Track robot obstacle avoidance method, device, track robot and storage medium

Abstract

An embodiment of the present application provides an obstacle avoidance method, device, rail robot, and storage medium for a rail robot. The method includes: the rail robot determines first obstacle information by according to a preset safe obstacle avoidance area of the rail robot and TOF data. Then, the minimum value between the braking distance of the rail robot and the preset detection distance is determined as the first distance, and the maximum value between the deceleration stop distance of the rail robot and the preset distance is determined as the second distance. Next, second obstacle information is determined according to ultrasonic data, the first distance, and the second distance. Finally, according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor, the credible type of each obstacle is determined, and the operation of the rail robot is controlled according to the credible type of each obstacle. This technical solution can reduce the sensor misdetection rate and improve the control accuracy of the rail robot.

Description

Technical Field

[0001] This application relates to the field of robot technology, and particularly to an obstacle avoidance method, device, rail robot, and storage medium for a rail robot. Background Art

[0002] The movement of a rail robot depends on real-time detection of the surrounding environment by sensors, and then determines the subsequent movement mode according to the detection results. Therefore, it is very necessary for the sensors installed on the rail robot to have high precision and fast response capabilities.

[0003] During the process of using sensors by a rail robot for environmental detection, sensor misdetection is inevitable. Currently, in the scenario of using multiple sensors simultaneously, mainly by combining the ranging information of Time-of-Flight (TOF) data and ultrasonic data, an obstacle fusion point cloud is generated in real time to identify obstacles, thereby reducing sensor misdetection.

[0004] However, the scenarios applied by the existing technologies are relatively limited, and the sensor misdetection rate is relatively high, resulting in low accuracy in controlling the rail robot. Summary of the Invention

[0005] Embodiments of this application provide an obstacle avoidance method, device, rail robot, and storage medium for a rail robot, so as to achieve the effect of improving the control accuracy of the rail robot.

[0006] In a first aspect, embodiments of this application provide an obstacle avoidance method for a rail robot, which is applied to a rail robot equipped with a TOF sensor and an ultrasonic sensor. The method includes:

[0007] Determine first obstacle information according to a preset safe obstacle avoidance area of the rail robot and TOF data. The first obstacle information includes the obstacle position and a first obstacle type, and the first obstacle type includes a first type;

[0008] Determine the minimum value between the braking distance of the rail robot and a preset detection distance as a first distance, and determine the maximum value between the deceleration-to-stop distance of the rail robot and a preset distance as a second distance. The deceleration-to-stop distance is the distance traveled by the rail robot when decelerating to a stop at a preset acceleration, and the preset distance is the minimum distance preset between the rail robot and a fixed obstacle;

[0009] Determine second obstacle information based on the ultrasonic data, the first distance, and the second distance. The second obstacle information includes the obstacle distance and the second obstacle type. The second obstacle type includes the first type and the second type. The distance between the obstacle in the second type and the rail robot is less than the distance between the obstacle in the first type and the rail robot.

[0010] Determine the credible type of each obstacle according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor.

[0011] Control the operation of the rail robot according to the credible type of each obstacle.

[0012] In a second aspect, an obstacle avoidance device for a rail robot provided by an embodiment of the present application is characterized in that it is applied to a rail robot, and the rail robot is equipped with a TOF sensor and an ultrasonic sensor. The device includes:

[0013] A determination module, configured to determine first obstacle information according to a preset safe obstacle avoidance area of the rail robot and TOF data. The first obstacle information includes the obstacle position and the first obstacle type. The first obstacle type includes the first type.

[0014] The determination module is further configured to determine the minimum value between the braking distance of the rail robot and the preset detection distance as the first distance, and determine the maximum value between the deceleration stop distance of the rail robot and the preset distance as the second distance. The deceleration stop distance is the distance traveled by the rail robot when decelerating to a stop at a preset acceleration, and the preset distance is the minimum distance preset between the rail robot and a fixed obstacle.

[0015] The determination module is further configured to determine second obstacle information according to the ultrasonic data, the first distance, and the second distance. The second obstacle information includes the obstacle distance and the second obstacle type. The second obstacle type includes the first type and the second type. The distance between the obstacle in the second type and the rail robot is less than the distance between the obstacle in the first type and the rail robot.

[0016] The determination module is further configured to determine the credible type of each obstacle according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor.

[0017] A control module, configured to control the operation of the rail robot according to the credible type of each obstacle.

[0018] In a third aspect, an embodiment of the present application provides an orbital robot, which is characterized by comprising: a TOF sensor, an ultrasonic sensor, a memory, and a processor;

[0019] The memory stores computer-executable instructions;

[0020] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the implementation manners of the first aspect as described above.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which is characterized in that computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement the implementation manners of the first aspect as described above.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the implementation manners of the first aspect as described above.

[0023] The obstacle avoidance method, device, orbital robot, and storage medium provided by the embodiments of the present application determine the first obstacle information detected by the TOF sensor and the second obstacle information detected by the ultrasonic sensor according to the TOF data and the ultrasonic data at the same moment. Then, according to the first obstacle information and the second obstacle information, it is determined whether the obstacles in the overlapping detection area of the TOF sensor and the ultrasonic sensor are detected by both sensors at the same time, so as to determine the credible type of the obstacles. At the same time, according to the dual-threshold strategy, the urgency of the obstacles detected by the ultrasonic sensor is determined. For the second type of obstacles with a higher urgency level, the detection process of sensor misdetection is not performed on them, and they are directly determined as credible obstacles, which can ensure that the orbital robot has a reaction time to perform a braking process, thereby avoiding the collision between the orbital robot and the obstacles and improving the control accuracy of the orbital robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present application, and are used together with the description to explain the principles of the present application.

[0025] Figure 1 Schematic structure of the orbital robot provided by the present application Figure 1 ;

[0026] Figure 2 Flow schematic of the obstacle avoidance method of the orbital robot provided by the present application Figure 1 ;

[0027] Figure 3Schematic diagram of projection components in the right - hand coordinate system provided by this application;

[0028] Figure 4 Flow schematic of the obstacle - avoidance method for the track robot provided by this application Figure 2 ;

[0029] Figure 5 Flow schematic of the obstacle - avoidance method for the track robot provided by this application Figure 3 ;

[0030] Figure 6 Flow schematic of the obstacle - avoidance method for the track robot provided by this application Figure 4 ;

[0031] Figure 7 Flow schematic of the obstacle - avoidance method for the track robot provided by this application Figure 5 ;

[0032] Figure 8 Flow schematic of the obstacle - avoidance method for the track robot provided by this application Figure 6 ;

[0033] Figure 9 Flow schematic of the obstacle - avoidance method for the track robot provided by this application Figure 7 ;

[0034] Figure 10 Flow schematic of the obstacle - avoidance method for the track robot provided by this application Figure 8 ;

[0035] Figure 11 Structure schematic diagram of the obstacle - avoidance device for the track robot provided by this application;

[0036] Figure 12 Structure schematic of the track robot provided by this application Figure 2 。

[0037] Through the above - mentioned drawings, specific embodiments of this application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0038] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with this application. On the contrary, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0039] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0040] First, the nouns involved in this application are explained as follows:

[0041] TOF sensor: By emitting an infrared light signal to the target object and measuring the time difference between the emission and return of the infrared light signal, the target distance between the TOF sensor and the target object is calculated, and three-dimensional dot matrix depth data is generated.

