Collision avoidance control method and device for mobile terminal and terminal

By generating grid maps and using machine learning to identify obstacles, dynamically adjusting the stopping distance and speed limits, the traffic jam problem in the existing technology of robots not adapting to different scenarios and collaborating with multiple machines is solved, and the traffic jamming problem in the current technology is achieved in a complex manner. Efficient traffic and safe operation in the environment.

CN119065376APending Publication Date: 2024-12-03INFORE ROBOTICS&AUTOMATION CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411191444.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The prior art uses a fixed stop distance when robots avoid obstacles, and cannot adapt to different scenarios, resulting in poor traffic and may cause traffic jams when multiple machines cooperate in collaboration.

Method used

By obtaining environmental data, generating a raster map and marking the stopping distance in the preset area, adjusting the stopping behavior according to the type of obstacles and task priority, identifying obstacles using machine learning and deep learning models, dynamically adjusting the stopping distance and Speed ​​limit to avoid multiple machines from stopping each other.

Benefits of technology

It realizes normal traffic in different scenarios, avoids traffic jams of multiple robots, and improves the safety and efficiency of robots in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065376A_ABST
    Figure CN119065376A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of robots, in particular to a collision avoidance control method and device for a mobile terminal and the terminal, and the method comprises the steps: S1, obtaining environment data of an environment where the mobile terminal is located; s2, acquiring obstacle data according to the environment data, and acquiring a preset obstacle stopping distance of the preset area according to the environment data; s3, acquiring a real-time distance between the obstacle and the mobile terminal; s4, when the real-time distance is smaller than the preset obstacle stopping distance, the type of the obstacle is determined; s5, if the obstacle is another mobile terminal, the mobile terminal moves according to the obstacle and the task priority of the mobile terminal; and S6, if the obstacle is a common obstacle, the mobile terminal stops moving. According to the scheme, the occupied CPU resources are low, and the situation that multiple mobile terminals stop mutually at the same time can be avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of mobile robots, and in particular to a collision avoidance control method, device and terminal for a mobile terminal. Background Art

[0002] With the rapid development of robot technology, robots have been widely used in industry, service industry, logistics and other fields. In order to ensure the safe operation of robots in complex environments, collision avoidance technology is particularly important.

[0003] The existing solution is: determine the obstacles in the robot's current driving path based on the environmental information, determine the robot's motion state based on the obstacles, and stop to avoid obstacles when the distance from the obstacle to the vehicle body is less than a fixed distance. However, there are the following problems: 1. Using a fixed obstacle stop distance, it is impossible to pass all channels normally, and the adaptability to different scenarios is not strong enough; 2. When multiple robots work together, other robots will also be treated as obstacles, causing multiple robots to stop each other and cause traffic congestion.

[0004] In view of the above problems, those skilled in the art have been seeking solutions. Summary of the invention

[0005] The technical problem to be solved by the present application is to provide a collision avoidance control method, device and terminal for a mobile terminal in view of the defects of the above-mentioned prior art.

[0006] In order to achieve the above objectives, this application is implemented through the following technical solutions:

[0007] A collision avoidance control method for a mobile terminal, comprising:

[0008] S1. Obtaining environmental data of the environment in which the mobile terminal is located;

[0009] S2. Obtain obstacle data according to the environmental data, and obtain a preset obstacle stopping distance of a preset area according to the environmental data;

[0010] S3, obtaining a real-time distance between the obstacle and the mobile terminal;

[0011] S4. determining the type of the obstacle when the real-time distance is less than the preset obstacle stopping distance;

[0012] S5. If the obstacle is another mobile terminal, the mobile terminal moves according to the obstacle and the task priority of the mobile terminal;

[0013] S6. If the obstacle is a common obstacle, the movable terminal stops moving.

[0014] Optionally, step S2 includes:

[0015] Obstacle identification is performed on the environmental data using a machine learning and / or deep learning model to obtain obstacle data.

