Map generation method and related equipment

By navigating to obstacles without static maps and generating maps in the existing technology, the problem of the need for static maps and obstacle changes affecting map construction is solved, and an efficient and safe robot independent map construction is achieved.

CN119085625APending Publication Date: 2024-12-06HUAWEI TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202311055770.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-06-05
Filing Date
2023-08-18
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Existing robot independent mapping methods require static maps, and changes in obstacles will affect the mapping performance and even bring dangers, making it difficult to achieve efficient mapping without static maps.

Method used

By acquiring obstacles in the scanning range of the terminal device sensor, the terminal device is controlled to navigate to the first obstacle, and generate a map based on the navigation trajectory, and update candidate obstacles in real time for comprehensive exploration, reducing repeated exploration, and achieving efficient map construction.

Benefits of technology

Complete the map construction plan without a static map, which improves the map construction efficiency and security, and reduces the energy consumption and mobile distance of terminal equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085625A_ABST
    Figure CN119085625A_ABST
Patent Text Reader

Abstract

The invention discloses a map generation method which can be applied to robot mapping scenes in families, hotels, restaurants, shopping malls, airports, hospitals, scenic spots, factories and other scenes. The method comprises the following steps: acquiring a plurality of obstacles in a scanning range of a sensor; controlling the terminal equipment to navigate to a first obstacle, wherein the first obstacle is the obstacle closest to the terminal equipment in the plurality of obstacles; and then determining a next navigation point of the terminal device, the next navigation point being an obstacle which is the smallest distance from the first obstacle in the plurality of candidate obstacles, or the next navigation point being an obstacle which is not selected in the plurality of obstacles and the terminal device does not pass through. And generating a map based on the navigation trajectory of the terminal device. In the map generation process, the candidate obstacles can be updated in real time, so that comprehensive exploration is carried out, and mapping is completed under the condition that no static map exists.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application claims the priority of the Chinese patent application filed with the China Patent Office on June 5, 2023, with application number 202310659014.3 and invention name “A map generation method and related equipment”, the entire contents of which are incorporated by reference in this application. Technical Field

[0002] The present application relates to the field of artificial intelligence, and in particular to a map generation method and related equipment. Background Art

[0003] Robotic autonomous mapping technology refers to the technology that allows robots to efficiently explore completely unknown new environments without human intervention. In the engineering world, robotic mapping technology is implemented by manually setting mapping points in advance and then letting the robot follow, which has high labor costs. In the academic world, existing mapping methods require the input of a static global map to complete mapping path planning, but obstacles in the real world change frequently, making the application of mapping methods unrealistic.

[0004] At present, the random fast search tree algorithm is an autonomous mapping algorithm based on the principle of random optimization. First, the user needs to give a boundary range, then the algorithm randomly selects points and determines whether the point is an obstacle-free point, then finds the node closest to the point in the random tree, and connects the two points with a certain step length to generate new points to form a new expansion of the random tree. After the search tree randomly expands until it reaches the boundary point within the radar range of the car, it finds the shortest path between the car and the boundary point in the search tree and drives the car to move to the boundary point. When reaching the boundary point, continue to explore new boundary points in the same way until there is no explorable area in the boundary range.

[0005] However, the above-mentioned autonomous mapping method needs to complete mapping planning based on a known static map. Changes in obstacles during the planning process will directly affect the mapping performance and even bring danger. Summary of the invention

[0006] The present application provides a map generation method for completing map planning without a static map.

[0007] In a first aspect, an embodiment of the present application provides a map generation method, which can be applied to robot map building scenarios in scenarios such as homes, hotels, restaurants, shopping malls, airports, hospitals, scenic spots, and factory areas. The method can be executed by a map generation device, or by a component of the map generation device (such as a processor, a chip, or a chip system, etc.). The map generation device can be a terminal device, or a control device for controlling a terminal device. In the method: first, a plurality of obstacles in a scanning range (also referred to as a first range) of a sensor in a terminal device are obtained; the terminal device is controlled to navigate to a first obstacle, where the first obstacle may be randomly selected or may be the obstacle closest to the terminal device among multiple obstacles, or the obstacle whose distance is less than or equal to a first preset threshold; then a next navigation point of the terminal device is determined, where the next navigation point is an obstacle with the shortest distance from the first obstacle or less than or equal to a second preset threshold among multiple candidate obstacles, or the next navigation point is an obstacle that is not selected among multiple obstacles and has not been passed by the terminal device (or understood to be a second range, which is smaller than the first range), wherein the candidate obstacles include obstacles newly scanned by the terminal device in the process of navigating to the first obstacle (i.e., the scanning range of the sensor) and / or any obstacle among multiple obstacles except the first obstacle; and a map is generated based on the navigation trajectory of the terminal device, where the navigation trajectory includes the first obstacle and the next navigation point.

[0008] In an embodiment of the present application, the terminal device is controlled to navigate to the first obstacle in the sensor scanning range, the next navigation point is determined, and then a map is generated based on the navigation trajectory of the terminal device. Since the next navigation point may be the obstacle closest to the first obstacle among multiple candidate obstacles, or the next navigation point may be an obstacle that has not been selected among multiple obstacles and has not been passed by the terminal device. Then the map is generated through the navigation trajectory of the terminal device. That is, in the process of generating the map, the next navigation point is determined through the candidate obstacles. On the one hand, the candidate obstacles can be updated in real time, so as to conduct a comprehensive exploration, thereby achieving the completion of mapping without a static map. On the other hand, by determining the candidate obstacles through two ranges corresponding to the scan, the repeated exploration of subsequent scanned obstacles can be reduced, thereby achieving efficient mapping.

[0009] Optionally, in a possible implementation manner of the first aspect, the terminal device includes a first navigation mode and a second navigation mode, and the first navigation mode and the second navigation mode are used to determine a next navigation point of the terminal device.

[0010] In this possible implementation, the terminal device may determine different next navigation points according to different modes through multiple navigation modes of the terminal device, thereby reducing the risk of the terminal device navigation point falling into a local loop exploration due to a single navigation mode.

[0011] Optionally, in a possible implementation of the first aspect, the above-mentioned step of determining the next navigation point of the terminal device includes: determining, according to the first navigation mode, that the next navigation point is an obstacle among multiple candidate obstacles whose distance to the first obstacle is the shortest or less than or equal to a second preset threshold.

[0012] In this possible implementation, in the first navigation mode, the next navigation point is determined according to the distance, so that the terminal device can greedily explore in an unknown environment and quickly perceive the environment, and the moving distance of the terminal device can be saved and energy consumption can be reduced.

[0013] Optionally, in a possible implementation of the first aspect, the above-mentioned step of determining the next navigation point of the terminal device includes: determining, according to the second navigation mode, that the next navigation point is an obstacle that is not selected among multiple obstacles and that the terminal device has not passed through.

[0014] In this possible implementation, the next navigation point in the second navigation mode is an obstacle that is not selected and has not been passed among multiple obstacles, that is, the scanned obstacles are no longer scanned repeatedly, which can save the moving distance of the terminal device and reduce energy consumption.

[0015] Optionally, in a possible implementation of the first aspect, the navigation trajectory further includes at least one of the following: the position of an obstacle scanned during the movement of the terminal device, and the distance between multiple obstacles scanned during the movement of the terminal device. The steps also include: determining multiple first distances, each of the multiple first distances is used to represent the sum of the distances between each unexplored obstacle in the multiple obstacles and each new obstacle in the multiple new obstacles and the terminal device; determining the unexplored obstacle and / or new obstacle in the multiple obstacles corresponding to the distance less than or equal to the second preset threshold in the multiple first distances as the next navigation point.