[0042] Ultrasonic sensor: Utilizing the reflection characteristics of ultrasonic waves, the time difference between the emission and reception of ultrasonic waves is measured to calculate the target distance between the ultrasonic sensor and the target object. The detection field of view angle is approximately conical, and it can only return a single distance information without providing azimuth information.

[0043] Sensor misdetection: The sensor misidentifies the target object, resulting in inaccurate data or system misjudgment, usually caused by environmental interference or sensor failure.

[0044] Rail robot: An intelligent robot that can operate along a specific track. It combines robot technology, automatic control technology, and a track system, and is usually designed to perform specific tasks, such as material transportation, equipment inspection, environmental monitoring, etc. in many fields of industrial production.

[0045] Next, the scenarios involved in this application are explained as follows:

[0046] The movement of the robot depends on the real-time detection of the surrounding environment by the sensor, and then the subsequent movement mode is determined according to the detection result. Especially for rail robots, due to the fixed movement path and relatively fast speed, they must be able to accurately and quickly determine whether there are obstacles ahead based on the detection result, and then make a choice among three movement states: stop, decelerate, and maintain the current speed. This requires the sensor to have high precision and fast response capabilities.

[0047] In practical applications, sensors are installed in front of the rail robot to detect in advance whether there are obstacles near the front track. At the same time, sensors can also be installed behind the rail robot so that when the rail robot needs to reverse or other equipment approaches the rail robot from behind, it can detect the situation behind in a timely manner to prevent rear-end collisions.

[0048] Among them, the commonly used sensors of the rail robot include ultrasonic sensors and TOF sensors. Although the TOF sensor has a simple structure, low cost, and sensitive response, it has certain requirements for ambient light, cannot detect the distance of approximate blackbody or transparent objects, and is affected by the environment during use, resulting in "ghost" false alarms. The ultrasonic sensor has strong air penetration, is not easily affected by particles such as dust, is insensitive to light and color, can identify transparent and dark objects, is not easily interfered by the environmental electromagnetic field, but is interfered by high-frequency noise and self-generated ultrasound, can only measure distance without azimuth information, and due to the existence of the diffusion angle of ultrasonic waves, false alarms are likely to occur outside the theoretical field of view.

[0049] Figure 1 Structural schematic of the rail robot provided by this application Figure 1 , such as Figure 1 shown, the rail robot includes two ultrasonic sensors and two TOF sensors. Among them, one ultrasonic sensor and one TOF sensor are arranged in front of the rail robot, and the other ultrasonic sensor and the other TOF sensor are arranged behind the rail robot.

[0050] It should be understood that the front refers to the direction in which the rail robot runs, and the rear is the direction in which the rail robot retreats.

[0051] It should be understood that the embodiments of this application do not limit the number of sensors. That is to say, the rail robot can include one ultrasonic sensor and one TOF sensor, and can also include multiple ultrasonic sensors and multiple TOF sensors.

[0052] In practical applications, other types of sensors can also be set in the rail robot, such as laser sensors, vision sensors, etc., and the embodiments of this application do not specifically limit this.

[0053] Therefore, during the process of the rail robot using sensors for environmental detection, sensor misdetection is inevitable. Moreover, in the scenario of simultaneous use of multiple sensors, the misdetection problems of different sensors will be superimposed, further increasing the risk of misdetection. Once misdetection occurs, the rail robot may take unnecessary braking or deceleration measures, which not only affects the motion stability of the rail robot, but also reduces the inspection efficiency. Therefore, reducing the sensor misdetection rate is an urgent problem to be solved.

[0054] Currently, in the scenario of simultaneous use of multiple sensors, mainly by combining the ranging information of TOF data and ultrasonic data, an obstacle fusion point cloud is generated in real time to identify obstacles, thereby reducing sensor misdetection.

[0055] However, the existing technology is mainly used in scenarios containing transparent objects, specular reflections, and dark objects. The TOF sensor cannot detect the distance of approximate blackbodies or transparent objects, but the ultrasonic sensor can identify transparent and dark objects. By combining the ranging information of TOF data and ultrasonic data, the sensor misdetection can be reduced. However, there are still many other scenarios where sensor misdetection problems occur, such as sensor failures themselves. In these scenarios, the existing technology cannot solve the sensor misdetection problem, resulting in a relatively high sensor misdetection rate, and further leading to a low accuracy in controlling the rail robot based on the wrong detection results.

[0056] Based on the above technical problems, the inventive concept of this application is as follows: Considering that there is an overlapping detection area between the TOF sensor and the ultrasonic sensor. Therefore, it is possible to determine whether there are misdetection problems with the TOF sensor and the ultrasonic sensor by judging whether the obstacles existing in the overlapping detection area are detected by both sensors at the same time, and then accurately control the rail robot according to the detection results. At the same time, considering that the closer the obstacle is to the rail robot, the more accurate the sensor detection is. Therefore, when the ultrasonic sensor detects an obstacle at a position relatively close to the rail robot, it is used as a credible non-misdetection obstacle to control the rail robot, thereby avoiding the risk of the rail robot colliding with the obstacle and further improving the accuracy of controlling the rail robot.

[0057] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. These several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0058] Figure 2 Flow schematic of the obstacle avoidance method for the rail robot provided by this application Figure 1 , as Figure 2 shown, the obstacle avoidance method for the rail robot can be implemented through the following steps:

[0059] S21. Determine the first obstacle information according to the preset safe obstacle avoidance area of the rail robot and the TOF data.

[0060] The execution subject of the embodiment of this application is a rail robot, which is equipped with a TOF sensor and an ultrasonic sensor. Its structure can refer to the embodiment shown in Figure 1 , which will not be elaborated here. Among them, the TOF sensor and the ultrasonic sensor are on the same side. That is to say, the TOF sensor and the ultrasonic sensor can be both on the front side of the rail robot at the same time, or both on the rear side of the rail robot at the same time.

[0061] Among them, the preset safety obstacle avoidance area is a pre-set area, and objects within this area pose a risk of colliding with the rail robot.

[0062] Among them, the TOF data can be the original depth map at a certain moment collected by the TOF sensor, or it can be the depth map at a certain moment obtained after aligning the original depth map collected by the TOF sensor and the original ultrasonic data collected by the sensor in time. That is, the TOF data can be the original depth map directly collected by the TOF sensor, or it can be the depth map obtained by post-processing the original depth map, which can be determined according to the actual situation, and the embodiments of the present application do not specifically limit this.

