Coal mining vehicle path planning and obstacle avoidance method based on inertial navigation

By integrating GPS, inertial navigation, and visual obstacle recognition technologies, the coal mining vehicle achieves precise positioning and dynamic obstacle avoidance in the mining environment, solving the problems of low navigation accuracy and poor obstacle avoidance capability, and improving the safety and operational efficiency of the coal mining vehicle.

CN119002494APending Publication Date: 2024-11-22CHINA AEROSPACE TECH CO LTD (HANGZHOU)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411104163.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Traditional coal mining vehicles suffer from low navigation accuracy and poor obstacle avoidance capabilities in complex mining environments, resulting in high safety risks and low efficiency.

Method used

By combining GPS, inertial navigation, and visual obstacle recognition modules, it achieves precise positioning and obstacle recognition, dynamically adjusts path planning, generates return routes, and provides real-time feedback to the control center and mobile terminals.

Benefits of technology

Significantly reduces collision risk, improves operational safety and efficiency, optimizes path planning, enhances the level of intelligent operation and maintenance management, and reduces downtime due to failures.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119002494A_ABST
    Figure CN119002494A_ABST
Patent Text Reader

Abstract

The invention discloses a coal mining vehicle path planning and obstacle avoidance method based on inertial navigation. The method comprises the following steps: a control center issues a pre-planned advancing path to a coal mining vehicle control module; the initial position of the coal mining vehicle is obtained according to a GPS module, and whether the initial position of the coal mining vehicle is located at the starting point of the advancing path is judged; if not, generating a homing path according to the initial position of the coal mining vehicle and the starting point of the advancing path; in the process that the coal mining vehicle moves to the starting point of the advancing path, obstacle avoidance is conducted through the inertial navigation module and the visual obstacle recognition module. By integrating the GPS module, the inertial navigation module and the visual impairment recognition module, accurate positioning and immediate recognition of obstacles can be achieved in a complex mine environment, the collision risk is remarkably reduced, and the safety of coal mining workers and equipment is guaranteed; through combination of visual disorder recognition and inertial navigation prediction, the advancing route of the coal mining vehicle can be dynamically adjusted, obstacles are avoided, it is ensured that the coal mining vehicle advances along the safest and most efficient path all the time, and therefore the operation efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of mining operations, and in particular to a coal mining vehicle path planning and obstacle avoidance method based on inertial navigation. Background Art

[0002] With the continuous development of the coal industry, the level of automation and intelligence is particularly important in coal mining operations. Traditional coal mining operations rely on manual driving and simple guidance systems, which are not only inefficient, but also have extremely high safety risks in complex and changeable mine environments. Especially in underground mines, due to factors such as insufficient light, narrow space, and complex terrain, coal mining vehicles often face problems such as low navigation accuracy and poor obstacle avoidance. Therefore, developing an efficient and reliable coal mining vehicle path planning and obstacle avoidance system has become the key to improving the safety and production efficiency of mining operations.

[0003] Inertial navigation technology, combined with GPS positioning and visual recognition, provides a possible solution to the above problems. The inertial navigation system is not affected by the external environment and can provide continuous and autonomous positioning information, while visual recognition technology can effectively identify obstacles ahead. The combination of the two can significantly improve the environmental adaptability and autonomous navigation performance of coal mining vehicles. However, how to accurately integrate this information to achieve dynamic path planning and real-time obstacle avoidance is still the focus of current technical research. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a coal mining vehicle path planning and obstacle avoidance method based on inertial navigation.

[0005] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be a general review, nor is it intended to identify key / important components or to delineate the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0006] The present invention adopts the following technical solution:

[0007] The present invention provides a coal mining vehicle path planning and obstacle avoidance method based on inertial navigation, comprising the following steps:

[0008] S100: The control center sends the pre-planned travel path to the coal mining vehicle control module;

[0009] S200: The coal mining vehicle control module obtains the initial position of the coal mining vehicle according to the GPS module, and determines whether the initial position of the coal mining vehicle is located at the starting point of the travel path; if not, a return path is generated according to the initial position of the coal mining vehicle and the starting point of the travel path;

[0010] S300: The coal mining vehicle control module drives the coal mining vehicle to move to the starting point of the travel path according to the homing path; wherein, during the process of the coal mining vehicle moving to the starting point of the travel path, obstacle avoidance is performed through the inertial navigation module and the visual obstacle recognition module.