[0016] Optionally, step S2 further includes:

[0017] generating a grid map according to the environmental data;

[0018] Marking a preset area in the grid map according to a special area in the environmental data;

[0019] The preset safety distance is marked as the preset obstacle stopping distance of the preset area.

[0020] Optionally, the grid map includes a plurality of grids, each of which stores speed limit information of the mobile terminal;

[0021] The method further comprises:

[0022] The movable terminal moves according to the speed limit information.

[0023] Optionally, step S5 includes:

[0024] When the obstacle is another mobile terminal, obtaining the mobile ID of the obstacle;

[0025] Acquire the task priority of the obstacle according to the mobile ID;

[0026] Determining whether the task priority of the obstacle is higher than the task priority of the mobile terminal;

[0027] If yes, the mobile terminal stops at the obstacle according to the preset obstacle stopping distance, and the obstacle passes;

[0028] If not, the movable terminal passes and the obstacle stops.

[0029] The present application also provides a collision avoidance control device, comprising: a data acquisition module, a data processing module, and an execution module;

[0030] The data acquisition module is used to acquire environmental data of the environment in which the mobile terminal is located, and to acquire the real-time distance between the obstacle and the mobile terminal;

[0031] The data processing module is used to obtain obstacle data according to the environmental data, obtain a preset obstacle stopping distance of a preset area according to the environmental data, and determine the type of the obstacle when the real-time distance is less than the preset obstacle stopping distance;

[0032] The execution module is used to control the movable terminal to move according to the obstacle and the task priority of the movable terminal when the obstacle is another mobile terminal, and to control the movable terminal to stop moving when the obstacle is a common obstacle.

[0033] Optionally, the data processing module is further used to use machine learning and / or deep learning models to perform obstacle identification on the environmental data to obtain obstacle data.

[0034] Optionally, the data processing module is also used to generate a grid map based on the environmental data, and mark preset areas in the grid map according to special areas in the environmental data, and mark a preset safety distance as a preset obstacle stopping distance of the preset area.

[0035] Optionally, the data acquisition module is further used to acquire the mobile ID of the obstacle when the obstacle is another mobile terminal, and acquire the task priority of the obstacle according to the mobile ID;

[0036] The data processing module is further used to determine whether the task priority of the obstacle is higher than the task priority of the mobile terminal;

[0037] The execution module is further used to: when the task priority of the obstacle is higher than the task priority of the mobile terminal, control the mobile terminal to stop the obstacle according to the preset obstacle stopping distance;

[0038] The execution module is further used to control the passage of the mobile terminal when the task priority of the obstacle is lower than the task priority of the mobile terminal.

[0039] The present application also provides a terminal, comprising: a memory and a processor, wherein a computer program is stored in the memory;

[0040] wherein the processor is configured to execute a computer program in the memory;

[0041] When the computer program is executed by the processor, the above method is implemented.

[0042] The present application provides a collision avoidance control method, device and terminal for a mobile terminal, which converts a safe area into a grid map, searches for attributes in the grid map in real time, calculates the terminal's movement priority according to the task priority, uses different obstacle stopping distances according to the different areas currently entered by the mobile terminal, occupies low CPU resources, can avoid multiple mobile terminals from stopping at each other at the same time, and can pass through different narrow scenes normally.

[0043] In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present application is described in detail below with reference to the accompanying drawings and specific implementation methods;

[0045] Figure 1 is a flow chart of a collision avoidance control method provided by an embodiment of the present application;

[0046] Figure 2 is a schematic diagram of a global map provided by an embodiment of the present application;

[0047] Figure 3 is a partial schematic diagram of a grid map provided in an embodiment of the present application;

[0048] Figure 4 It is a schematic diagram of the structure of a collision avoidance control device provided in one embodiment of the present application. Specific embodiments

[0049] It should be understood that the specific embodiments described herein are only used to explain the present application, and the movable terminal in the specific embodiments is a robot, which is not used to limit the present application.