[0063] Among them, the TOF data includes the distance and direction between an object within the acquisition range of the TOF sensor at a certain moment and the TOF sensor.

[0064] Among them, the first obstacle information includes the obstacle position and the first obstacle type, and the first obstacle type includes the first type. It should be understood that the obstacle position can be determined according to the distance and direction between the object and the TOF sensor in the TOF data.

[0065] Since the TOF data is the straight-line distance between the object and the TOF sensor, and the TOF data is a depth map of size N×N, according to the installation position of the TOF sensor and the positions of each pixel in the depth map, the projection values of each object in the three spatial directions can be calculated with the geometric center of the TOF sensor as the origin in the right-handed coordinate system.

[0066] In a possible implementation, the origin can be set as the sensor, and in the right-handed coordinate system, the connection line between each detection point (the object within the acquisition range of the TOF sensor) and the origin can be determined. According to the installation position of the TOF sensor when it is installed correctly and the prior knowledge of the TOF pixel information, the angles between this connection line and the X-axis, Y-axis, and Z-axis can be determined. Then, according to the length of this connection line and the angles between this connection line and the X-axis, Y-axis, and Z-axis, the components of this connection line on the X-axis, Y-axis, and Z-axis can be determined. Finally, according to the preset safety obstacle avoidance area and the installation position of the TOF sensor, the spatial obstacle avoidance thresholds of the preset safety obstacle avoidance area on the X-axis, Y-axis, and Z-axis can be calculated. If the components of this connection line on the X-axis, Y-axis, and Z-axis are all less than the corresponding spatial obstacle avoidance thresholds, then it is determined that this object is an obstacle, and the first obstacle type is the first type. If any one of the components of this connection line on the X-axis, Y-axis, and Z-axis is not less than the corresponding spatial obstacle avoidance threshold, then it is determined that this object is a non-obstacle.

[0067] Among them, the X-axis direction is the forward direction of the rail robot, the Z-axis direction is the direction perpendicular to the ground and upward, and the Y-axis direction is the direction perpendicular to both the X-axis and the Z-axis at the same time.

[0068] Figure 3 Schematic diagram of projection components in the right - hand coordinate system provided for this application. As Figure 3 shown, is the detection point, the angle with the X - axis is , the angle with the Z - axis is , the angle with the Y - axis is , the length of the line connecting it to the origin is d.

[0069] The relationship between the line connecting to the origin and its components on the X - axis, Y - axis, and Z - axis can be achieved through the following formula:

[0070]

[0071] Among them, is the length of the line connecting to the origin, is the component of the line on the X - axis, is the component of the line on the Y - axis, is the component of the line on the Z - axis.

[0072] The projected length of this line on the XY - plane can be achieved through the following formula:

[0073]

[0074] Among them, is the projected length of this line on the XY - plane.

[0075] The projected length of this line on the XZ - plane can be achieved through the following formula:

[0076]

[0077] Among them, is the projected length of this line on the XZ - plane.

[0078] The projected length of this line on the YZ - plane can be achieved through the following formula:

[0079]

[0080] Among them, is the projected length of this line on the YZ - plane.

[0081] The relationship between the angles with each coordinate axis and the components of the line on each coordinate axis can be achieved through the following formula:

[0082]

[0083]

[0084]

[0085] According to the above formula, the following equivalent relationships exist for the components of the connection line on each coordinate axis:

[0086]

[0087] Furthermore, according to the above formula, 、 、 can be expressed by the following formula:

[0088]

[0089]

[0090]

[0091] S22. Determine the minimum value between the braking distance of the rail robot and the preset detection distance as the first distance, and determine the maximum value between the deceleration-stop distance of the rail robot and the preset distance as the second distance.

[0092] Among them, the braking distance is the distance traveled by the rail robot when it steps on the brake and decelerates to a stop. The preset detection distance is the minimum ultrasonic detection distance that can cover the rail robot body set in advance. The deceleration-stop distance is the distance traveled by the rail robot when it decelerates to a stop with a preset acceleration. The preset distance is the minimum distance between the rail robot and a fixed obstacle set in advance. In practical applications, the preset distance can be the closest required distance from the rail robot to a fixed obstacle such as a wall in the installation specification of the rail robot.

[0093] It should be understood that in practical applications, the braking distance should be less than or equal to the deceleration-stop distance. Therefore, the first distance should be less than or equal to the second distance.

[0094] S23. Determine the second obstacle information according to the ultrasonic data, the first distance, and the second distance.

[0095] Among them, similar to the TOF data, it can be the original ultrasonic wave at a certain moment collected by the ultrasonic sensor, or the ultrasonic data at a certain moment obtained after aligning the original depth map collected by the TOF sensor and the original ultrasonic data collected by the sensor in terms of time. That is, the ultrasonic data can be the original ultrasonic data directly collected by the ultrasonic sensor, or the ultrasonic data obtained by post-processing the original ultrasonic data, which can be determined according to the actual situation, and the embodiments of the present application do not specifically limit this.

[0096] It should be understood that the ultrasonic data in this step and the TOF data in S21 are data at the same moment.

[0097] Among them, the second obstacle information includes the obstacle distance and the second obstacle type. The obstacle distance refers to the straight-line distance between the obstacle and the ultrasonic sensor, which can be determined according to the ultrasonic data. The second obstacle type includes the first type and the second type. The distance between the obstacle of the second type and the rail robot is less than the distance between the obstacle of the first type and the rail robot.

[0098] In a possible implementation manner, if the ultrasonic data indicates that the object distance is less than or equal to the first distance, then the second obstacle type is determined to be the second type. If the object distance is greater than the first distance and less than the second distance, then the second obstacle type is determined to be the first type. According to the object distance and the second obstacle type, the second obstacle information is determined.

[0099] In practical applications, it can first be determined whether the object distance indicated by the ultrasonic data is greater than or equal to the second distance. If it is greater than the second distance, then the object corresponding to the object distance is determined to be a non-obstacle; if the object distance is less than the second distance, then the object corresponding to the object distance is determined to be an obstacle, and the object distance is compared with the first distance and the second distance again to determine the second obstacle type of the obstacle.

[0100] In this implementation, a dual-threshold strategy (the first distance and the second distance) is used to determine the type of the second obstacle. Since the first distance is the minimum of the stopping distance of the rail robot and the preset detection distance, if the distance to the obstacle is less than the first distance, it means that the distance between the obstacle and the rail robot is very close at this time, and braking is required to avoid the rail robot colliding with the obstacle. Therefore, the type of the second obstacle is determined as the second type. And the first distance is the maximum of the decelerating and stopping distance of the rail robot and the preset distance. If the distance to the obstacle is less than the first distance and greater than the second distance, it means that the obstacle is within the range affecting the travel of the rail robot, but the rail robot can avoid colliding with the obstacle by decelerating and stopping, etc. Therefore, the type of the second obstacle is determined as the first type. The dual-threshold strategy is used to determine the urgency of the obstacle, so as to accurately control the rail robot according to the urgency of the obstacle subsequently.