[0011] Furthermore, in the process of the coal mining vehicle moving to the starting point of the travel path, obstacle avoidance is performed by using the inertial navigation module and the visual obstacle recognition module, including:

[0012] S310: The visual obstacle recognition module uses a camera to capture an image in the direction of the coal mining vehicle, and recognizes obstacles in the image;

[0013] S320: Obtain the obstacle position;

[0014] S330: The inertial navigation module predicts the position of the coal mining vehicle after a set time interval;

[0015] S340: The coal mining vehicle control module determines whether the obstacle is located within the position of the coal mining vehicle after the set time interval. If so, S350 is executed; if not, S360 is executed;

[0016] S350: The coal mining vehicle control module generates a new homing path and re-executes S310;

[0017] S360: The coal mining vehicle control module drives the coal mining vehicle to continue moving along the original return path.

[0018] Furthermore, the step S320 includes:

[0019] S321: Obtain camera intrinsic parameters and camera extrinsic parameters; wherein the camera intrinsic parameters include focal length and principal point position, and the camera extrinsic parameters include rotation matrix and translation vector;

[0020] S322: extracting pixel coordinates to determine the pixel position of the obstacle on the image;

[0021] S323: converting normalized coordinates, using camera intrinsic parameters to convert pixel coordinates into normalized coordinates;

[0022] S324: Three-dimensional coordinate reconstruction, using normalized coordinates and focal length to obtain the three-dimensional coordinates of the obstacle in the camera coordinate system;

[0023] S325: Obtain world coordinates, use camera extrinsics to transform the obstacle position in the camera coordinate system into the world coordinate system, and obtain the coordinates of the obstacle in the world coordinate system.

[0024] Furthermore, the obstacles include rocks, pits or other coal mining machines.

[0025] Furthermore, the coal mining vehicle path planning and obstacle avoidance method based on inertial navigation further includes the following steps:

[0026] S400: The coal mining vehicle control module sends the return path to the control center, and the control center generates an estimated return time according to the return path;

[0027] S500: When the estimated return time is reached, the control center determines whether the coal mining vehicle has reached the starting point of the travel path. If the coal mining vehicle has not reached the starting point of the travel path within the estimated return time, the control center generates inspection information and sends the inspection information to the mobile terminal, wherein the inspection information includes: the coal mining vehicle number and the return path.

[0028] Furthermore, the coal mining vehicle path planning and obstacle avoidance method based on inertial navigation further includes the following steps:

[0029] S600: The mobile terminal generates a collection box of the coal mining vehicle number, the return path and the cause of the fault on the screen of the mobile terminal according to the acquired inspection information, and issues a sound alarm;

[0030] S700: After the mobile terminal collects the cause of the fault and the transmission signal, it binds the coal mining vehicle number, the return path and the cause of the fault to generate feedback information and uploads it to the control center

[0031] The beneficial effects brought by the present invention are:

[0032] Improve safety and reliability: By integrating GPS module, inertial navigation module and visual obstacle recognition module, this method can achieve accurate positioning and instant obstacle recognition in complex mine environments, significantly reduce collision risks, and ensure the safety of coal mining workers and equipment;

[0033] Optimize path planning efficiency: Combining visual obstacle recognition with inertial navigation prediction, the route of the coal mining vehicle can be dynamically adjusted to avoid obstacles, ensuring that the coal mining vehicle always moves along the safest and most efficient path, thereby improving overall operating efficiency;