[0050] With the rapid development of robotics technology, robots have been widely used in industries, services, logistics and other fields. In order to ensure the safe operation of robots in complex environments, collision avoidance technology is particularly important. Traditional single-sensor collision avoidance methods have limitations in environmental perception and processing complexity. Therefore, a robot collision avoidance method based on multi-sensor fusion is proposed to improve the safety and efficiency of robots in dynamic environments.

[0051] like Figure 1 As shown, the present application provides a collision avoidance control method for a mobile terminal, comprising:

[0052] S1. Obtain environmental data of the environment in which the mobile terminal is located.

[0053] When the mobile terminal is located in a movable area, such as an allowed movable area calibrated by a program, surrounding environment data is acquired by various sensors in the mobile terminal, including but not limited to cameras, laser radars, and position sensors.

[0054] S2. Obtain obstacle data according to the environmental data, and obtain a preset obstacle stopping distance of a preset area according to the environmental data.

[0055] Optionally, step S2 includes:

[0056] Obstacle data is obtained by performing obstacle recognition on environmental data using machine learning and / or deep learning models.

[0057] Optionally, step S2 further includes:

[0058] Generate raster maps based on environmental data;

[0059] Marking preset areas in the grid map according to special areas in the environmental data;

[0060] Mark the preset safety distance as the preset obstacle stopping distance of the preset area.

[0061] Figure 2 is a schematic diagram of a global map provided by an embodiment of the present application, see Figure 2 , after constructing the acquired environmental data into a 2D map where the mobile terminal is located, the preset area is marked on the map according to the information of each special area in the environmental data. The special area in the environment described in this application refers to a functional special area and a terrain special area that are different from the flat passage area, including but not limited to the working area, the narrow channel area, the slope area, and the parking area. Based on the floor area and safety of the special area, the safety distance attribute values ​​of these areas can be dynamically set, such as the safety distance attribute value of the narrow channel area is 0.2m, the safety distance attribute value of the slope area is 1.0m, the safety distance attribute value of the working area is 2.0m, and the safety distance attribute value of the parking area is 0.05m, and the safety distance attribute value is marked on the map as the preset obstacle stop distance of the preset area. When reading the map, the preset obstacle stop distance of the preset area can be read at the same time. Different obstacle stop distances are used according to the robot currently entering different areas, that is, when the machine enters a special area, the corresponding obstacle stop distance is automatically updated to adapt to the current area scene, so that the robot can pass through narrow and other special scenes normally.

[0062] Optionally, the grid map includes a plurality of grids, each grid storing speed limit information of the mobile terminal;

[0063] The movable terminal moves according to the speed limit information.

[0064] Figure 3 is a partial schematic diagram of a grid map provided by an embodiment of the present application. Figure 2 and Figure 3 After the 2D map is built and the preset area is marked, the global map is evenly divided into multiple rectangular grids. In this grid map, the area outside the parking area is set as a deceleration zone. According to the defined deceleration zone and stop area, multiple grid maps (resolution is configurable) are generated in advance. Each grid in the grid map stores the speed limit value in different directions. For example:

[0065] Forward speed limit: max_ve l*k (0≤k≤1);

[0066] Reverse speed limit: max_ve l*k (0≤k≤1);

[0067] Left shift speed limit: max_ve l*k (0≤k≤1);

[0068] Right shift speed limit: max_ve l*k (0≤k≤1);

[0069] Left rotation speed limit: max_ve l*k (0≤k≤1);

[0070] Right rotation speed limit: max_ve l*k (0≤k≤1);

[0071] Among them, the k value can be dynamically adjusted according to the distance of the obstacle.

[0072] The robot fuses multiple sensor data and converts them into two-dimensional / three-dimensional coordinate points on the grid map. By finding the attributes of the point in the grid map, the speed limit value in each direction can be obtained. During the movement, the robot only needs to process the sensor data in the direction of movement. This solution processes the environmental data into a grid map by pre-generating a grid map, and loads the map before the robot runs, which can reduce the load of real-time calculation and reduce CPU resource consumption.

[0073] S3. Obtain the real-time distance between the obstacle and the movable terminal.