[0101] S24. Determine the credible type of each obstacle according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor.

[0102] In a possible implementation, S24 can be implemented through the following steps A1 - A5:

[0103] A1. Determine the overlapping detection area of the TOF sensor and the ultrasonic sensor according to the first field of view angle and the second field of view angle.

[0104] In A1, the installation position of the TOF sensor can be used as the origin, and according to the first field of view angle of the TOF sensor in the right-handed coordinate system, the detection area of the TOF sensor is fitted. At the same time, the installation position of the ultrasonic sensor is used as the origin, and according to the second field of view angle of the ultrasonic sensor in the right-handed coordinate system, the detection area of the ultrasonic sensor is fitted.

[0105] After determining the detection area of the TOF sensor and the detection area of the ultrasonic sensor, the overlapping detection area of the two can be determined as the overlapping detection area of the TOF sensor and the ultrasonic sensor.

[0106] A2. If the obstacle of the first type is not within the overlapping detection area, determine the credible type of the obstacle as credible.

[0107] A3. If the obstacle of the first type is within the overlapping detection area, and the obstacle position corresponding to the obstacle in the first obstacle information matches the obstacle distance corresponding to the obstacle in the second obstacle information, determine that the credible type of the obstacle is credible.

[0108] In practical applications, since an ultrasonic sensor can only detect the distance between itself and an object and cannot know the direction of the object. Therefore, when the first type of obstacle is detected by the ultrasonic sensor, it is necessary to determine whether the position points corresponding to the obstacle distance of the obstacle from the TOF sensor are all within the overlapping detection area. If so, it is determined that the first type of obstacle is within the overlapping detection area; if any position point is not within the overlapping detection area, it is determined that the obstacle is not within the overlapping detection area.

[0109] When the first type of obstacle is detected by the TOF sensor, it can be directly determined whether the obstacle is within the overlapping detection area based on the obstacle position corresponding to the obstacle.

[0110] Among them, determining whether the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information match can be achieved through the following process: According to the obstacle distance in the second obstacle information, determine multiple position points where the distance between the obstacle and the ultrasonic sensor is the obstacle distance. Then, determine whether any position point is the same as the obstacle position in the second obstacle information. If so, it is determined that the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information match, indicating that the obstacle is detected by both sensors; if all position points are not the same as the obstacle position in the second obstacle information, it is determined that the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information do not match.

[0111] Exemplarily, assume that the distance between the first type of obstacle and the ultrasonic sensor is 20 cm, then determine whether the position points at a distance of 20 cm from the ultrasonic sensor are all within the overlapping detection area. If all position points at a distance of 20 cm from the ultrasonic sensor are within the overlapping detection area, it is determined that the obstacle is within the overlapping detection area; if any position point at a distance of 20 cm from the ultrasonic sensor is not within the overlapping detection area, it is determined that the first type of obstacle is not within the overlapping detection area.

[0112] Furthermore, after determining that the first type of obstacle is within the overlapping detection area, then determine whether any of the above position points is the same as the obstacle position in the second obstacle information, and further determine whether the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information match.

[0113] A4. If the obstacle of the first type is within the overlapping detection area, and the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information do not match, the credible type of the obstacle is determined to be untrustworthy.

[0114] A5. Determine the credibility type of the second type of obstacle as credible.

[0115] In this implementation, when an obstacle is in the overlap detection area, the obstacle should be detected by two sensors at the same time in theory. Therefore, when it is determined that the first type of obstacle is in the overlap detection area, it can be determined whether the obstacle is detected by two sensors by judging whether the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information match. If it is determined that the obstacle is detected by two sensors at the same time, it means that the obstacle is credible and there is no sensor misdetection; if it is determined that the obstacle is not detected by two sensors at the same time, it means that the obstacle is uncredible, and there is a problem in one of the sensors that causes the obstacle to be not detected or to be detected incorrectly. At the same time, since the credible type of the obstacle is determined in real time, and since the urgency of the second type of obstacle is high, in order to avoid the real obstacle being mistakenly determined as an uncredible obstacle at a certain moment due to some unexpected circumstances, even if the wrong conclusion of the previous moment is corrected at the next moment, the real obstacle is mistakenly determined as a credible obstacle, which may cause the track robot to have no time to stop and the two to collide. For this reason, the second type of obstacles are directly determined as credible obstacles to avoid the problem of collision between the rail robot and the obstacles, thereby further improving the control accuracy of the rail robot.

[0116] S25. Control the track robot to run according to the trustworthy type of each obstacle.

[0117] It should be understood that this step can be implemented by Figure 4 The embodiments shown are explained and will not be described in detail here.

[0118] The obstacle avoidance method for the rail robot provided by the embodiment of the present application. The rail robot determines the first obstacle information according to the preset safe obstacle avoidance area of the rail robot and the TOF data. Then, the minimum value between the braking distance of the rail robot and the preset detection distance is determined as the first distance, and the maximum value between the decelerating and stopping distance of the rail robot and the preset distance is determined as the second distance. Next, according to the ultrasonic data, the first distance, and the second distance, the second obstacle information is determined. Finally, according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor, the credible type of each obstacle is determined, and the operation of the rail robot is controlled according to the credible type of each obstacle. Among them, the first obstacle information includes the obstacle position and the first obstacle type, and the first obstacle type includes the first type. The decelerating and stopping distance is the distance traveled by the rail robot when decelerating to a stop at a preset acceleration, and the preset distance is the minimum distance between the preset rail robot and the fixed obstacle. The second obstacle information includes the obstacle distance and the second obstacle type, and the second obstacle type includes the first type and the second type. The distance between the obstacle of the second type and the rail robot is less than the distance between the obstacle of the first type and the rail robot.

[0119] In this technical solution, sensor misdetection can be detected in multiple scenarios. According to the TOF data and ultrasonic data at the same moment, the first obstacle information detected by the TOF sensor and the second obstacle information detected by the ultrasonic sensor are determined. Then, according to the first obstacle information and the second obstacle information, it is determined whether the obstacles in the overlapping detection area of the TOF sensor and the ultrasonic sensor are detected by both sensors at the same time, so as to determine the credible type of the obstacles. At the same time, according to the dual-threshold strategy, the urgency of the obstacles detected by the ultrasonic sensor is determined. For the second type of obstacles with a higher urgency, the sensor misdetection detection process is not performed on them, and they are directly determined as credible obstacles, which can ensure that the rail robot has a reaction time for braking processing, thereby avoiding the collision between the rail robot and the obstacles and improving the control accuracy of the rail robot.

[0120] Next, through Figure 4 the implementation process of S25 will be explained.