[0034] Improve the intelligent level of operation and maintenance management: By feeding back information such as the return path and estimated duration to the control center and mobile terminals in real time, remote monitoring and intelligent analysis of the coal mining vehicle's operating status are realized, which facilitates timely scheduling and fault handling, and enhances the information management level of mine operations;

[0035] Fault response mechanism: Once the coal mining vehicle fails to return as planned, the system automatically triggers the inspection process. The intervention of mobile terminals makes the collection of fault information more convenient, promotes the rapid location and processing of faults, reduces downtime, and ensures the continuity of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flow chart of a coal mining vehicle path planning and obstacle avoidance method based on inertial navigation of the present invention;

[0038] Figure 2 It is a schematic diagram of the process of avoiding obstacles by using an inertial navigation module and a visual obstacle recognition module in the present invention;

[0039] Figure 3 It is a schematic diagram of the process of obtaining the obstacle position of the present invention. DETAILED DESCRIPTION

[0040] The embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. It should be clear that the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] like Figure 1-3 As shown, in some illustrative embodiments, a coal mining vehicle path planning and obstacle avoidance method based on inertial navigation is provided, comprising the following steps:

[0042] S100: The control center sends the pre-planned travel path to the coal mining vehicle control module.

[0043] Based on the mine map and mining progress, the control center sends a preset optimal path data packet to the coal mining vehicle control module through wireless communication technology (such as Wi-Fi or private network), which contains information such as the travel path and expected travel speed formed by the path point coordinate sequence. The coal mining vehicle control module obtains the travel path issued by the control center to ensure that the coal mining vehicle moves in accordance with the overall planning and safety requirements of the mining area, avoiding inefficiency or safety accidents caused by random driving.

[0044] S200: The coal mining vehicle control module obtains the initial position of the coal mining vehicle according to the GPS module, and determines whether the initial position of the coal mining vehicle is located at the starting point of the travel path. If it is located at the starting point of the travel path, S201 is performed: a travel start instruction is issued; if not, S202 is performed: a return path is generated according to the initial position of the coal mining vehicle and the starting point of the travel path.

[0045] After the coal mining car control module receives the latitude and longitude data of the initial position sent by the GPS module, it compares it with the coordinates of the starting point of the travel path. If there is a deviation, the Dijkstra algorithm is used to find the shortest or optimal path from the initial position of the coal mining car to the starting point of the travel path on the mine map as the return path. This ensures that the coal mining car reaches the task starting point safely and accurately from the current position, improving the efficiency of task startup.

[0046] S300: The coal mining vehicle control module drives the coal mining vehicle to move to the starting point of the travel path according to the return path. In order to ensure that the coal mining vehicle can dynamically adjust the route to avoid obstacles and ensure the safety of the journey when it moves to the starting point of the mission, the coal mining vehicle avoids obstacles through the inertial navigation module and the visual obstacle recognition module when it moves to the starting point of the travel path, which specifically includes the following steps:

[0047] S310: The visual obstacle recognition module uses a camera to capture an image of the coal mining vehicle's forward direction and recognizes obstacles in the image. The obstacles include rocks, pits, or other coal mining machines.

[0048] The camera is installed on the coal mining car to capture real-time images in the direction of the coal mining car. The camera setting ensures that it can cover the path of the coal mining car and the range of possible obstacles. The images obtained by the visual obstacle recognition module may contain noise, light reflection and other problems, and need to be purified through pre-processing technology, such as filtering, contrast enhancement, denoising, etc., in order to more accurately identify obstacles.

[0049] The pre-processed images are analyzed to identify potential obstacles through image recognition algorithms such as edge detection, contour recognition, deep learning models, etc. After the obstacles are detected, they are further classified to distinguish their nature and size, such as distinguishing between rocks, pits or other coal mining machines.

[0050] S320: Obtain the obstacle position.

[0051] S330: The inertial navigation module predicts the position of the coal mining vehicle after a set time interval.