[0016] In this possible implementation, a map may be generated based on obstacle positions and / or relative positions between obstacles.

[0017] Optionally, in a possible implementation manner of the first aspect, the next navigation point is determined by any of the following methods: minimum triangular perimeter, minimum triangular area, shortest distance, etc. The three angles in the minimum triangular perimeter and the minimum triangular area refer to the position of the terminal device, an unexplored obstacle among multiple obstacles, and the position of a newly scanned obstacle among candidate obstacles.

[0018] In this possible implementation, the next navigation point can be determined based on the minimum triangle perimeter, minimum triangle area, shortest distance, etc., to avoid greedy exploration using only the shortest path without considering global obstacle distribution information, thereby enabling the mapping algorithm to efficiently escape the local minimum. It can also save the moving distance of the terminal device and reduce energy consumption.

[0019] Optionally, in a possible implementation manner of the first aspect, before the above step: determining the next navigation point of the terminal device, the method further includes: determining a navigation mode of the terminal device based on the scanned obstacles and candidate obstacles.

[0020] In this possible implementation, the navigation mode is determined by the scanned obstacles and the candidate obstacles, thereby reasonably reducing the repeated scanning of the scanned obstacles and improving the mapping efficiency.

[0021] Optionally, in a possible implementation of the first aspect, the above-mentioned step of determining the navigation mode of the terminal device based on the scanned obstacles and candidate obstacles includes: inputting the scanned obstacles and the candidate obstacles into a trained neural network to obtain a result, the result including the first navigation mode or the second navigation mode, and the trained neural network is trained according to a preset navigation path.

[0022] In this possible implementation, by determining the two modes according to the neural network trained according to the preset navigation path, a better navigation path can be found as much as possible, thereby improving the mapping efficiency.

[0023] Optionally, in a possible implementation of the first aspect, the above steps: before generating a map based on the navigation trajectory of the terminal device, the method also includes: controlling the terminal device to navigate to the next navigation point; updating candidate obstacles; updating a third range based on preset conditions, the third range including: the first range and / or the second range, the second range is smaller than the first range, the preset condition is related to the updated scanned obstacles, or the preset condition is related to the first range and the updated candidate obstacles; controlling the terminal device to navigate based on the updated third range.

[0024] In this possible implementation, in order to reduce the energy consumption of autonomous mapping of large scenes, the scanning range of the radar (i.e., the first range) is adaptively adjusted according to the location distribution of the points that the terminal device has captured, so as to avoid power consumption caused by the full-range scanning of the radar. In addition, the larger the updated second range, the lower the search and walking cost of the terminal device. Setting preset conditions can adaptively adjust the second range and reduce the mapping cost of the terminal device.

[0025] In a second aspect, an embodiment of the present application provides a map generation device, which can be applied to robot mapping scenarios in scenarios such as homes, hotels, restaurants, shopping malls, airports, hospitals, scenic spots, and factory areas. The map generation device can be a terminal device, or a control device for controlling a terminal device. The map generation device includes: an acquisition unit, which is used to acquire multiple obstacles in a first range, and the first range is the scanning range of a sensor in the terminal device; a control unit, which is used to control the terminal device to navigate to a first obstacle, and the first obstacle is the obstacle closest to the terminal device among multiple obstacles, or the obstacle whose distance is less than or equal to a first preset threshold; a determination unit, which is used to determine the next navigation point of the terminal device, and the next navigation point is the obstacle with the smallest distance from the first obstacle or less than or equal to a second preset threshold among multiple candidate obstacles, or the next navigation point is an obstacle that is not selected among multiple obstacles and has not been passed by the terminal device, wherein the candidate obstacles include obstacles newly scanned by the terminal device in the process of navigating to the first obstacle and / or any obstacle among multiple obstacles except the first obstacle; a generation unit, which is used to generate a map based on the navigation trajectory of the terminal device, and the navigation trajectory includes the first obstacle and the next navigation point.

[0026] Optionally, in a possible implementation manner of the second aspect, the terminal device includes a first navigation mode and a second navigation mode, and the first navigation mode and the second navigation mode are used by a determination unit to determine a next navigation point of the terminal device.

[0027] Optionally, in a possible implementation manner of the second aspect, the above-mentioned determination unit is specifically used to determine, according to the first navigation mode, that the next navigation point is an obstacle among multiple candidate obstacles whose distance to the first obstacle is the shortest or less than or equal to a second preset threshold.

[0028] Optionally, in a possible implementation manner of the second aspect, the above-mentioned determination unit is specifically used to determine, according to the second navigation mode, that the next navigation point is an obstacle that is not selected among multiple obstacles and that the terminal device has not passed through.

[0029] Optionally, in a possible implementation manner of the second aspect, the above-mentioned navigation trajectory also includes at least one of the following: the position of an obstacle scanned during the movement of the terminal device, and the distance between multiple obstacles scanned during the movement of the terminal device.

[0030] Optionally, in a possible implementation manner of the second aspect, the next navigation point is determined by any one of the following methods: minimum triangle perimeter; minimum triangle area; shortest distance.

[0031] Optionally, in a possible implementation manner of the second aspect, the above-mentioned determination unit is further used to determine the navigation mode of the terminal device based on the scanned obstacles and the candidate obstacles.

[0032] Optionally, in a possible implementation of the second aspect, the above-mentioned determination unit is specifically used to input the scanned obstacles and candidate obstacles into a trained neural network to obtain a result, and the result includes a first navigation mode or a second navigation mode, and the trained neural network is trained according to a preset navigation path.

[0033] Optionally, in a possible implementation of the second aspect, the above-mentioned control unit is also used to control the terminal device to navigate to the next navigation point; the map generating device also includes: an updating unit, used to update candidate obstacles; the updating unit is also used to update a third range based on preset conditions, the third range includes: a first range and / or a second range, the second range is smaller than the first range, the preset condition is related to the updated scanned obstacles, or the preset condition is related to the first range and the updated candidate obstacles; the control unit is also used to control the navigation of the terminal device based on the updated third range.

[0034] A third aspect of an embodiment of the present application provides a map generating device, including: a processor, the processor is coupled to a memory, the memory is used to store programs or instructions, when the program or instructions are executed by the processor, the map generating device implements the method in the above-mentioned first aspect or any possible implementation method of the first aspect.

[0035] A fourth aspect of an embodiment of the present application provides a map generation method, which is applied to a control device, and the method includes: receiving a first request; in response to the first request, controlling the terminal device to navigate to a first obstacle and a next navigation point, and controlling the terminal device to generate a map based on the navigation trajectory of the terminal device; the first obstacle and the next navigation point are determined according to the method in the above-mentioned first aspect or any possible implementation of the first aspect; receiving a map from the terminal device.

[0036] A fifth aspect of an embodiment of the present application provides a map generation method, which is applied to a terminal device, and the method includes: sending a first request to a control device; receiving a control instruction in response to the first request, navigating to a first obstacle and a next navigation point, and generating a map based on the navigation trajectory of the terminal device; the first obstacle and the next navigation point are determined according to the method in the above-mentioned first aspect or any possible implementation of the first aspect; sending the map to the control device.