[0121] Figure 4 is the flow schematic of the obstacle avoidance method for the rail robot provided by the present application Figure 2 As Figure 4 shown, S25 can be implemented through the following steps:

[0122] S41. Determine the most credible obstacle closest to the rail robot and the least credible obstacle closest to the rail robot according to the credible type of each obstacle.

[0123] Among them, the distance between the obstacle and the rail robot can be the straight-line distance between the obstacle and the rail robot, or the X-direction projection distance of the straight-line distance between the obstacle and the rail robot (only for TOF sensors).

[0124] S42. Determine the first speed when the rail robot runs in front of the most credible obstacle and the second speed when it runs in front of the least credible obstacle.

[0125] Among them, the first speed and the second speed can be determined by the following formula:

[0126]

[0127]

[0128] Among them, is the first speed, is the second speed, is the current deceleration ratio, is the current speed, is the distance between the most credible obstacle (the most credible obstacle closest to the rail robot) and the rail robot, is the distance between the least credible obstacle (the least credible obstacle closest to the rail robot) and the rail robot.

[0129] S43. Determine the target speed of the rail robot according to the preset speed, the first speed, and the second speed.

[0130] Among them, the braking distance corresponding to the preset speed approaches 0.

[0131] In one implementation, if the first speed is less than or equal to the second speed, the first speed is determined as the target speed; if the first speed is less than or equal to the preset speed, the first speed is determined as the target speed; if the first speed is greater than the second speed, and the second speed is greater than the preset speed, the second speed is determined as the target speed; if the first speed is greater than the second speed, and the second speed is equal to the preset speed, the second speed is determined as the target speed; if the preset speed is greater than the second speed, and the preset speed is less than the first speed, the preset speed is determined as the target speed.

[0132] In this implementation, when the first speed is less than or equal to the second speed, it indicates that at this time the trusted obstacle is closer to the rail robot than the untrusted obstacle, and the untrusted obstacle does not affect the movement of the rail robot. At this time, it is necessary to determine the first speed as the target speed and control the rail robot to move forward with the target speed as the goal to ensure that the rail robot can stop in front of the trusted obstacle. When the first speed is less than or equal to the preset speed, it indicates that the first speed is a very small value at this time. Therefore, it is necessary to determine the first speed as the target speed. When the first speed is greater than the second speed and the second speed is greater than the preset speed, and when the first speed is greater than the second speed and the second speed is equal to the preset speed, it indicates that at this time the untrusted obstacle is closer to the rail robot than the trusted obstacle. To prevent the trusted obstacle from being incorrectly determined as an untrusted obstacle before, the untrusted obstacle can be temporarily trusted, and the second speed corresponding to the untrusted obstacle is determined as the target speed, and the trusted type of the untrusted obstacle is updated in real time during the forward movement. If the trusted type corresponding to the untrusted obstacle determined before is accurate, when the rail robot travels to a very close distance to both the untrusted obstacle and the trusted obstacle and the first speed is less than the preset speed, the rail robot will be controlled according to the first speed corresponding to the trusted obstacle. If the trusted type corresponding to the untrusted obstacle determined before is inaccurate, that is, the untrusted obstacle is actually a trusted obstacle, then since the rail robot is currently controlled according to the second speed corresponding to the obstacle, it can also ensure that the rail robot stops in front of the obstacle.

[0133] S44. Control the rail robot to run at the target speed.

[0134] In this implementation, considering that there may be unexpected situations that cause the determined trusted type of the obstacle to be incorrect, and the detection ability and accuracy of the sensor will increase when the rail robot approaches the obstacle, the determined trusted type of the obstacle may be updated. Through the speed control strategy updated in real time, the influence caused by the incorrect judgment of the obstacle type and the trusted type of the obstacle in the early stage is suppressed. By comparing the preset speed, the first speed, and the second speed, the target speed of the rail robot is determined, ensuring that the vehicle can stop in front of the obstacle in time, avoiding collision with the obstacle, and further improving the control accuracy of the rail robot.

[0135] It should be understood that in practical applications, according to the TOF data and ultrasonic data at a certain moment, the type of obstacle and the credible type of the obstacle corresponding to that moment are determined, and then the target speed is determined, and the track robot is controlled to travel at the target speed. After that, at the next moment, according to the TOF data and ultrasonic data at that moment, the type of obstacle and the credible type of the obstacle corresponding to that moment are updated, and then the target speed is updated, and the track robot is controlled to travel at the updated target speed. At the same time, the track robot will dynamically determine the target speed in real time until a dynamic balance is formed between the target speed and the actual speed.

[0136] Through the above technical solution, a linkage mechanism is formed between sensor misdetection and speed control, which can not only ensure that the speed of the track robot is not affected by long-distance misdetection, but also ensure that it stops in time when a close-range obstacle is detected. Especially when the obstacle approaches and the type of obstacle changes, the impact on the speed of the track robot is also small, thus effectively enhancing the stability and safety of the robot's movement and reducing the missed detection rate of non-obstacles.

[0137] In practical applications, the TOF sensor and ultrasonic data usually cannot be collected at the same time. Therefore, before S21, the first TOF data collected by the TOF sensor and the first ultrasonic data collected by the ultrasonic sensor can also be aligned in time according to the running speed of the track robot to obtain the TOF data and ultrasonic data.

[0138] It should be understood that the first TOF data is Figure 2 the original depth map in the illustrated embodiment, and the first ultrasonic data is the original ultrasonic data.

[0139] In this implementation manner, by aligning the first TOF data and the first ultrasonic data in time, it is possible to ensure that the relevant information of the obstacle is determined in the same time dimension, laying a foundation for subsequently determining the accurate control of the operation of the track robot.

[0140] Among them, according to the running speed of the track robot, aligning the first TOF data collected by the TOF sensor and the first ultrasonic data collected by the ultrasonic sensor in time to obtain the TOF data and ultrasonic data can be explained by Figure 5 the illustrated embodiment.

[0141] Figure 5 This is the flowchart of the obstacle avoidance method for the track robot provided by this application Figure 3 As Figure 5As shown in the figure, according to the running speed of the rail robot, the first TOF data collected by the TOF sensor and the first ultrasonic data collected by the ultrasonic sensor are aligned in time to obtain TOF data and ultrasonic data. This can be achieved through the following steps:

[0142] S51. According to the running speed of the rail robot, align the first TOF data collected by the TOF sensor and the first ultrasonic data collected by the ultrasonic sensor in time to obtain the second TOF data and the second ultrasonic data.

[0143] In a possible implementation, taking a certain sensor (sensor A) as a reference, according to the running speed of the rail robot, determine the sensor data collected by this sensor at each moment, and determine the theoretical position A of the rail robot corresponding to this moment. Then, according to the acquisition time interval between another sensor (sensor B) and sensor A, based on this acquisition time interval and the running speed of the rail robot, determine the moving distance within this acquisition time interval. Then, based on this moving distance, reverse-infer the sensing data collected by sensor B, and thus obtain the sensor data corresponding to sensor B when the rail robot is at the theoretical position A.