[0074] S4. When the real-time distance is less than the preset obstacle stopping distance, determine the type of obstacle.

[0075] S5. If the obstacle is another mobile terminal, the movable terminal moves according to the obstacle and the task priority of the movable terminal.

[0076] Optionally, step S5 includes:

[0077] When the obstacle is another mobile terminal, obtain the mobile ID of the obstacle;

[0078] Obtain the task priority of the obstacle based on the mobile ID;

[0079] Determine whether the task priority of the obstacle is higher than the task priority of the movable terminal;

[0080] If so, the mobile terminal stops at the obstacle according to the preset obstacle stopping distance, and the obstacle is passed;

[0081] If not, the mobile terminal can pass and the obstacle will be stopped.

[0082] Based on multi-machine scheduling, the positions of other robots are obtained in real time, the outer contour of the robot is updated to other mobile terminals, and the attributes of the obstacle are set to the corresponding robot id. Step S5 is specifically as follows: (a) Determine whether the other mobile terminal is another robot. If not, the current robot stops the obstacle; (b) If it is another robot, obtain the id of the other robot and obtain its task priority; (c) Compare it with the priority of the current robot; (d) The robot with a low priority triggers the obstacle stop, and the robot with a high priority continues to pass.

[0083] In other embodiments, step S5 may further include: if the other mobile terminal is not a robot, or the ID of the other mobile terminal cannot be obtained, the current terminal is disabled.

[0084] S6. If the obstacle is a common obstacle, the movable terminal stops moving.

[0085] The common obstacles are any other obstacles different from the movable terminal, including dynamic obstacles (such as mobile life forms, mobile furniture, etc.) and static obstacles (such as immovable furniture, buildings, etc.).

[0086] The solution of the present application calculates the robot's passage priority based on the task priority, and stops for low-priority obstacles, which can avoid multiple machines stopping for obstacles at the same time, and the robot efficiency is better.

[0087] Figure 4 is a schematic diagram of the structure of a collision avoidance control device provided in an embodiment of the present application, see Figure 4 The present application also provides a collision avoidance control device, including: a data acquisition module, a data processing module, and an execution module.

[0088] The data acquisition module is used to acquire environmental data of the environment in which the mobile terminal is located, and to acquire the real-time distance between the obstacle and the mobile terminal.

[0089] The data processing module is used to obtain obstacle data according to the environmental data, obtain a preset obstacle stopping distance of a preset area according to the environmental data, and determine the type of obstacle when the real-time distance is less than the preset obstacle stopping distance.

[0090] The execution module is used to control the movable terminal to move according to the obstacle and the task priority of the movable terminal when the obstacle is other mobile terminals, and to control the movable terminal to stop moving when the obstacle is a common obstacle.

[0091] Optionally, the data processing module is also used to use machine learning and / or deep learning models to perform obstacle identification on environmental data to obtain obstacle data.

[0092] Optionally, the data processing module is also used to generate a grid map according to the environmental data, and mark a preset area in the grid map according to a special area in the environmental data, and mark a preset safety distance as a preset obstacle stopping distance of the preset area.

[0093] Optionally, the data acquisition module is further used to acquire the mobile ID of the obstacle when the obstacle is another mobile terminal, and acquire the task priority of the obstacle according to the mobile ID;

[0094] The data processing module is also used to determine whether the task priority of the obstacle is higher than the task priority of the movable terminal;

[0095] The execution module is also used to: when the task priority of the obstacle is higher than the task priority of the mobile terminal, control the mobile terminal to stop the obstacle according to the preset obstacle stopping distance;

[0096] The execution module is also used for controlling the passage of the movable terminal when the task priority of the obstacle is lower than the task priority of the movable terminal.

[0097] The present application also provides a terminal, comprising: a memory and a processor, wherein a computer program is stored in the memory;

[0098] wherein the processor is configured to execute a computer program in the memory;

[0099] When the computer program is executed by a processor, the above-mentioned method is implemented.

