Transparent obstacle contour detection method and device, robot and medium
By combining lidar and ultrasonic radar, using SLAM technology and motion instructions to detect the contours of transparent obstacles in robot navigation, the problem of difficulty in detecting transparent obstacles in the prior art is solved, and navigation safety and efficiency are improved.
Patent Information
- Application Number
- CN202411186436.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-06
AI Technical Summary
Existing robot navigation technology is difficult to accurately detect transparent obstacles, especially lidar cannot sense transparent obstacles, such as glass doors and floor-to-ceiling windows, resulting in impairment of robot navigation safety.
Combining the advantages of lidar and ultrasonic radar, by acquiring environmental data during SLAM, generating motion instructions to move the robot to one side of the transparent obstacle and move on the other side to obtain contour information, and using ultrasonic data and optical data to determine transparency Profile of obstacles.
Accurate capture of transparent obstacle profiles is achieved, the risk of collision with obstacles is reduced, and the safety and navigation efficiency of robot navigation are improved.
Smart Images

Figure CN119088011A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of robotics technology, and in particular to a method, device, robot and medium for detecting the contour of a transparent obstacle. Background Art
[0002] With the rapid development of robotics technology, robots are increasingly used in daily life, industrial production, medical care, military exploration and other fields. In these applications, accurate positioning of robots is the basis for realizing their autonomous navigation, task execution and other functions. However, the environment in which robots are located is often complex and changeable, which poses a severe challenge to the robot's detection technology of environmental objects. In related technologies, the detection scheme for transparent obstacles is not accurate enough and the contour information of transparent obstacles cannot be obtained. Summary of the invention
[0003] In view of this, the embodiments of the present application at least provide a method, device, robot and medium for detecting the contour of a transparent obstacle.
[0004] The technical solution of the embodiment of the present application is implemented as follows:
[0005] On the one hand, an embodiment of the present application provides a method for detecting the contour of a transparent obstacle, the method comprising: in the process of generating an environmental map through a simultaneous positioning and mapping scheme, obtaining environmental data in an obstacle detection process; in response to the environmental data in the obstacle detection process indicating the presence of a transparent obstacle around a robot, generating a first motion instruction; the first motion instruction is used to instruct the robot to move to one side of the transparent obstacle; in response to the robot reaching one side of the transparent obstacle, generating a second motion instruction; the second motion instruction is used to instruct the robot to move from one side of the transparent obstacle to the other side; in the movement process based on the second motion instruction, obtaining environmental data in a contour acquisition process, and determining the contour information of the transparent obstacle based on the environmental data in the contour acquisition process.
[0006] On the other hand, an embodiment of the present application provides a contour detection device for a transparent obstacle, the device comprising: an acquisition module, used to acquire environmental data in an obstacle detection process in the process of generating an environmental map through a simultaneous positioning and mapping scheme; a first generation module, used to generate a first motion instruction in response to the environmental data in the obstacle detection process characterizing the presence of a transparent obstacle around a robot; the first motion instruction is used to instruct the robot to move to one side of the transparent obstacle; a second generation module, used to generate a second motion instruction in response to the robot reaching one side of the transparent obstacle; the second motion instruction is used to instruct the robot to move from one side of the transparent obstacle to the other side; a determination module, used to acquire environmental data in a contour acquisition process during the movement process based on the second motion instruction, and determine the contour information of the transparent obstacle based on the environmental data in the contour acquisition process.
[0007] On the other hand, an embodiment of the present application provides a robot, including a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.
[0008] On the other hand, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements part or all of the steps in the above method when executed by a processor.
[0009] On the other hand, an embodiment of the present application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements some or all of the steps in the above method.
[0010] In an embodiment of the present application, by collecting environmental data during the simultaneous localization and mapping (SLAM) process, when a transparent obstacle is detected in the environment, a first motion instruction is immediately generated and executed to move to one side of the obstacle, thereby reducing the risk of collision with the obstacle; at the same time, when the robot reaches one side of the obstacle, a second motion instruction is used to instruct it to continue moving to the other side, thereby enabling the robot to fully perceive the obstacle from different angles to determine the contour information of the transparent obstacle, thereby achieving accurate capture of the contour of the transparent obstacle.