[0037] In a sixth aspect of the embodiments of the present application, a system for map generation is provided, the system comprising a control device and a terminal device; the terminal device is used to provide a plurality of obstacles within a first range, the first range being the scanning range of a sensor in the terminal device; the control device is used to determine a first obstacle and a next navigation point, the first obstacle and the next navigation point being determined according to the method in the first aspect or any possible implementation of the first aspect. The control device is also used to control the terminal device to navigate to the first obstacle and the next navigation point, and to control the terminal device to generate a map based on the navigation trajectory of the terminal device.

[0038] A seventh aspect of an embodiment of the present application provides a computer-readable medium on which a computer program or instruction is stored. When the computer program or instruction is executed on a computer, the computer executes the method in the aforementioned first aspect or any possible implementation of the first aspect.

[0039] An eighth aspect of the embodiments of the present application provides a computer program product. When the computer program product is executed on a computer, it enables the computer to execute the method in the aforementioned first aspect or any possible implementation of the first aspect.

[0040] It can be seen from the above technical solutions that the present application has the following advantages: controlling the terminal device to navigate to the first obstacle in the sensor scanning range, determining the next navigation point, and then generating a map based on the navigation trajectory of the terminal device. Since the next navigation point may be the obstacle closest to the first obstacle among multiple candidate obstacles, or the next navigation point may be an obstacle that has not been selected among multiple obstacles and has not been passed by the terminal device. Then the map is generated through the navigation trajectory of the terminal device. That is, in the process of generating the map, the next navigation point is determined through the candidate obstacles. On the one hand, the candidate obstacles can be updated in real time, so as to conduct a comprehensive exploration, thereby achieving the completion of mapping without a static map. On the other hand, by determining the candidate obstacles through two ranges corresponding to the scan, the repeated exploration of subsequent scanned obstacles can be reduced, thereby achieving efficient mapping. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1A A schematic diagram of the structure of the system architecture provided in the embodiment of the present application;

[0042] Figure 1B A schematic diagram of another system architecture provided in an embodiment of the present application;

[0043] Figure 2 A flowchart of a map generation method provided in an embodiment of the present application;

[0044] Figure 3 An example diagram of a first range, multiple obstacles, and a second range provided in an embodiment of the present application;

[0045] Figure 4 An example diagram of a first obstacle provided in an embodiment of the present application;

[0046] Figure 5 An example diagram of a triangle in the perimeter of a triangle provided in an embodiment of the present application;

[0047] Figure 6 An example diagram of a first range before and after updating provided in an embodiment of the present application;

[0048] Figure 7 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application;

[0049] Figure 8 A functional diagram of each module in the terminal device provided in an embodiment of the present application;

[0050] Fig. 9 Another flowchart of the map generation method provided in the embodiment of the present application;

[0051] Fig.10 A schematic diagram of the structure of a map generating device provided in an embodiment of the present application;

[0052] Fig.11 Another structural schematic diagram of the map generating device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The present application provides a map generation method for completing map planning without a static map.

[0054] To facilitate understanding, the relevant terms and concepts mainly involved in the embodiments of the present application are first introduced below.

[0055] 1. Neural Networks

[0056] A neural network can be composed of neural units. A neural unit can be a s and intercept b as inputs, the output of the operation unit can be:

[0057]

[0058] Where, s = 1, 2, ... n, n is a natural number greater than 1, W s For X sThe weight of the neural unit, b is the bias of the neural unit. f is the activation function of the neural unit, which is used to introduce nonlinear characteristics into the neural network to convert the input signal in the neural unit into the output signal. The output signal of the activation function can be used as the input of the next convolutional layer. The activation function can be a sigmoid function. A neural network is a network formed by connecting many of the above-mentioned single neural units together, that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract the features of the local receptive field. The local receptive field can be an area composed of several neural units.

[0059] 2. Neural State Machine

[0060] A neural state machine refers to a finite state machine built using a neural network, that is, a model that determines whether a system is in a certain state.

[0061] Robot autonomous mapping technology refers to the technology that allows robots to efficiently explore completely unknown new environments without human intervention. At present, the random fast search tree algorithm is an autonomous mapping algorithm based on the principle of random optimization. First, the user needs to give a boundary range, and then the algorithm randomly selects points and determines whether the point is an obstacle-free point. Then, the node closest to the point in the random tree is found, and the two points are connected by a line with a certain step length to generate new points to form a new expansion of the random tree. After the search tree is randomly expanded until it reaches the boundary point within the first range of the car, it finds the shortest path between the car and the boundary point in the search tree and drives the car to move to the boundary point. After reaching the boundary point, continue to explore new boundary points in the same way until there is no explorable area in the boundary range.

[0062] However, the above-mentioned autonomous mapping method needs to complete mapping planning based on a known static map. Changes in obstacles during the planning process will directly affect the mapping performance and even bring danger.

[0063] In order to solve the above technical problems, an embodiment of the present application provides a map generation method, which controls the terminal device to navigate to the first obstacle in the sensor scanning range, determines the next navigation point, and then generates a map based on the navigation trajectory of the terminal device. Since the next navigation point may be the obstacle closest to the first obstacle among multiple candidate obstacles, or the next navigation point may be an obstacle that has not been selected among multiple obstacles and has not been passed by the terminal device. Then, a map is generated through the navigation trajectory of the terminal device. That is, in the process of generating a map, the next navigation point is determined through the candidate obstacles. On the one hand, the candidate obstacles can be updated in real time, so as to conduct a comprehensive exploration, thereby achieving the completion of mapping without a static map. On the other hand, by determining the candidate obstacles through two ranges corresponding to the scan, the repeated exploration of subsequent scanned obstacles can be reduced, thereby achieving efficient mapping.

[0064] The map generation method provided in the embodiment of the present application can be applied to robot map building scenarios in scenarios such as homes, hotels, restaurants, shopping malls, airports, hospitals, scenic spots, and factory areas. It can be understood that the above scenarios are just examples, and in actual applications, there may be other application scenarios, which are not specifically limited here.

[0065] Before describing the map generation method provided in the embodiments of the present application, several system architectures provided in the embodiments of the present application are first described.

[0066] Figure 1A A schematic diagram of the system architecture provided in the embodiment of the present application, the system architecture includes a terminal device and a control device. The terminal device is the initiator of the map generation method, as the initiator of the map generation request, usually initiated by a user through the terminal device.

[0067] Optionally, the control device receives a map generation request from the terminal device through an interactive interface, and then performs decision-making, navigation control, mapping, and other processing through a memory for storing data and a processor for map generation. For example, the control device receives multiple obstacles reported by the terminal device (obstacles within the sensor scanning range of the terminal device, also referred to as obstacles within the first range) and analyzes them to obtain navigation points, and controls the terminal device to move to the next navigation point. The next navigation point is an obstacle among multiple candidate obstacles that has the shortest distance from the first obstacle or is less than or equal to a second preset threshold, or the next navigation point is an obstacle that is not selected among multiple obstacles and that the terminal device has not passed through, wherein the candidate obstacles include obstacles newly scanned by the terminal device during navigation to the first obstacle and / or any obstacle among multiple obstacles except the first obstacle.

[0068] Optionally, the control device receives a list determined by the terminal device during the process of moving to the navigation point. The list may include a list of scanned obstacles and a candidate list. The list of scanned obstacles includes obstacles scanned within a second range during the movement of the terminal device to the first obstacle, and the second range is smaller than the first range. The candidate list includes unexplored obstacles and multiple new obstacles among multiple obstacles, and the multiple new obstacles include obstacles scanned within the first range during the navigation of the terminal device to the first obstacle. The control device then determines the latest navigation point based on the list and controls the terminal device to move. On the one hand, the control device can also generate a map based on each navigation point of the terminal device. On the other hand, the terminal device can generate a map based on each navigation point and report the map to the control device.