[0100] The terminal of the present application can be a robot, which is suitable for multi-machine scheduling scenarios in high dynamic environments. It can solve the collision problem in multi-machine scheduling scenarios, and the multi-machine scheduling efficiency and safety are good.

[0101] Obviously, the above shows and describes the basic principles and main features of the present application and the advantages of the present application. Those skilled in the art should understand that the present application is not limited by the above embodiments, and the embodiments and descriptions are only for explaining the principles of the present application. Any modification, equivalent replacement or improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A collision avoidance control method for a mobile terminal, characterized in that: include: S1. Obtaining environmental data of the environment in which the mobile terminal is located; S2. Obtain obstacle data according to the environmental data, and obtain a preset obstacle stopping distance of a preset area according to the environmental data; S3, obtaining a real-time distance between the obstacle and the mobile terminal; S4. determining the type of the obstacle when the real-time distance is less than the preset obstacle stopping distance; S5. If the obstacle is another mobile terminal, the mobile terminal moves according to the obstacle and the task priority of the mobile terminal; S6. If the obstacle is a common obstacle, the movable terminal stops moving.

2. The method according to claim 1, characterized in that Step S2 includes: Obstacle identification is performed on the environmental data using a machine learning and / or deep learning model to obtain obstacle data.

3. The method according to claim 1, characterized in that Step S2 also includes: generating a grid map according to the environmental data; Marking a preset area in the grid map according to a special area in the environmental data; The preset safety distance is marked as the preset obstacle stopping distance of the preset area.

4. The method according to claim 3, characterized in that The grid map includes a plurality of grids, each of which stores speed limit information of the mobile terminal; The method further comprises: The movable terminal moves according to the speed limit information.

5. The method according to claim 3, characterized in that Step S5 includes: When the obstacle is another mobile terminal, obtaining the mobile ID of the obstacle; Acquire the task priority of the obstacle according to the mobile ID; Determining whether the task priority of the obstacle is higher than the task priority of the mobile terminal; If yes, the mobile terminal stops at the obstacle according to the preset obstacle stopping distance, and the obstacle passes; If not, the movable terminal passes and the obstacle stops.

6. A collision avoidance control device, characterized in that: include: Data acquisition module, data processing module, execution module; The data acquisition module is used to acquire environmental data of the environment in which the mobile terminal is located, and to acquire the real-time distance between the obstacle and the mobile terminal; The data processing module is used to obtain obstacle data according to the environmental data, obtain a preset obstacle stopping distance of a preset area according to the environmental data, and determine the type of the obstacle when the real-time distance is less than the preset obstacle stopping distance; The execution module is used to control the movable terminal to move according to the obstacle and the task priority of the movable terminal when the obstacle is another mobile terminal, and to control the movable terminal to stop moving when the obstacle is a common obstacle.

7. The device according to claim 6, characterized in that The data processing module is also used to use machine learning and / or deep learning models to perform obstacle identification on the environmental data to obtain obstacle data.

8. The device according to claim 6, characterized in that The data processing module is also used to generate a grid map according to the environmental data, mark a preset area in the grid map according to a special area in the environmental data, and mark a preset safety distance as a preset obstacle stopping distance of the preset area.

9. The device according to claim 6, characterized in that The data acquisition module is also used to acquire the mobile ID of the obstacle when the obstacle is another mobile terminal, and acquire the task priority of the obstacle according to the mobile ID; The data processing module is further used to determine whether the task priority of the obstacle is higher than the task priority of the mobile terminal; The execution module is further used to: when the task priority of the obstacle is higher than the task priority of the mobile terminal, control the mobile terminal to stop the obstacle according to the preset obstacle stopping distance; The execution module is further used to control the passage of the mobile terminal when the task priority of the obstacle is lower than the task priority of the mobile terminal.

10. A terminal, characterized in that: include: A memory and a processor, wherein the memory stores a computer program; wherein the processor is configured to execute a computer program in the memory; When the computer program is executed by the processor, the method according to any one of claims 1 to 5 is implemented.