[0011] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.
[0013] Figure 1 A schematic diagram of the implementation process of a transparent obstacle contour detection method provided in an embodiment of the present application Figure 1 ;
[0014] Figure 2 A schematic diagram of the implementation process of a transparent obstacle contour detection method provided in an embodiment of the present application Figure 2 ;
[0015] Figure 3 A schematic diagram of the implementation process of a transparent obstacle contour detection method provided in an embodiment of the present application Figure 3 ;
[0016] Figure 4 A detection flow chart of a transparent obstacle detection method provided in an embodiment of the present application;
[0017] Figure 5 A schematic diagram of a scene of a robot moving process of a transparent obstacle detection method provided in an embodiment of the present application;
[0018] Figure 6 A schematic diagram of the relative position relationship between a transparent obstacle and a robot provided in an embodiment of the present application;
[0019] Figure 7 A schematic diagram of the structure of a transparent obstacle contour detection device provided in an embodiment of the present application;
[0020] Figure 8 A schematic diagram of a hardware entity of a robot provided in an embodiment of the present application. DETAILED DESCRIPTION
[0021] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.
[0022] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "first / second / third" involved are merely used to distinguish similar objects and do not represent a specific order for the objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.
[0023] Before further describing the embodiments of the present disclosure in detail, the nouns and terms involved in the embodiments of the present disclosure are described. The nouns and terms involved in the embodiments of the present disclosure are subject to the following interpretations.
[0024] (1) Simultaneous Localization and Mapping (SLAM): Allows a robot to determine its position in an unknown environment and build a map of its surroundings in real time. It achieves two core tasks: localization and mapping by combining data collected by multiple sensors (such as lidar, cameras, inertial measurement units, etc.) and processing these data with complex algorithms. In the SLAM process, the robot first obtains information about the surrounding environment through its sensors. This sensor data may include laser point clouds, image frames, inertial measurements, etc. Next, the SLAM algorithm extracts useful feature points from this raw data, which represent key parts of the environment that can be used for localization and mapping. The algorithm then performs data association, that is, matching the features of the current frame with the features of the previous map or other frames. This process is key to understanding how the robot moves and how the environment changes. Through data association, the SLAM algorithm can infer the robot's motion trajectory, including translation and rotation. After determining the robot's motion trajectory, the SLAM algorithm uses this information to build a map of the environment. There are many ways to build a map, the most common of which include overlaying grid maps and point cloud maps.
[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing this application and are not intended to limit this application.
[0026] At present, the technology of autonomous mobile navigation robots is becoming more and more mature, and more and more mobile robots are used in daily production, such as AGV (Automated Guided Vehicle) in factories and sweeping robots in homes. Most of these mobile robots use SLAM (Simultaneous Localization And Mapping) technology to achieve autonomous navigation. SLAM technology can provide mobile robots with their own posture information and environmental maps under the premise of unknown scenes and unknown robot initial postures, thereby helping mobile robots to achieve autonomous navigation. Compared with traditional robot navigation methods, SLAM technology does not require manual deployment of scenes, does not require real-time GPS (Global Positioning System) signals, and is more convenient and faster. Existing SLAM solutions can be roughly divided into laser SLAM and visual SLAM according to different sensors. Visual SLAM uses cameras as environmental perception sensors, which have the advantages of low price and small size, but the visual method is greatly affected by changes in ambient light and is difficult to work normally at night. Although the laser SLAM method using lidar as the perception sensor is more expensive than the visual solution, lidar has a larger field of view and more reliable stability. Lidar can scan the 360-degree environment around the robot at a high speed of 10 Hz, almost unaffected by changes in ambient light.