[0069] Furthermore, the control device may also update the scanning range of the terminal device according to the list, thereby reducing the energy consumption of the terminal device.

[0070] exist Figure 1A In the embodiment, the control device and / or the terminal device can execute the map generation method of the embodiment of the present application.

[0071] Figure 1B Another structural diagram of the system architecture provided in the embodiment of the present application is shown in Figure 1B In the process, the terminal device has the capabilities of navigation, decision-making, and mapping, which can be directly processed by the hardware of the terminal device itself. The specific process is similar to Figure 1A Similarly, please refer to the above description and will not repeat them here.

[0072] For example, the terminal device first determines multiple obstacles through sensors, then analyzes the multiple obstacles to obtain the next navigation point, and moves to the next navigation point. The terminal device determines the list during the process of moving to the next navigation point. The terminal device then determines the latest navigation point based on the list and moves. The terminal device can generate a map based on each navigation point.

[0073] exist Figure 1B In the embodiment of the present application, the terminal device itself can execute the map generation method.

[0074] The terminal device in the embodiments of the present application may be a mobile robot, an unmanned aircraft, an autonomous driving vehicle, etc., or a cloud device (or a control device) that controls the movement of the mobile robot. If the terminal device is a mobile robot, the mobile robot may be a robot that can move and perform certain tasks in an indoor environment (for example, a home, hospital, airport, shopping mall, factory workshop, etc.) or an outdoor environment (for example, a factory area, a park, etc.). Specifically, the mobile robot may include a sweeping robot, a handling robot, a guiding robot, and the like. The following description will only take the example of a mobile robot as the terminal device.

[0075] The control device in the embodiment of the present application can be a device or server with data processing functions such as a cloud server, a network server, an application server, and a management server. The memory in the control device can be a general term, including local storage and a database for storing historical data. The database can be on the control device or on other network servers. The control device can control the movement of the terminal device to realize the process of generating a map in the embodiment of the present application.

[0076] The map generation method provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0077] See also Figure 2The map generation method provided in the present application is an embodiment of the present invention. The method can be executed by a map generation device or by a component of the map generation device (such as a processor, a chip, or a chip system). The map generation device can be a control device (such as the aforementioned Figure 1A As shown), it can also be a terminal device (such as the aforementioned Figure 1B Of course, the method can also be executed by a system composed of a control device and a terminal device (for example, the aforementioned Figure 1A The method includes steps 201 to 204.

[0078] Step 201: Acquire multiple obstacles in a first range.

[0079] The map generating device first obtains a plurality of obstacles in a first range, where the first range is a scanning range of a sensor in the terminal device (eg, a radar scanning range).

[0080] In a possible implementation, the map generation device is the control device in the aforementioned system architecture. The control device may obtain the multiple obstacles in the same manner as the receiving terminal device sends the multiple obstacles.

[0081] In another possible implementation, the map generating device is a terminal device in the aforementioned system architecture. The terminal device determines a plurality of obstacles in the first range through its own sensor.

[0082] It is understandable that the first range may be expressed in the form of radius, coordinates, etc. The multiple obstacles may be expressed in the form of map coordinates or arrays, etc., which are not specifically limited here.

[0083] In addition, the number of the multiple obstacles may be two or more, which is not specifically limited here.

[0084] Optionally, when the map generating device is a terminal device (such as a vehicle), the vehicle contains a sensor system, which may include a plurality of sensors for sensing information about the vehicle's position. For example, the sensor system may include a positioning system (the positioning system may be a global positioning GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (IMU), a radar, a laser rangefinder, and a camera.

[0085] Among them, the positioning system can be used to estimate the geographic location of the vehicle, such as the latitude and longitude information of the vehicle's location. The IMU is used to sense the position and orientation changes of the vehicle based on the inertial acceleration rate. In one embodiment, the IMU can be a combination of an accelerometer and a gyroscope. The radar can use radio signals to sense objects in the surrounding environment of the vehicle, which can be specifically manifested as a millimeter wave radar or a laser radar. In some embodiments, in addition to sensing objects, the radar can also be used to sense the speed and / or direction of travel of the object. The laser rangefinder can use lasers to sense objects in the environment where the vehicle is located. In some embodiments, the laser rangefinder may include one or more laser sources, a laser scanner, and one or more detectors, as well as other system components. The camera can be used to capture multiple images of the surrounding environment of the vehicle. The camera can be a still camera or a video camera.

[0086] For example, the first range and the plurality of obstacles may be as follows: Figure 3 As shown. It is understandable that Figure 3 The number of obstacles being 4 is just an example.

[0087] Step 202: Control the terminal device to navigate to the first obstacle among multiple obstacles.

[0088] After the map generation device obtains multiple obstacles, it can control the terminal device to navigate to the first obstacle among the multiple obstacles, where the first obstacle is the obstacle closest to the terminal device or the obstacle whose distance is less than or equal to the first preset threshold among the multiple obstacles. The first preset threshold can be set according to actual needs and is not specifically limited here.

[0089] In a possible implementation, the map generating device is a control device in the aforementioned system architecture. After acquiring multiple obstacles, the control device determines a first obstacle and sends a control instruction to the terminal device, where the control instruction is used for the terminal device to navigate to the first obstacle.

[0090] In another possible implementation, the map generating device is a terminal device in the aforementioned system architecture. After acquiring multiple obstacles, the terminal device may first determine a first obstacle among the multiple obstacles and navigate to the first obstacle.

[0091] In the embodiment of the present application, the first obstacle may be an obstacle randomly selected from multiple obstacles, or the obstacle closest to the terminal device among multiple obstacles may be the first obstacle, or the first obstacle may be determined randomly or according to the direction of travel of the current terminal device when there are multiple obstacles whose distance to the terminal device is less than or equal to the first preset threshold, etc. The embodiment of the present application does not limit the method for determining the first obstacle.

[0092] Optionally, the distance between the first obstacle and the terminal device may be equal to a first preset threshold, which is the distance between the terminal device and the obstacle closest to the multiple obstacles. Alternatively, it is understood that the obstacle closest to the terminal device among the multiple obstacles is determined to be the first obstacle.

[0093] For example, taking the first obstacle as the closest obstacle to the terminal device as an example, the first obstacle is as follows: Figure 4 It can be seen that the distance between the first obstacle and the terminal device is smaller than the distance between other obstacles and the terminal device.

[0094] Step 203: determine the next navigation point of the terminal device.

[0095] After the map generating device controls the terminal device to navigate to the first obstacle, the next navigation point of the terminal device is determined, where the next navigation point is an obstacle among multiple candidate obstacles that has the shortest distance to the first obstacle or is less than or equal to a second preset threshold, or the next navigation point is an obstacle that is not selected among the multiple obstacles and that the terminal device has not passed through, and the candidate obstacles include obstacles newly scanned by the terminal device during navigation to the first obstacle and / or any obstacle among the multiple obstacles except the first obstacle.

[0096] Among them, the above-mentioned "terminal device passing by", "terminal device navigating by" or "terminal device passing by" corresponds to the second range, "terminal device scanning" corresponds to the first range, and the second range is smaller than the first range (it can also be understood that the radius of the second range is smaller than the radius of the first range).

[0097] For example, the relationship between the first range and the second range can be as follows: Figure 3 shown.