[0052] The inertial navigation module is an important system on the coal mining car. It predicts the position of the coal mining car after a preset time interval by analyzing the coal mining car's current speed, direction and acceleration information. When predicting the coal mining car's future position, the inertial navigation module takes into account the coal mining car's current speed and acceleration, as well as any known dynamic changes, such as acceleration or deceleration that the coal mining car may encounter. By integrating the coal mining car's speed and acceleration data, the displacement of the coal mining car in the next time interval is calculated, thereby predicting the future position.

[0053] S340: The coal mining vehicle control module determines whether the obstacle position is within the position of the coal mining vehicle after the set time interval. If so, execute S350, if not, execute S360.

[0054] S350: The coal mining car control module generates a new homing path and re-executes S310. If it is determined that the obstacle is located within the position after the time interval set by the coal mining car, it means that the obstacle may still exist when the coal mining car moves to this position, and there is a risk of collision. Therefore, the coal mining car control module executes S350, that is, generates a new homing path, which will bypass the obstacle and ensure that the coal mining car can travel safely.

[0055] S360: The coal mining car control module drives the coal mining car to continue to move along the original homing path. If the obstacle is not within the position after the time interval set by the coal mining car, it means that the obstacle will not affect the driving of the coal mining car. In this case, the coal mining car control module will execute S360 and drive the coal mining car to continue to move along the original homing path.

[0056] Among them, S320: obtaining the obstacle position, specifically includes:

[0057] S321: Obtain camera intrinsic parameters and camera extrinsic parameters; wherein the camera intrinsic parameters include focal length and principal point position, and the camera extrinsic parameters include rotation matrix and translation vector relative to the world coordinate system.

[0058] The principal point position refers to a specific point on the camera image sensor, which is the point where the camera optical axis (i.e. the extension line of the camera lens center) intersects with the image sensor plane. In the camera coordinate system, this point has a special geometric meaning because it determines the focus position on the image plane after the object is projected through the lens at infinity without distortion.

[0059] S322: Extract pixel coordinates to determine the pixel position of the obstacle on the image. Use image processing technology to separate the obstacle area from the entire image, and use edge linking technology to find the outline of the obstacle in the obstacle area. Once the outline of the obstacle is determined, the coordinates of each pixel can be extracted by traversing the points on these contours.

[0060] S323: Convert normalized coordinates, convert pixel coordinates to normalized coordinates using camera intrinsic parameters, and correct scale issues caused by image resolution and focal length.

[0061] S324: Reconstruct the three-dimensional coordinates using the triangulation principle, and use the normalized coordinates and focal length to obtain the three-dimensional coordinates of the obstacle in the camera coordinate system.

[0062] S325: Obtain world coordinates, use camera extrinsics to transform the obstacle position in the camera coordinate system into the world coordinate system, and obtain the coordinates of the obstacle in the world coordinate system.

[0063] S400: In order to improve the transparency and coordination of the entire operating system and facilitate remote management and emergency response, the coal mining vehicle control module sends the return path to the control center, and the control center generates an estimated return time based on the return path.

[0064] The control center will evaluate the environmental conditions on the return route, including weather conditions, channel congestion, traffic light status, traffic rules, etc. Based on the evaluated environmental conditions, the control center will predict the average speed of the coal mining vehicle on a specific path, multiply the path length and the predicted average speed, and calculate the time required to complete the entire voyage.

[0065] S500: When the estimated return time is reached, the control center determines whether the coal mining vehicle has reached the starting point of the travel path. If so, proceed to S201. If the coal mining vehicle has not reached the starting point of the travel path within the estimated return time, proceed to S501: The control center generates inspection information and sends the inspection information to the mobile terminal, where the inspection information includes: the coal mining vehicle number and the return path.

[0066] S600: In order to simplify the fault reporting process, speed up problem solving, and reduce downtime caused by faults, the mobile terminal generates a collection box for the coal mining vehicle number, return path, and fault cause on the screen of the mobile terminal based on the inspection information obtained, displays it, and issues a sound alarm.