[0027] One challenge faced by the SLAM solution using LiDAR as an environmental perception sensor in actual use is that it cannot perceive transparent obstacles in the environment, such as glass doors and French windows, which is very dangerous during the navigation of mobile robots. When the robot cannot perceive closed glass doors and French windows, there is a high risk of collision, causing damage to the robot and huge property losses. The emergency method at this stage is to integrate different sensors on the robot to assist robot navigation, such as installing ultrasonic radars around the robot to detect obstacles around the robot. The difference between ultrasonic radar and LiDAR is that the former uses sound waves to detect obstacles and the latter uses lasers, so ultrasonic radar can detect transparent obstacles. However, one limitation of ultrasonic radar is that it can only perceive obstacles, and the location information and geometry of the obstacles are still unknown. The method of this application combines the advantages of LiDAR and ultrasonic radar to realize the detection of transparent obstacles and their boundaries, thereby helping the robot perceive transparent obstacles in the environment to ensure navigation safety.
[0028] The embodiment of the present application provides a method for detecting the contour of a transparent obstacle, which can be executed by a processor of a robot. The robot can be a device with autonomous movement capability, sensor integration, and data processing capability. These devices can perform complex tasks, including but not limited to navigation, path planning, object recognition and manipulation, and environmental perception.
[0029] In some embodiments, the robot may be a device that not only has basic data processing capabilities, but also integrates sensors (such as cameras, laser radars, ultrasonic sensors, gyroscopes, accelerometers, etc.), actuators (such as motors, wheels, robotic arms, etc.), and algorithms and software for controlling and optimizing these components. Exemplarily, the robot may be a service robot (such as a household sweeping robot, a restaurant food delivery robot, a hospital nursing robot, etc.), an industrial robot (a robot that performs processing, assembly, and handling tasks with high repetitiveness and strict precision requirements on a production line), an exploration robot (for exploration and reconnaissance tasks in extreme environments or dangerous areas), and a mobile robot (self-driving cars, drones, etc.).
[0030] Figure 1 A schematic diagram of the implementation process of a transparent obstacle contour detection method provided in an embodiment of the present application Figure 1 ,like Figure 1 As shown, the method includes the following steps S101 to S104:
[0031] Step S101: in the process of generating an environment map by using a simultaneous positioning and mapping solution, obtaining environment data in the process of obstacle detection.
[0032] In the embodiment of the present application, the environment map can be any one of a grid map and a label map. Taking the grid map as an example, the grid map is a map representation method that divides the environment into multiple small cells (grids), each grid represents a small area in the environment, and a value is assigned to indicate whether the area is occupied by an obstacle. Exemplarily, the grid can have three states: unknown state, occupied state, and idle state.
[0033] In some embodiments, the above process of generating an environmental map through a simultaneous positioning and mapping solution can actually be understood as: the robot keeps moving, using sensors such as lidar and ultrasonic sensors to scan the surrounding environment in real time, and using the SLAM algorithm to process the sensor data, and estimate the robot's position (position and posture) by matching feature points in the sensor data; at the same time, a grid map of the environment is constructed based on the sensor data, marking obstacles and free areas.
[0034] It should be noted that the above obstacle detection process refers to the process in which the robot collects and processes environmental data through its sensor system (such as lidar, ultrasonic sensor, camera, etc.) to identify and locate surrounding obstacles when creating (or updating) a grid map. This process occurs when the robot starts to move and continues until the robot detects a transparent obstacle.
[0035] In the embodiment of the present application, the above-mentioned environmental data may include ultrasonic data and optical data. Among them, ultrasonic data is data collected by ultrasonic sensors. It can be understood that the ultrasonic sensor has a better detection effect on transparent materials (such as glass). Optical data is data collected by optical sensors such as cameras and lasers. Compared with ultrasonic sensors, it can identify and restore the position of non-transparent obstacles in the environment with higher accuracy through image recognition, point cloud feature analysis, etc.
[0036] Step S102: In response to the environmental data in the obstacle detection process indicating that there is a transparent obstacle around the robot, a first motion instruction is generated; the first motion instruction is used to instruct the robot to move to one side of the transparent obstacle.
