2 The autonomous driving wheelchair navigation system based on intelligent voice interaction can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0110] Optionally, the embodiment of the present application further provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein when the program or instruction is executed by the processor, each process of the above-mentioned embodiment of the method for navigating an autonomous driving wheelchair based on intelligent voice interaction is implemented, and the same technical effect can be achieved. To avoid repetition, it is not described here. The electronic device can be a control system set in an autonomous driving wheelchair.

[0111] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned embodiment of the automatic driving wheelchair navigation method based on intelligent voice interaction is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0112] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0113] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the embodiment of the automatic driving wheelchair navigation method based on intelligent voice interaction, and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0114] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0115] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0116] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for navigation of an autonomous driving wheelchair based on intelligent voice interaction, applied to an autonomous driving wheelchair, characterized in that: The method comprises: In response to the voice wake-up command, the voice interaction system, visual perception system and navigation system of the autonomous driving wheelchair are turned on; Calling the voice interaction system to output a navigation destination inquiry instruction, and receiving navigation destination feedback information input by a user; Invoking the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and operating environment during movement; Calling the navigation system to mark the target location information in the navigation destination feedback information in the three-dimensional semantic point cloud map model; Calling the navigation system to generate a moving path according to the current position information of the autonomous driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information; The automatic driving wheelchair is controlled to move according to the moving path.

2. The method according to claim 1, characterized in that The step of the voice interaction system outputting a navigation destination inquiry instruction and receiving navigation destination feedback information input by a user comprises: a navigation destination inquiry instruction preset in the voice interaction system output, wherein the navigation destination inquiry instruction can guide the user to input navigation destination information conforming to a preset format; Monitoring whether the navigation destination feedback information input by the user is received within a preset time; If not, the navigation destination inquiry instruction is output again until the navigation destination feedback information input by the user is received.

3. The method according to claim 1, characterized in that The steps of calling the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and operating environment during movement include: During the movement, the visual perception system is called to collect the environment perception video stream including the spatial depth information and image color information of the surrounding environment in real time; Generating a three-dimensional point cloud map model of the operating environment according to the environment perception video stream; An image semantic segmentation algorithm is used to perform semantic segmentation on each frame of the environment perception image in the environment perception video stream, and the segmentation result is rendered onto the three-dimensional point cloud map model of the operating environment to generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment.

4. The method according to claim 3, characterized in that The step of generating a three-dimensional point cloud map model of the operating environment according to the environment perception video stream comprises: Dividing the environment perception video stream into a plurality of single-frame environment perception images; For each frame of the environment perception image, construct a corresponding point cloud map according to the spatial depth information and image color information in the environment perception image; The point cloud fusion algorithm is used to fuse the point cloud map corresponding to each frame of the environmental perception image to generate a three-dimensional point cloud map model of the operating environment.

5. The method according to claim 1, characterized in that Before the step of calling the visual perception system to generate a three-dimensional semantic point cloud map model containing semantic information and an operating environment during movement, the method further includes: After receiving the navigation destination feedback information, move at a first speed; wherein the first moving speed is less than the speed at which the automatic driving wheelchair is controlled to move according to the moving path.

6. An autonomous driving wheelchair navigation system based on intelligent voice interaction, arranged in an autonomous driving wheelchair, characterized in that: The autonomous driving wheelchair navigation system based on intelligent voice interaction includes: a control system, a voice interaction system, a visual perception system and a navigation system; The control system is used to activate the voice interaction system, the visual perception system and the navigation system of the autonomous driving wheelchair in response to a voice wake-up command; The voice interaction system is used to output a navigation destination inquiry instruction and receive navigation destination feedback information input by a user; The visual perception system is used to generate a three-dimensional semantic point cloud map model containing semantic information and an operating environment during the movement of the autonomous driving wheelchair; The navigation system is used to mark the target position information in the navigation destination feedback information sent by the voice interaction system in the three-dimensional semantic point cloud map model; generate a moving path according to the current position information of the autonomous driving wheelchair and the three-dimensional semantic point cloud map model marked with the target position information; The control system is also used to control the movement of the automatic driving wheelchair according to the moving path sent by the navigation system.

7. The automatic driving wheelchair navigation based on intelligent voice interaction according to claim 6, characterized in that: The voice interaction system comprises: an output module, used for outputting a preset navigation destination inquiry instruction, wherein the navigation destination inquiry instruction can guide the user to input navigation destination information conforming to a preset format; The monitoring module is used to monitor whether the navigation destination feedback information input by the user is received within a preset time; if not, the output module is called again to output the navigation destination inquiry instruction until the navigation destination feedback information input by the user is received.

8. The automatic driving wheelchair navigation system based on intelligent voice interaction according to claim 6, characterized in that: The visual perception system comprises: A startup module, used to start a preset device to collect an environment perception video stream including spatial depth information and image color information of the surrounding environment in real time; A first generating module, used for generating a three-dimensional point cloud map model of the operating environment according to the environment perception video stream; The second generation module is used to perform semantic segmentation on each frame of the environment perception image in the environment perception video stream using an image semantic segmentation algorithm, render the segmentation result onto the three-dimensional point cloud map model of the operating environment, and generate a three-dimensional semantic point cloud map model containing semantic information and the operating environment.

9. The automatic driving wheelchair navigation system based on intelligent voice interaction according to claim 8, characterized in that: The first generating module is specifically used for: Dividing the environment perception video stream into a plurality of single-frame environment perception images; For each frame of the environment perception image, construct a corresponding point cloud map according to the spatial depth information and image color information in the environment perception image; The point cloud fusion algorithm is used to fuse the point cloud map corresponding to each frame of the environmental perception image to generate a three-dimensional point cloud map model of the operating environment.

10. The automatic driving wheelchair navigation system based on intelligent voice interaction according to claim 6, characterized in that: The control system is also used for: After receiving the navigation destination feedback information, the automatic driving wheelchair is controlled to move at a first speed; wherein the first moving speed is less than a speed moving according to the moving path.

Images