[0098] Optionally, in order to include fewer points in the scanned obstacles, the second range may be the smallest circumscribed circle of the terminal device. Of course, in order to improve the efficiency of mapping, the second range may be larger than the smallest circumscribed circle of the terminal device and smaller than the first range, so that more points can be included in the scanned obstacles.

[0099] Optionally, the terminal device includes a first navigation mode and a second navigation mode, and the first navigation mode and the second navigation mode are used to determine a next navigation point of the terminal device.

[0100] Furthermore, the map generating device determining the next navigation point may specifically include: the map generating device first determines a navigation mode of the terminal device, and determines different next navigation points according to different navigation modes.

[0101] Exemplarily, the map generation device determines the navigation mode of the terminal device based on the scanned obstacles and the candidate obstacles, which can be specifically: the scanned obstacles and the candidate obstacles are input into the trained neural network to obtain a result, and the first result includes the first navigation mode or the second navigation mode. The trained neural network is trained according to the preset navigation path. The trained neural network can also be understood as a classifier for a binary classification task. The label value is determined by the preset navigation path, and the difference between the label value and the result output by the neural network is reduced to train the neural network.

[0102] The scanned obstacles include obstacles scanned within the second range when the terminal device moves to the first obstacle. The scanned obstacles include the first obstacle, and the second range is smaller than the first range. The candidate obstacles include obstacles that have not been explored among the multiple obstacles and obstacles scanned within the first range when the terminal device moves to the first obstacle.

[0103] In a possible implementation, the map generating device is the control device in the aforementioned system architecture. The control device controls the terminal device to navigate to the first obstacle, and controls the terminal device to collect and report the scanned obstacles and candidate obstacles in the process of navigating to the first obstacle, and the control device determines the next navigation point according to the scanned obstacles and candidate obstacles.

[0104] In another possible implementation, the map generating device is a terminal device in the aforementioned system architecture. The terminal device collects scanned obstacles and candidate obstacles during navigation to the first obstacle, and determines the next navigation point according to the scanned obstacles and the candidate obstacles.

[0105] In a possible implementation, the next navigation point is determined to be an obstacle with the shortest distance from the first obstacle or less than or equal to a second preset threshold value among multiple candidate obstacles according to the first navigation mode. Specifically, when the navigation mode is the first mode, the map generating device determines that the next navigation point is an obstacle with the shortest distance from the first obstacle or less than or equal to the second preset threshold value among multiple candidate obstacles.

[0106] In another possible implementation, the next navigation point is determined according to the second navigation mode to be an obstacle that is not selected among multiple obstacles and that the terminal device has not passed through. Specifically, when the navigation mode is the second mode, the map generating device determines that the next navigation point is an obstacle that is not selected among multiple obstacles and that the terminal device has not passed through.

[0107] Optionally, in the case where the navigation mode is the second navigation mode, multiple first distances may be determined first, and then the unexplored obstacles and / or new obstacles (i.e., newly scanned obstacles) among the multiple obstacles corresponding to the distances in the first distances that are less than or equal to the third preset threshold are determined as the next navigation point. Each of the multiple first distances is used to represent the sum of the distances between each unexplored obstacle in the multiple obstacles and each new obstacle in the multiple new obstacles and the terminal device. The process can also be understood as planning the next navigation point through the minimum triangular perimeter. The triangles correspond to unexplored obstacles in the candidate obstacles (e.g., unexplored obstacles in the multiple obstacles), new obstacles, and terminal devices (e.g., geometric center points, side center points, etc. of the terminal device). It can be understood that the next navigation point includes the candidate obstacles corresponding to the minimum triangular perimeter. In the case where the next navigation point includes unexplored obstacles and new obstacles among the multiple obstacles, the terminal device may first navigate to the new obstacle, and then navigate to the unexplored obstacle among the multiple obstacles. Of course, it is also possible to first navigate to the unexplored obstacle among the multiple obstacles, and then navigate to the new obstacle.

[0108] In addition, in the case of the second navigation mode, the point closest to the first obstacle among multiple candidate obstacles can also be directly determined as the next navigation point. The point closest to the first obstacle among multiple new obstacles can also be directly determined as the next navigation point. In addition, the next navigation point can also be determined by the minimum triangle area and other methods, which are not limited here. Among them, the above-mentioned minimum triangle perimeter refers to: the distance between the unexplored obstacle and the new obstacle among the candidate obstacles + the distance between the new obstacle and the terminal device + the distance between the terminal device and the unexplored obstacle among the candidate obstacles = the sum of distances, and the unexplored obstacle and / or new obstacle that can make the above-mentioned triangle perimeter minimum is found between multiple unexplored obstacles and multiple new obstacles as the next navigation point. The above-mentioned minimum triangle area means that among the multiple triangles formed by the unexplored obstacles, new obstacles and terminal devices among the candidate obstacles, the unexplored obstacle and / or new obstacle corresponding to the smallest triangle area is the next navigation point. Generally, when the distance between an unexplored obstacle among candidate obstacles and a new obstacle = the distance between the new obstacle and the terminal device = the distance between the terminal device and an unexplored obstacle among candidate obstacles, the formed triangle is an equilateral triangle, and the area in this case is the smallest.

[0109] For example, the triangle can be shown as follows: Figure 5 shown.

[0110] Optionally, when the number of multiple candidate obstacles is less than or equal to the third preset threshold, the minimum triangle perimeter is used to plan the next navigation point in the second navigation mode. When the number of multiple candidate obstacles is greater than or equal to the fourth preset threshold, a neural network or other method may be used to plan the next navigation point in the second navigation mode. The input of the neural network is the scanned obstacles and the candidate obstacles. The output is the obstacle among the candidate obstacles (as the next navigation point).

[0111] Step 204: Generate a map based on the navigation track of the terminal device.

[0112] After determining the next navigation point, the map generating device generates a map based on the navigation track of the terminal device, where the navigation track includes the first obstacle and the next navigation point.

[0113] Optionally, the navigation trajectory further includes at least one of the following: the position of an obstacle scanned during the movement of the terminal device, the distance between multiple obstacles scanned during the movement of the terminal device, etc.

[0114] The type or form of expression of the map in the embodiment of the present application may be a grid map, a scale map, a topological map, a semantic map, etc., which is not specifically limited here.

[0115] In a possible implementation, the map generating device is the control device in the aforementioned system architecture. While the control device controls the terminal device to navigate to the first obstacle and the next navigation point, the terminal device generates a map according to the collected obstacle information. Alternatively, the terminal device reports the obstacle information, and then the control device generates a map according to the obstacle information reported by the terminal device.

[0116] In another possible implementation, the map generating device is a terminal device in the aforementioned system architecture. After navigating to the first obstacle and the next navigation point, the terminal device can generate a map based on the collected obstacle information, or report the obstacle information to the control device, so that the control device generates a map based on the obstacle information reported by the terminal device.

[0117] It is understandable that after the terminal device navigates to the next navigation point, the scanned obstacles and candidate obstacles can be updated. For example, the next navigation point and the obstacles within the second range during the navigation of the terminal device to the next navigation point are included in the scanned obstacles, and the candidate obstacles that have not been explored in the first range during the navigation of the terminal device to the next navigation point are included in the candidate obstacles. Then, the next navigation point is determined based on the obstacles scanned in the first range during the navigation of the terminal device to the next navigation point, the updated scanned obstacles and the candidate obstacles. The determination method is similar to that of determining the next navigation point, and will not be repeated here.