[0144] S52. Perform time-domain smoothing and noise elimination processing on the second TOF data and the second ultrasonic data to generate TOF data and ultrasonic data.

[0145] Among them, time-domain smoothing is to smooth continuous multi-frame data, eliminate accidental misdetections, and retain short-term determined obstacles; noise elimination is filtering based on the spatial domain and the time domain to eliminate noise in the sensor data.

[0146] S53. If it is determined that any one of the TOF sensor and the ultrasonic sensor has a fault according to the anomaly mark and / or preset conditions, then increase the detection range of the other sensor.

[0147] Among them, the anomaly mark is a mark generated by the sensor when it determines that it has a fault, and the preset condition is the state when the sensor has a fault determined according to prior knowledge. When it is determined that any one of the TOF sensor and the ultrasonic sensor has a fault according to the anomaly mark and / or preset conditions, by increasing the detection range of the other sensor, it is ensured that there is no blind area for the positions that the rail robot needs to detect, and the safety of the movement process is guaranteed.

[0148] In the above technical solution, by performing time-domain smoothing and noise elimination on the originally collected sensor data, incorrect information is removed, laying a foundation for the accurate control of the rail robot in the subsequent process.

[0149] To more clearly explain this application, the following will use specific examples to illustrate it.

[0150] Figure 6 Schematic flow of the obstacle avoidance method for the track robot provided by this application Figure 4 As Figure 6 shown, the obstacle avoidance method for the track robot includes the following steps:

[0151] S61. Obtain the first TOF data of the TOF sensor and the first ultrasonic data of the ultrasonic sensor.

[0152] S62. Preprocess the first TOF data and the first ultrasonic data respectively to generate TOF data and ultrasonic data at the same moment.

[0153] It should be understood that the implementation method and principle of this step can refer to the Figure 5 illustrated embodiment, which will not be elaborated here.

[0154] S63. Perform polygon fitting on the detection areas of the TOF sensor and the ultrasonic sensor.

[0155] The installation position of the TOF sensor can be used as the origin, and according to the first field of view angle of the TOF sensor in the right-handed coordinate system, the detection area of the TOF sensor can be polygonally fitted. At the same time, the installation position of the ultrasonic sensor is used as the origin, and according to the second field of view angle of the ultrasonic sensor in the right-handed coordinate system, the detection area of the ultrasonic sensor is polygonally fitted.

[0156] S64. Determine the first obstacle information according to the TOF data, and determine the second obstacle information according to the ultrasonic data.

[0157] S65. Multisensor data fusion.

[0158] S66. Control the track robot to run with the target speed as the goal.

[0159] Furthermore, Figure 7 Schematic flow of the obstacle avoidance method for the track robot provided by this application Figure 5 As Figure 7 shown, the determination of the first obstacle information according to the TOF data in S64 can be achieved through the following steps:

[0160] S71. Determine the installation position of the TOF sensor and the preset safe obstacle avoidance area.

[0161] S72. Calculate the spatial obstacle avoidance thresholds on the X-axis, Y-axis, and Z-axis of the preset safe obstacle avoidance area in the right-handed coordinate system.

[0162] S73. Determine the depth map corresponding to the TOF sensor.

[0163] S74. Determine the projection components of the object on the X-axis, Y-axis, and Z-axis of the right-handed coordinate system pixel by pixel.

[0164] S75. Determine whether the projection component of each axis is less than the corresponding spatial obstacle avoidance threshold.

[0165] If not, that is, if the projection component of any axis is greater than the corresponding spatial obstacle avoidance threshold, then execute S76. If the projection component of each axis is less than the corresponding spatial obstacle avoidance threshold, then execute S77;

[0166] S76. Determine the object as a non-obstacle.

[0167] S77. Determine the object as an obstacle and determine the obstacle type as initial obstacle 1.

[0168] It should be understood that initial obstacle 1 is the first type.

[0169] Further, Figure 8 is the flow schematic of the obstacle avoidance method for the rail robot provided by this application Figure 6 . As Figure 8 shown, determining the second obstacle information according to the ultrasonic data in S64 can be achieved through the following steps:

[0170] S81. Determine the installation position of the ultrasonic sensor, the preset detection distance, and the preset distance.

[0171] S82. Calculate threshold 1 and threshold 2.

[0172] It should be understood that threshold 1 is the first distance and threshold 2 is the second distance.

[0173] S83. Whether the object distance is greater than threshold 1.

[0174] If so, then execute S84. If not, then determine the object as an obstacle and determine the obstacle type as initial obstacle 2.

[0175] It should be understood that initial obstacle 2 is the second type.

[0176] S84. Whether the object distance is greater than threshold 2.

[0177] If so, then determine the object as a non-obstacle; if not, then determine the object as an obstacle and determine the obstacle type as initial obstacle 1.

[0178] Figure 9 is the flow schematic of the obstacle avoidance method for the rail robot provided by this application Figure 7 . As Figure 9 shown, S65 can be achieved through the following steps:

[0179] S91. Obtain the obstacle type.

[0180] S92. Determine whether the obstacle type is the initial obstacle 1.

[0181] If not, determine the obstacle type as the initial obstacle 2 and determine the obstacle as the obstacle type 1; if so, execute S93.

[0182] S93. Determine the overlapping detection area of the TOF sensor and the ultrasonic sensor.

[0183] S94. Determine whether the obstacle is in the overlapping detection area.

[0184] If so, execute S95; if not, determine the obstacle as the obstacle type 1.

[0185] S95. Determine whether the obstacle is detected by other sensors.

[0186] If so, determine the obstacle as the obstacle type 2; if not, determine the obstacle as the obstacle type 3.

[0187] It should be understood that the obstacle type 1 means that the obstacle is in the blind area of other detectors or is very close to the device, and an emergency brake needs to be triggered. Such obstacles are regarded as trustworthy obstacles. The obstacle type 2 is an obstacle detected by two detectors at the same time and can also be regarded as a trustworthy obstacle. The obstacle type 3 means that the obstacle is in the overlapping detection area, but the corresponding other sensors in the overlapping detection area do not detect the obstacle, and the obstacle is considered an untrustworthy obstacle.

[0188] Among them, the obstacles corresponding to the obstacle type 2 and the obstacle type 1 are trustworthy obstacles, and the obstacles corresponding to the obstacle type 3 are untrustworthy obstacles.

[0189] Figure 10 This is the flowchart of the obstacle avoidance method for the rail robot provided by this application Figure 8 . As Figure 10 shown, S66 can be implemented through the following steps:

[0190] S101. Determine , , .

[0191] Among them, is the preset speed.

[0192] S102. Determine whether it satisfies .