[0037] Among them, the transparent obstacles in the embodiments of the present application refer to obstacles that are difficult to be directly detected by optical sensors / visual sensors such as lidar, such as transparent glass doors, transparent windows, etc.
[0038] In an embodiment of the present application, the above-mentioned environmental data may include ultrasonic data and optical data; the method also includes: generating a first obstacle detection result based on the ultrasonic data, and generating a second obstacle detection result based on the optical data; when the first obstacle detection result and the second obstacle detection result are different, determining that there are transparent obstacles around the robot.
[0039] In some embodiments, when the robot generates an environmental map through the simultaneous localization and mapping solution, the robot collects environmental data using ultrasonic sensors and optical sensors at the same time. When the detection results of the two sensors are inconsistent, that is, when the ultrasonic sensor detects an obstacle but the optical sensor does not recognize the corresponding object, it can be determined that there is a transparent obstacle around the robot.
[0040] In the embodiment of the present application, when the robot detects a transparent obstacle through ultrasonic sensors and optical sensors, in order to more accurately identify and locate the obstacle, the robot needs to perform a series of actions, one of which is to move to one side of the transparent obstacle. Accordingly, the first motion instruction is actually to control the robot to move to one end of the transparent obstacle, so as to subsequently move from one end of the obstacle to the other end, thereby obtaining the overall outline of the obstacle.
[0041] In some embodiments, optical data (such as lidar point cloud, camera image, etc.) in the obstacle detection process can be used to preliminarily determine the position and approximate shape of the transparent obstacle, and then identify the relative direction of the transparent obstacle in the robot coordinate system, and then randomly select one side (one end) of the transparent obstacle as the target direction to generate the first motion instruction.
[0042] In other embodiments, the ultrasonic data in the obstacle detection process can also be used to estimate the relative direction of the transparent obstacle in the robot coordinate system. The implementation process can include: arranging multiple ultrasonic sensors in an arc or ring manner at the front end or around the robot in advance to detect transparent obstacles from multiple angles. When a transparent obstacle is detected, by obtaining and comparing the distances from different ultrasonic sensors to the transparent obstacle, the angle of the transparent obstacle relative to the center point of the robot is calculated according to the layout of each ultrasonic sensor and the distance from each ultrasonic sensor to the transparent obstacle. It can be understood that the direction corresponding to the ultrasonic sensor with a closer distance is closer to the actual position of the transparent obstacle.
[0043] After obtaining the relative direction of the transparent obstacle in the robot coordinate system, any direction perpendicular to the relative direction can be used as the moving direction corresponding to the first motion instruction. It should be understood that the direction of the transparent obstacle determined here does not require too high accuracy. Its main function is to determine the moving direction corresponding to the first motion instruction, as long as the moving direction does not control the robot to move directly toward the transparent obstacle. Doing so can ensure that the robot does not move directly toward the obstacle, thereby reducing the risk of collision. At the same time, it also provides the robot with more flexibility and possibilities to further explore the environment and obtain more information about transparent obstacles.
[0044] Step S103: in response to the robot reaching one side of the transparent obstacle, generating a second motion instruction; the second motion instruction is used to instruct the robot to move from one side of the transparent obstacle to the other side.
[0045] In some embodiments, the moving direction corresponding to the second motion instruction may be opposite to the moving direction corresponding to the first motion instruction. In this way, in the process of controlling the movement of the robot based on the second motion instruction, the overall contour features of the robot can be detected, that is, the contour features from one side to the other side (also understood as one end to the other end) of the transparent obstacle.
[0046] In some embodiments, the first motion instruction and the second motion instruction further include the moving speed of the robot. The moving speed may be related to the obstacle distance detected by the robot and the obstacle distance between the robots; for example, the greater the obstacle distance, the greater the moving speed, and the smaller the obstacle distance, the smaller the moving speed. In this way, it is possible to avoid the robot from hitting a transparent obstacle or losing the transparent obstacle target due to excessive moving speed. In other embodiments, the moving speed may also be related to the generation accuracy of the contour information. For example, the higher the generation accuracy, the smaller the moving speed, and the lower the generation accuracy, the larger the moving speed. The generation accuracy of the contour information may be related to the resolution of the grid map.