[0118] In an embodiment of the present application, the terminal device is controlled to navigate to the first obstacle in the sensor scanning range, the next navigation point is determined, and then a map is generated based on the navigation trajectory of the terminal device. Since the next navigation point may be the obstacle closest to the first obstacle among multiple candidate obstacles, or the next navigation point may be an obstacle that has not been selected among multiple obstacles and has not been passed by the terminal device. Then the map is generated through the navigation trajectory of the terminal device. That is, in the process of generating the map, the next navigation point is determined through the candidate obstacles. On the one hand, the candidate obstacles can be updated in real time, so as to conduct a comprehensive exploration, thereby achieving the completion of mapping without a static map. On the other hand, by determining the candidate obstacles through two ranges corresponding to the scan, the repeated exploration of subsequent scanned obstacles can be reduced, thereby achieving efficient mapping.

[0119] Optionally, after the terminal device navigates to the next navigation point, the scanned obstacles and candidate obstacles may be updated.

[0120] In a possible implementation manner, the map generating device may determine the second obstacle according to the updated scanned obstacles and the updated candidate obstacles, and navigate to the second obstacle.

[0121] In this case, the above Figure 2 In the illustrated embodiment, step 204 may specifically include: generating a map based on the first obstacle, the next navigation point, and the second obstacle. It may also be understood that after step 204, the map is updated based on the second obstacle.

[0122] In another possible implementation, the map generation device may update the third range according to the updated scanned obstacles and the updated candidate obstacles, thereby reducing the energy consumption of the terminal device and improving the endurance. The third range includes the aforementioned first range and / or second range.

[0123] Optionally, after the terminal device navigates to the next navigation point, the third range is updated based on a preset condition, and the terminal device is controlled to navigate to the next navigation point (e.g., the second obstacle) according to the updated third range. The preset condition is related to the updated scanned obstacle, or the preset condition is related to the first range and the updated candidate obstacle.

[0124] When the third range includes the first range, since the boundary points that have been scanned do not need to be scanned by the radar, the radar scanning interval can be determined by the obstacle distribution in the scanned obstacles, or it can be understood that the radar does not emit radar beams at the positions of the scanned obstacles. This situation can be understood as modifying the scanning angle of the radar.

[0125] For example, Figure 6 Example graphs showing the first range before and after the update.

[0126] When the third range includes the second range, it can be understood that the radius of the second range is modified. The above preset conditions may include at least one of the following:

[0127] 1. The radius of the second range after update is less than or equal to the distance between the terminal device and the nearest obstacle among the candidate obstacles;

[0128] 2. The radius of the second range after update is less than or equal to half of the radar scanning radius of the terminal device;

[0129] 3. The radius of the second range after update is greater than or equal to the distance between the terminal device and the nearest obstacle among the scanned obstacles;

[0130] It can be understood that the above-mentioned preset conditions are only examples. In actual applications, there may be other situations, such as the radius of the second range after update is less than or equal to one third of the radar scanning radius of the terminal device, etc., which are not limited here.

[0131] The map generation method provided in the embodiment of the present application can be understood as a real-time map building and planning method for a robot that imitates bionic behavior. For ease of understanding, the following describes the above method from the perspective of bionic behavior. Figure 2 The embodiments are described in another dimension.

[0132] To facilitate understanding, the structure of the terminal device is first introduced from a bionic perspective.

[0133] The structure of the terminal device is as follows Figure 7 As shown, the terminal device includes: a first navigation module 701 and a second navigation module 702.

[0134] The first navigation module 701 is used to identify multiple obstacles in the scanning range (also referred to as the first range, i.e., the first range) of the sensor (e.g., radar), and use obstacles whose distance to the terminal device is less than or equal to the first preset threshold as navigation points, and drive the terminal device to navigate with the shortest path planning algorithm. During the navigation process, obstacles in the area scanned by the second range are marked as scanned obstacles, and candidate obstacles are recorded (or understood as obstacles that have not been scanned and are not scanned obstacles). After the navigation is completed, the sensor will continue to scan multiple new obstacles (i.e., new obstacles scanned in the first range during the movement process). Obstacles in the scanned obstacles will not be navigated again. The first navigation module 701 may repeat the shortest path exploration, or it may enter the second navigation module 702. Or it can be understood as determining whether the navigation mode of the terminal device uses the first navigation module 701 or the second navigation module 702 through the neural state machine. The input of the neural state machine includes: obstacles in the first range of the current terminal device, obstacles in the scanned obstacles, and candidate obstacles.

[0135] The second navigation module 702 is used to determine the next navigation point according to the minimum triangle perimeter planning for the candidate obstacles obtained by the first navigation module 701. For example, by calculating multiple triangle perimeters, the candidate obstacle corresponding to the triangle perimeter that meets the conditions (such as less than a certain threshold, or the minimum, etc.) is selected as the next navigation point. The triangle perimeter refers to the perimeter of the triangle formed by the terminal device, the unexplored obstacles among the multiple obstacles, and the new obstacles. The selected candidate obstacle can also be converted into the first obstacle for cyclic exploration, or the candidate obstacle and the first obstacle can be converted without conversion.

[0136] Optionally, in order to reduce energy consumption of the terminal device, the terminal device may further include an auxiliary module 703 .

[0137] The auxiliary module 703 is used to adaptively scan the range according to the scanned obstacles, and / or adaptively update the third range according to the candidate obstacles (such as distribution, quantity, etc.) and the density of the first obstacles.

[0138] For example, the above Figure 7 The functions of each module can be as follows Figure 8 shown.

[0139] Combine the following Figure 7 and Figure 8 The modules in the above Figure 2 Another dimension is described in the embodiment of FIG. Fig. 9 , another map generation method provided in an embodiment of the present application.

[0140] First, initialize the first range and second range of the terminal device, and obtain obstacle information at the terminal device location with the maximum radar scanning range. Then, track the obstacles to obtain the obstacle distribution. Enter the first navigation module, and regard the obstacle with the shortest distance to the terminal device as the next target point, and save the unexplored points as candidate obstacles. In the process of the terminal device moving the target, the obstacles covered by the second range will be passed by the terminal device, and the passed obstacles will be included in the scanned obstacles, that is, the terminal device will not navigate again. After moving the target in the first navigation mode, the neural state machine is used to determine whether the navigation mode conversion occurs. If no conversion occurs, the first navigation module is repeated. If the navigation mode conversion occurs, the minimum triangular perimeter planning method is selected according to the number of candidate obstacles and the current obstacle distribution. After navigation is completed and moved to the selected candidate obstacle, the navigation mode is switched. The first range and / or the second range are adaptively modified in real time according to the scanned obstacles, candidate obstacles and obstacle distribution.

[0141] Among them, the adaptive radar scanning range refers to the scanning interval of the radar. Since the boundary points that have been scanned do not need radar scanning, the radar scanning interval can be determined by the distribution of the scanned obstacles, and the radar does not emit radar beams at the positions of the scanned obstacles. The adaptive second range refers to the control of the second range. The larger the second range, the more boundary points will be listed as scanned obstacles, saving the model exploration space. Therefore, under given constraints, the larger the adaptive mapping range, the better. Here are three examples of constraints: 1. The radius of the second range is less than or equal to the distance between the terminal device and the nearest obstacle in the candidate point list (i.e., candidate obstacles); 2. The radius of the second range is less than or equal to the first range*0.5; 3. The radius of the second range is greater than or equal to the distance between the terminal device and the nearest obstacle in the scanned obstacles.