[0067] S700: When the mobile terminal collects the cause of the fault and the transmission signal, it binds the coal mining car number, return path and cause of the fault to generate feedback information and upload it to the control center. The mobile terminal application interface is user-friendly and easy to operate. Workers can quickly enter the cause of the fault and submit it. The background system automatically records and classifies the fault information and notifies the maintenance team. At the same time, historical data can be used for preventive maintenance analysis.

[0068] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A coal mining vehicle path planning and obstacle avoidance method based on inertial navigation, characterized in that: The steps include: S100: The control center sends the pre-planned travel path to the coal mining vehicle control module; S200: The coal mining vehicle control module obtains the initial position of the coal mining vehicle according to the GPS module, and determines whether the initial position of the coal mining vehicle is located at the starting point of the travel path; if not, a return path is generated according to the initial position of the coal mining vehicle and the starting point of the travel path; S300: The coal mining vehicle control module drives the coal mining vehicle to move to the starting point of the travel path according to the homing path; wherein, during the process of the coal mining vehicle moving to the starting point of the travel path, obstacle avoidance is performed through the inertial navigation module and the visual obstacle recognition module.

2. A coal mining vehicle path planning and obstacle avoidance method based on inertial navigation according to claim 1, characterized in that: In the process of the coal mining vehicle moving to the starting point of the travel path, obstacle avoidance is performed by using the inertial navigation module and the visual obstacle recognition module, including: S310: The visual obstacle recognition module uses a camera to capture an image in the direction of the coal mining vehicle, and recognizes obstacles in the image; S320: Obtain the obstacle position; S330: The inertial navigation module predicts the position of the coal mining vehicle after a set time interval; S340: The coal mining vehicle control module determines whether the obstacle is located within the position of the coal mining vehicle after the set time interval. If so, S350 is executed; if not, S360 is executed; S350: The coal mining vehicle control module generates a new homing path and re-executes S310; S360: The coal mining vehicle control module drives the coal mining vehicle to continue moving along the original return path.

3. A coal mining vehicle path planning and obstacle avoidance method based on inertial navigation according to claim 2, characterized in that: The step S320 includes: S321: Obtain camera intrinsic parameters and camera extrinsic parameters; wherein the camera intrinsic parameters include focal length and principal point position, and the camera extrinsic parameters include rotation matrix and translation vector; S322: extracting pixel coordinates to determine the pixel position of the obstacle on the image; S323: converting normalized coordinates, using camera intrinsic parameters to convert pixel coordinates into normalized coordinates; S324: Three-dimensional coordinate reconstruction, using normalized coordinates and focal length to obtain the three-dimensional coordinates of the obstacle in the camera coordinate system; S325: Obtain world coordinates, use camera extrinsics to transform the obstacle position in the camera coordinate system into the world coordinate system, and obtain the coordinates of the obstacle in the world coordinate system.

4. A coal mining vehicle path planning and obstacle avoidance method based on inertial navigation according to claim 3, characterized in that: The obstacles include rocks, pits or other coal mining machines.

5. A coal mining vehicle path planning and obstacle avoidance method based on inertial navigation according to claim 4, characterized in that: The following steps are also included: S400: The coal mining vehicle control module sends the return path to the control center, and the control center generates an estimated return time according to the return path; S500: When the estimated return time is reached, the control center determines whether the coal mining vehicle has reached the starting point of the travel path. If the coal mining vehicle has not reached the starting point of the travel path within the estimated return time, the control center generates inspection information and sends the inspection information to the mobile terminal, wherein the inspection information includes: the coal mining vehicle number and the return path.

6. A coal mining vehicle path planning and obstacle avoidance method based on inertial navigation according to claim 5, characterized in that: The following steps are also included: S600: The mobile terminal generates a collection box of the coal mining vehicle number, the return path and the cause of the fault on the screen of the mobile terminal according to the acquired inspection information, and issues a sound alarm; S700: After the mobile terminal collects the cause of the fault and the sending signal, the coal mining vehicle number, the return path and the cause of the fault are bound to generate feedback information and uploaded to the control center.