[0193] If so, determine as the target speed; if not, execute S103.

[0194] S103. Determine whether the following conditions are met .

[0195] If yes, then set as the target speed. If no, then execute S104.

[0196] S104. Determine whether the following conditions are met .

[0197] If yes, then set as the target speed. If no, then set as the target speed.

[0198] After that, control the rail robot to run with the target speed as the goal.

[0199] In summary, the technical solution provided by this application realizes real-time multi-sensor joint obstacle avoidance misdetection elimination and motion control through data fusion of multiple sensors, without complex steps such as map construction and target trajectory calculation, ensuring the stability and safety of the rail robot during movement. At the same time, a dual-threshold obstacle avoidance strategy for ultrasonic waves is proposed, which combines the preset detection distance, the robot speed, and the environment, making full use of the detection characteristics of the ultrasonic sensor. On the basis of ensuring safety, it effectively reduces the misdetection caused by ultrasonic waves and enhances the stability of the rail robot's movement.

[0200] The following is an embodiment of the device of this application, which can be used to execute the embodiment of the method of this application. For details not disclosed in the embodiment of the device of this application, please refer to the embodiment of the method of this application.

[0201] Figure 11 is a schematic structural diagram of the obstacle avoidance device of the rail robot provided by this application. As Figure 11 shown, the obstacle avoidance device 110 of the rail robot provided in this embodiment includes:

[0202] A determination module 111, configured to determine first obstacle information according to the preset safe obstacle avoidance area of the rail robot and TOF data. The first obstacle information includes the obstacle position and the first obstacle type, and the first obstacle type includes the first type;

[0203] The determination module 111 is further configured to determine the minimum value between the braking distance of the rail robot and the preset detection distance as the first distance, and determine the maximum value between the deceleration stop distance of the rail robot and the preset distance as the second distance. The deceleration stop distance is the distance traveled by the rail robot when decelerating to a stop at a preset acceleration, and the preset distance is the minimum distance between the rail robot and a fixed obstacle set in advance;

[0204] The determination module 111 is further configured to determine second obstacle information according to the ultrasonic data, the first distance, and the second distance. The second obstacle information includes an obstacle distance and a second obstacle type. The second obstacle type includes a first type and a second type. The distance between an obstacle of the second type and the rail robot is less than the distance between an obstacle of the first type and the rail robot.

[0205] The determination module 111 is further configured to determine a credible type of each obstacle according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor.

[0206] The control module 112 is configured to control the operation of the rail robot according to the credible type of each obstacle.

[0207] In a possible implementation manner, the determination module 111 is specifically configured to:

[0208] If the object distance indicated by the ultrasonic data is less than or equal to the first distance, determine that the second obstacle type is the second type;

[0209] If the object distance is greater than the first distance and less than the second distance, determine that the second obstacle type is the first type;

[0210] Determine the second obstacle information according to the object distance and the second obstacle type.

[0211] In a possible implementation manner, the control module 112 is specifically configured to:

[0212] Determine the closest credible obstacle to the rail robot and the closest non-credible obstacle to the rail robot according to the credible type of each obstacle;

[0213] Determine a first speed when the rail robot runs in front of the credible obstacle and a second speed when the rail robot runs in front of the non-credible obstacle;

[0214] Determine the target speed of the rail robot according to the preset speed, the first speed, and the second speed. The braking distance corresponding to the preset speed approaches 0;

[0215] Control the rail robot to run at the target speed.

[0216] In a possible implementation manner, the determination module 111 is specifically configured to:

[0217] Determine the overlapping detection area of the TOF sensor and the ultrasonic sensor according to the first field of view angle and the second field of view angle;

[0218] If the obstacle of the first type is not within the overlapping detection area, determine the reliable type of the obstacle as reliable;

[0219] If the obstacle of the first type is within the overlapping detection area and the obstacle position corresponding to the obstacle in the first obstacle information matches the obstacle distance corresponding to the obstacle in the second obstacle information, determine that the reliable type of the obstacle is reliable;

[0220] If the obstacle of the first type is within the overlapping detection area and the obstacle position corresponding to the obstacle in the first obstacle information does not match the obstacle distance corresponding to the obstacle in the second obstacle information, determine that the reliable type of the obstacle is unreliable;

[0221] Determine the reliable type of the obstacle of the second type as reliable.

[0222] In a possible implementation manner, the determining module 111 is specifically configured to:

[0223] If the first speed is less than or equal to the second speed, determine the first speed as the target speed;

[0224] If the first speed is less than or equal to the preset speed, determine the first speed as the target speed;

[0225] If the first speed is greater than the second speed and the second speed is greater than the preset speed, determine the second speed as the target speed;

[0226] If the first speed is greater than the second speed and the second speed is equal to the preset speed, determine the second speed as the target speed;

[0227] If the preset speed is greater than the second speed and the preset speed is less than the first speed, determine the preset speed as the target speed.

[0228] In a possible implementation manner, before determining the first obstacle information according to the preset safe obstacle avoidance area of the rail robot and the TOF data, the obstacle avoidance device of the rail robot further includes a preprocessing module, configured to align the first TOF data collected by the TOF sensor and the first ultrasonic data collected by the ultrasonic sensor in time according to the running speed of the rail robot, and obtain the TOF data and the ultrasonic data.

[0229] In a possible implementation manner, the preprocessing module is specifically configured to:

[0230] According to the running speed of the rail robot, align the first TOF data collected by the TOF sensor and the first ultrasonic data in time, and obtain the second TOF data and the second ultrasonic data

[0231] Perform time-domain smoothing and noise elimination processing on the second TOF data and the second ultrasonic data to generate TOF data and ultrasonic data;

[0232] If it is determined that any one of the TOF sensor and the ultrasonic sensor has a fault according to the anomaly mark and / or preset conditions, the detection range of the other sensor will be increased.

[0233] The obstacle avoidance device for the rail robot provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0234] Figure 12 The structural schematic of the rail robot provided by this application Figure 2 As Figure 12 shown, the rail robot 120 provided in this embodiment includes: a TOF sensor 121, an ultrasonic sensor 122, at least one processor 123, and a memory 124.

[0235] Optionally, the rail robot 120 further includes a communication component 125. Among them, the processor 123, the memory 124, and the communication component 125 are connected through a bus 126.

[0236] In the specific implementation process, at least one processor 123 executes the computer execution instructions stored in the memory 124, so that at least one processor 123 executes the above method.

[0237] The specific implementation process of the processor 123 can refer to the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0238] In the above embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), or other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0239] The memory may include high-speed memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0240] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0241] This application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0242] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the above method is implemented.

[0243] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disc. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0244] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0245] The division of units is only a logical function division. In actual implementation, there can be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0246] The unit described as a separating component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed across multiple network units. Some or all of these units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0247] In addition, in each embodiment of the present invention, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0248] If the function 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 invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs and other various media that can store program codes.