[0142] The above method, on the one hand, uses a bionic boundary exploration mapping method. The boundary points of obstacle information captured by the radar are regarded as prey. The first navigation mode leads the team to find the shortest distance obstacles. During the movement, obstacles covered by the second range enter the scanned obstacles and are no longer explored. The second navigation mode saves the obstacles that have not been navigated in the first navigation mode. The first navigation mode and the second navigation mode are adaptively switched, and the minimum triangle area planning method or the neural state machine is used to determine the mapping algorithm to efficiently escape the local minimum. On the other hand, the adaptive radar scanning range and the second range adjustment feedback optimization. In order to reduce the energy consumption of the large-scene autonomous mapping robot, the scanning range of the radar is adaptively adjusted according to the position distribution of the obstacles that the terminal device has passed, so as to avoid the power consumption caused by the full range scanning of the radar. The larger the second range, the lower the cost of searching and walking required by the terminal device. The multi-constraint objective function of the second range is set, and the second range is adaptively adjusted to reduce the mapping cost of the terminal device.

[0143] The map generation method in the embodiment of the present application is described above. The map generation device in the embodiment of the present application is described below. The map generation device can be a terminal device or a control device. Fig.10 , an embodiment of the map generation device in the embodiment of the present application includes:

[0144] An acquisition unit 1001 is used to acquire a plurality of obstacles in a first range, where the first range is a scanning range of a sensor in a terminal device;

[0145] The control unit 1002 is used to control the terminal device to navigate to a first obstacle, where the first obstacle is the obstacle closest to the terminal device among multiple obstacles, or the obstacle whose distance is less than or equal to a first preset threshold;

[0146] The determining unit 1003 is used to determine a next navigation point of the terminal device, where the next navigation point is an obstacle with the shortest distance from the first obstacle or less than or equal to a second preset threshold among multiple candidate obstacles, or the next navigation point is an obstacle that is not selected among the multiple obstacles and has not been passed by the terminal device, wherein the candidate obstacles include obstacles newly scanned by the terminal device during navigation to the first obstacle and / or any obstacle among the multiple obstacles except the first obstacle;

[0147] The generating unit 1004 is used to generate a map based on the navigation track of the terminal device, where the navigation track includes a first obstacle and a next navigation point.

[0148] Optionally, the terminal device includes a first navigation mode and a second navigation mode, and the first navigation mode and the second navigation mode are used for the determination unit 1003 to determine a next navigation point of the terminal device.

[0149] Optionally, the determining unit 1003 is specifically configured to determine, according to the first navigation mode, that the next navigation point is an obstacle among multiple candidate obstacles whose distance to the first obstacle is the shortest or is less than or equal to a second preset threshold.

[0150] Optionally, the determination unit 1003 is specifically configured to determine, according to the second navigation mode, that the next navigation point is an obstacle that is not selected among multiple obstacles and that the terminal device has not passed through.

[0151] Optionally, the navigation trajectory further includes at least one of the following: a position of an obstacle scanned during the movement of the terminal device, and a distance between multiple obstacles scanned during the movement of the terminal device.

[0152] Optionally, the next navigation point is determined by any of the following methods: minimum triangle perimeter; minimum triangle area; shortest distance.

[0153] Optionally, the determination unit 1003 is further configured to determine a navigation mode of the terminal device based on the scanned obstacles and the candidate obstacles.

[0154] Optionally, the determination unit 1003 is specifically configured to input the scanned obstacles and the candidate obstacles into a trained neural network to obtain a result, wherein the result includes a first navigation mode or a second navigation mode, and the trained neural network is trained according to a preset navigation path.

[0155] Optionally, the control unit 1002 is also used to control the terminal device to navigate to the next navigation point; the map generating device also includes: an updating unit 1005, used to update candidate obstacles; the updating unit 1005 is also used to update a third range based on preset conditions, the third range includes: a first range and / or a second range, the second range is smaller than the first range, the preset condition is related to the updated scanned obstacles, or the preset condition is related to the first range and the updated candidate obstacles; the control unit 1002 is also used to control the terminal device to navigate based on the updated third range.

[0156] In this embodiment, the operations performed by each unit in the map generation device are the same as those described above. Figures 1A to 9 The description in the illustrated embodiment is similar and will not be repeated here.

[0157] In this embodiment, the control unit 1002 controls the terminal device to navigate to the first obstacle in the sensor scanning range, the determination unit 1003 determines the next navigation point, and the generation unit 1004 generates a map based on the navigation track of the terminal device. Since the next navigation point may be the obstacle closest to the first obstacle among multiple candidate obstacles, or the next navigation point may be an obstacle that has not been selected among multiple obstacles and has not been passed by the terminal device. Then the map is generated through the navigation track of the terminal device. That is, in the process of generating the map, the next navigation point is determined through the candidate obstacles. On the one hand, the candidate obstacles can be updated in real time, so as to conduct a comprehensive exploration, thereby achieving the completion of the map without a static map. On the other hand, by determining the candidate obstacles through the two ranges corresponding to the scan, the repeated exploration of the subsequent scanned obstacles can be reduced, thereby achieving efficient mapping.

[0158] See also Fig.11 , a schematic diagram of the structure of another map generation device provided in an embodiment of the present application. The map generation device may include a processor 1101, a memory 1102, and a communication port 1103. The processor 1101, the memory 1102, and the communication port 1103 are interconnected via a line. The memory 1102 stores program instructions and data.

[0159] The memory 1102 stores the aforementioned Figures 1A to 9 In the corresponding implementation manner shown, the steps executed by the map generating device correspond to program instructions and data.

[0160] Processor 1101, used to execute the above Figures 1A to 9 The steps performed by the map generating device in any of the illustrated embodiments.

[0161] The communication port 1103 can be used to receive and send data, and to perform the aforementioned Figures 1A to 9The steps related to obtaining, sending and receiving in any of the embodiments shown.

[0162] In one implementation, the map generation device may include a Fig.11 More or fewer components are merely illustrative in this application and are not limiting.

[0163] The embodiment of the present application also provides another map generation method, which is applied to a control device, and includes: receiving a first request; in response to the first request, controlling the terminal device to navigate to a first obstacle and a next navigation point, and generating a map based on the navigation track of the terminal device. The first obstacle and the next navigation point are based on the aforementioned Figures 1A to 9 Determined by the method in the illustrated embodiment; receiving map construction information from a terminal device; and generating a map based on the map construction information.

[0164] The embodiment of the present application also provides another map generation method, which is applied to a terminal device, and the method includes: sending a first request to a control device; receiving a control instruction in response to the first request, navigating to a first obstacle and a next navigation point, and generating a map based on the navigation trajectory of the terminal device; the first obstacle and the next navigation point are based on the aforementioned Figures 1A to 9 Determined by the method in the illustrated embodiment; a map is sent to a control device.

[0165] The embodiment of the present application also provides a system for map generation, the system comprising a control device and a terminal device; the terminal device is used to provide a plurality of obstacles within a first range, the first range being a scanning range of a sensor in the terminal device; the control device is used to determine a first obstacle and a next navigation point, the first obstacle and the next navigation point being based on the aforementioned Figures 1A to 9 The control device is also used to control the terminal device to navigate to the first obstacle and the next navigation point, and control the terminal device to generate a map based on the navigation track of the terminal device.