[0249] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disks, or optical discs and other various media that can store program codes.

[0250] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation schemes of the present invention. The present invention aims to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include the common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the precise structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A rail robot obstacle avoidance method, characterized in that: Applied to a rail robot, the rail robot is equipped with a time-of-flight TOF sensor and an ultrasonic sensor, and the method comprises: Determining first obstacle information according to a preset safe obstacle avoidance area of ​​the rail robot and the TOF data, wherein the first obstacle information includes an obstacle position and a first obstacle type, and the first obstacle type includes a first type; The minimum value between the braking distance of the rail robot and the preset detection distance is determined as the first distance, and the maximum value between the deceleration distance of the rail robot and the preset distance is determined as the second distance, wherein the deceleration distance is the distance traveled by the rail robot when it decelerates to a stop at a preset acceleration, and the preset distance is the preset minimum distance between the rail robot and the fixed obstacle; Determine second obstacle information according to the ultrasonic data, the first distance, and the second distance, wherein the second obstacle information includes an obstacle distance and a second obstacle type, wherein the second obstacle type includes the first type and a second type, and the distance between an obstacle of the second type and the track robot is smaller than the distance between an obstacle of the first type and the track robot; Determining a credible type of each obstacle according to the first obstacle information, the second obstacle information, a first field of view angle of the TOF sensor, and a second field of view angle of the ultrasonic sensor; Controlling the track robot to run according to the credible type of each obstacle; The determining the credible type of each obstacle according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor includes: Determining an overlapping detection area of ​​the TOF sensor and the ultrasonic sensor according to the first field of view angle and the second field of view angle; If the obstacle of the first type is not within the overlap detection area, determining the credible type of the obstacle as credible; If the obstacle of the first type is within the overlap detection area, and the obstacle position corresponding to the obstacle in the first obstacle information matches the obstacle distance corresponding to the obstacle in the second obstacle information, determining that the credible type of the obstacle is credible; If the obstacle of the first type is within the overlap detection area, and the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information do not match, determining that the credible type of the obstacle is untrustworthy; The plausible type of the second-type obstacle is determined to be plausible.

2. The method according to claim 1, characterized in that The determining the second obstacle information according to the ultrasonic data, the first distance, and the second distance includes: If the object distance indicated by the ultrasonic data is less than or equal to the first distance, determining that the second obstacle type is the second type; If the object distance is greater than the first distance and the object distance is less than the second distance, determining that the second obstacle type is the first type; The second obstacle information is determined according to the object distance and the second obstacle type.

3. The method according to claim 1 or 2, characterized in that: The step of controlling the operation of the track robot according to the trustworthy type of each obstacle comprises: According to the trust type of each obstacle, determine the trustworthy obstacle closest to the track robot and the untrustworthy obstacle closest to the track robot; Determine a first speed at which the track robot moves to the front of the credible obstacle and a second speed at which the track robot moves to the front of the uncredible obstacle; Determine a target speed of the track robot according to a preset speed, the first speed, and the second speed, wherein a braking distance corresponding to the preset speed approaches 0; The track robot is controlled to run at the target speed.

4. The method according to claim 3, characterized in that Determining the target speed of the track robot according to the preset speed, the first speed and the second speed includes: If the first speed is less than or equal to the second speed, determining the first speed as the target speed; If the first speed is less than or equal to the preset speed, determining the first speed as the target speed; If the first speed is greater than the second speed, and the second speed is greater than the preset speed, determining the second speed as the target speed; If the first speed is greater than the second speed, and the second speed is equal to the preset speed, determining the second speed as the target speed; If the preset speed is greater than the second speed and the preset speed is less than the first speed, the preset speed is determined as the target speed.

5. The method according to claim 1 or 2, characterized in that: Before determining the first obstacle information according to the preset safe obstacle avoidance area of ​​the rail robot and the TOF data, the method includes: According to the running speed of the track robot, the first TOF data collected by the TOF sensor and the first ultrasonic data collected by the ultrasonic sensor are aligned in time to obtain the TOF data and the ultrasonic data.

6. The method according to claim 5, characterized in that The step of aligning the first TOF data collected by the TOF sensor and the first ultrasonic data collected by the ultrasonic sensor in time according to the running speed of the track robot to obtain the TOF data and the ultrasonic data includes: According to the running speed of the track robot, the first TOF data and the first ultrasonic data collected by the TOF sensor are aligned in time to obtain the second TOF data and the second ultrasonic data. Performing time domain smoothing and noise elimination processing on the second TOF data and the second ultrasonic data to generate the TOF data and the ultrasonic data; If it is determined according to the abnormal mark and / or the preset condition that any one of the TOF sensor and the ultrasonic sensor is faulty, the detection range of the other sensor is increased.

7. A rail robot obstacle avoidance device, characterized in that: Applied to a rail robot, the rail robot is equipped with a time-of-flight TOF sensor and an ultrasonic sensor, and the device comprises: A determination module, configured to determine first obstacle information according to a preset safe obstacle avoidance area of ​​the rail robot and TOF data, wherein the first obstacle information includes an obstacle position and a first obstacle type, and the first obstacle type includes a first type; The determination module is further used to determine the minimum value of the braking distance of the rail robot and the preset detection distance as the first distance, and determine the maximum value of the deceleration distance of the rail robot and the preset distance as the second distance, wherein the deceleration distance is the distance traveled by the rail robot when it decelerates to a stop at a preset acceleration, and the preset distance is the preset minimum distance between the rail robot and the fixed obstacle; The determination module is further used to determine second obstacle information according to the ultrasonic data, the first distance, and the second distance, the second obstacle information includes an obstacle distance and a second obstacle type, the second obstacle type includes the first type and a second type, and the distance between an obstacle of the second type and the track robot is smaller than the distance between an obstacle of the first type and the track robot; The determination module is further used to determine the credible type of each obstacle according to the first obstacle information, the second obstacle information, the first field of view angle of the TOF sensor, and the second field of view angle of the ultrasonic sensor; A control module, used for controlling the operation of the track robot according to the trustworthy type of each obstacle; The determination module is specifically used to determine the overlapping detection area of ​​the TOF sensor and the ultrasonic sensor according to the first field of view angle and the second field of view angle; if the first type of obstacle is not in the overlapping detection area, the credible type of the obstacle is determined to be credible; if the first type of obstacle is in the overlapping detection area, and the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information match, then the credible type of the obstacle is determined to be credible; if the first type of obstacle is in the overlapping detection area, and the obstacle position corresponding to the obstacle in the first obstacle information and the obstacle distance corresponding to the obstacle in the second obstacle information do not match, then the credible type of the obstacle is determined to be uncredible; and the credible type of the second type of obstacle is determined to be credible.

8. A rail robot, characterized in that: include: Time-of-flight TOF sensor, ultrasonic sensor, memory and processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The method comprises a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images