[0166] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0167] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0170] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A map generation method, characterized in that: The method comprises: Acquire a plurality of obstacles in a first range, where the first range is a scanning range of a sensor in a terminal device; Controlling the terminal device to navigate to a first obstacle, where the first obstacle is the obstacle closest to the terminal device among the multiple obstacles, or the obstacle whose distance is less than or equal to a first preset threshold; Determine a next navigation point of the terminal device, the next navigation point being an obstacle among the multiple candidate obstacles that has the shortest distance from the first obstacle or is less than or equal to a second preset threshold, or the next navigation point being an obstacle that is not selected among the multiple obstacles and that the terminal device has not passed through, wherein the candidate obstacles include obstacles newly scanned by the terminal device during navigation to the first obstacle and / or any obstacle among the multiple obstacles except the first obstacle; A map is generated based on a navigation track of the terminal device, where the navigation track includes the first obstacle and the next navigation point.

2. The method according to claim 1, characterized in that The terminal device includes a first navigation mode and a second navigation mode, and the first navigation mode and the second navigation mode are used to determine a next navigation point of the terminal device.

3. The method according to claim 2, characterized in that The determining the next navigation point of the terminal device includes: The next navigation point is determined according to the first navigation mode to be an obstacle among the multiple candidate obstacles whose distance to the first obstacle is the shortest or is less than or equal to a second preset threshold.

4. The method according to claim 2, characterized in that: The determining the next navigation point of the terminal device includes: The next navigation point is determined according to the second navigation mode to be an obstacle that is not selected among the multiple obstacles and that the terminal device has not passed through.

5. The method according to any one of claims 1 to 4, characterized in that The navigation track also includes at least one of the following: the position of an obstacle scanned during the movement of the terminal device, and the distance between multiple obstacles scanned during the movement of the terminal device.

6. The method according to any one of claims 1 to 5, characterized in that The next navigation point is determined by any of the following methods: Minimum triangle perimeter; Minimum triangle area; Shortest distance.

7. The method according to any one of claims 1 to 6, characterized in that Before determining the next navigation point of the terminal device, the method further includes: The navigation mode of the terminal device is determined based on the scanned obstacles and the candidate obstacles.

8. The method according to claim 7, characterized in that The determining the navigation mode of the terminal device based on the scanned obstacles and the candidate obstacles includes: The scanned obstacles and the candidate obstacles are input into a trained neural network to obtain a result, wherein the result includes a first navigation mode or a second navigation mode, and the trained neural network is trained according to a preset navigation path.

9. The method according to any one of claims 1 to 8, characterized in that Before generating a map based on the navigation track of the terminal device, the method further includes: Controlling the terminal device to navigate to the next navigation point; Updating the candidate obstacles; updating a third range based on a preset condition, the third range including: the first range and / or the second range, the second range being smaller than the first range, the preset condition being related to the updated scanned obstacle, or the preset condition being related to the first range and the updated candidate obstacle; The terminal device is controlled to navigate based on the updated third range.

10. A map generating device, characterized in that: The map generating device comprises: An acquisition unit, configured to acquire a plurality of obstacles in a first range, where the first range is a scanning range of a sensor in a terminal device; A control unit, configured to control the terminal device to navigate to a first obstacle, where the first obstacle is the obstacle closest to the terminal device among the multiple obstacles, or the obstacle whose distance is less than or equal to a first preset threshold; a determining unit, configured to determine a next navigation point of the terminal device, the next navigation point being an obstacle among the multiple candidate obstacles that has the shortest distance from the first obstacle or is less than or equal to a second preset threshold, or the next navigation point being an obstacle that is not selected among the multiple obstacles and that the terminal device has not passed, wherein the candidate obstacles include obstacles newly scanned by the terminal device during navigation to the first obstacle and / or any obstacle among the multiple obstacles except the first obstacle; A generating unit is used to generate a map based on a navigation track of the terminal device, wherein the navigation track includes the first obstacle and the next navigation point.

11. The map generating device according to claim 10, characterized in that: The terminal device comprises a first navigation mode and a second navigation mode, and the first navigation mode and the second navigation mode are used by the determination unit to determine a next navigation point of the terminal device.

12. The map generating device according to claim 11, characterized in that: The determining unit is specifically configured to determine, according to the first navigation mode, that the next navigation point is an obstacle among the multiple candidate obstacles whose distance to the first obstacle is the shortest or is less than or equal to a second preset threshold.

13. The map generating device according to claim 11, characterized in that: The determination unit is specifically used to determine, according to the second navigation mode, that the next navigation point is an obstacle that is not selected among the multiple obstacles and that the terminal device has not passed through.

14. The map generating device according to any one of claims 10 to 13, characterized in that: The navigation track also includes at least one of the following: the position of an obstacle scanned during the movement of the terminal device, and the distance between multiple obstacles scanned during the movement of the terminal device.

15. The map generating device according to any one of claims 10 to 14, characterized in that: The next navigation point is determined by any of the following methods: Minimum triangle perimeter; Minimum triangle area; Shortest distance.

16. The map generating device according to any one of claims 10 to 15, characterized in that: The determination unit is further used to determine the navigation mode of the terminal device based on the scanned obstacles and the candidate obstacles.

17. The map generating device according to claim 16, characterized in that: The determination unit is specifically used to input the scanned obstacle and the candidate obstacle into a trained neural network to obtain a result, wherein the result includes a first navigation mode or a second navigation mode, and the trained neural network is trained according to a preset navigation path.

18. The map generating device according to any one of claims 10 to 17, characterized in that: The control unit is further used to control the terminal device to navigate to the next navigation point; The map generating device further comprises: An updating unit, configured to update the candidate obstacles; The updating unit is further configured to update a third range based on a preset condition, the third range including: the first range and / or the second range, the second range being smaller than the first range, the preset condition being related to the updated scanned obstacle, or the preset condition being related to the first range and the updated candidate obstacle; The control unit is further used to control the navigation of the terminal device based on the updated third range.

19. A map generating device, characterized in that: include: A processor is coupled to a memory, wherein the memory is used to store programs or instructions. When the programs or instructions are executed by the processor, the map generating device executes the method according to any one of claims 1 to 9.

20. A method for map generation, characterized in that: The method is applied to a control device, and the method comprises: receiving a first request; In response to the first request, controlling the terminal device to navigate to a first obstacle and a next navigation point, and collecting map construction information during the movement; the first obstacle and the next navigation point are determined according to any one of the methods of claims 1 to 9; Receiving the map construction information from the terminal device; A map is generated based on the map construction information.

21. A method for map generation, characterized in that: The method is applied to a terminal device, and the method comprises: Sending a first request to a control device; receiving a control instruction in response to the first request, navigating to a first obstacle and a next navigation point, and generating a map based on the navigation trajectory of the terminal device; the first obstacle and the next navigation point are determined according to any one of the methods of claims 1 to 9; The map is sent to the control device.

22. A system for map generation, characterized in that: Including control equipment and terminal equipment; The terminal device is used to provide a plurality of obstacles within a first range, where the first range is a scanning range of a sensor in the terminal device; The control device is used to determine a first obstacle and a next navigation point, wherein the first obstacle and the next navigation point are determined according to any one of the methods of claims 1 to 9; The control device is also used to control the terminal device to navigate to the first obstacle and the next navigation point, and control the terminal device to generate a map based on the navigation trajectory of the terminal device.

23. A computer storage medium, characterized in that The method comprises computer instructions, and when the computer instructions are executed on a terminal device, the terminal device executes the method according to any one of claims 1 to 9.

24. A computer program product, characterized in that When the computer program product is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 9.

Citation Information

Cited By

  • Map generation method and related device

    EP4722649A1

  • Map generation method and related device

    WO2024251021A1