[0047] Step S104: during the movement process based on the second motion instruction, environmental data of a contour acquisition process is acquired, and contour information of the transparent obstacle is determined based on the environmental data of the contour acquisition process.
[0048] In the embodiment of the present application, during the movement of the robot based on the second motion instruction, the system continuously acquires environmental data of the contour acquisition process. The environmental data may include the obstacle distance between the robot and the transparent obstacle during the above movement process, and then the robot can extract the contour information of the transparent obstacle based on the obstacle distance and the robot's position (position coordinates and orientation angle) in the world coordinate system.
[0049] In an embodiment of the present application, by collecting environmental data during the simultaneous localization and mapping (SLAM) process, when a transparent obstacle is detected in the environment, a first motion instruction is immediately generated and executed to move to one side of the obstacle, thereby reducing the risk of collision with the obstacle; at the same time, when the robot reaches one side of the obstacle, a second motion instruction is used to instruct it to continue moving to the other side, thereby enabling the robot to fully perceive the obstacle from different angles to determine the contour information of the transparent obstacle, thereby achieving accurate capture of the contour of the transparent obstacle.
[0050] Figure 2 This is a schematic diagram of the implementation process of a transparent obstacle contour detection method provided in an embodiment of the present application. Figure 2 , the method can be executed by a processor of the robot. Figure 1 , Figure 1 Step S103 in can be updated to step S201, combining Figure 2 The steps shown are explained.
[0051] Step S201: In response to the robot reaching a first position, generating the second motion instruction.
[0052] The first position is located on one side of the transparent obstacle, and the environmental data acquired at the first position indicates that there is no transparent obstacle around the robot.
[0053] In the embodiment of the present application, in the process of the robot moving to one side of the robot in response to the first motion instruction, in order to determine whether the robot has reached the end of the transparent obstacle on this side, it can be determined by detecting whether there is a transparent obstacle in the environmental data. Generally speaking, in the process of the robot moving to one end of the transparent obstacle, if it has not reached one end of the transparent obstacle, the environmental data collected by the robot can still determine that there is a transparent obstacle around; correspondingly, if it has reached one end of the transparent obstacle and continues to move, the environmental data collected by the robot can determine that there is no transparent obstacle around.
[0054] Based on this, the present application uses the acquired environmental data to represent the position reached by the robot when there are no transparent obstacles around the robot as the first position. For example, after the robot reaches the last position where the transparent obstacle can be detected, the next position reached is determined as the first position; the position after moving a certain distance can also be determined as the first position.
[0055] In some embodiments, whether the robot reaches the first position can be determined through steps S2011 and S2012.
[0056] Step S2011: When the robot moves toward one side of the transparent obstacle in response to the first motion instruction, environmental data of the first movement process is collected.
[0057] In some embodiments, since the process of constructing the outline of the transparent obstacle in the present application is in the subsequent outline acquisition process, the environmental data of the above-mentioned first movement process is only used to detect whether there are transparent obstacles around the robot, without determining the outline information of the transparent obstacle.
[0058] In other embodiments, considering that the position of the transparent obstacle will not change in a short time, the contour information for verification can be determined based on the collected environmental data during the first movement process. After the contour information of the contour collection process is obtained in step S104, the contour information for verification is used to verify it. In the case where the contour information error is large, a third motion instruction is generated, and the third control instruction is used to control the robot to move from the other side of the transparent obstacle to this side, and based on the contour information corresponding to the second motion instruction and the contour information corresponding to the third motion instruction, the final contour information corresponding to the transparent obstacle is generated. In general, the contour information corresponding to the second motion instruction and the contour information corresponding to the third motion instruction can be fused based on a weighted algorithm to obtain the final contour information corresponding to the transparent obstacle. Among them, considering that the third motion information reflects the updated contour data, the weight of the contour information corresponding to the third motion is higher than the weight of the contour information corresponding to the second motion instruction.
[0059] Step S2012: When the environmental data of the first movement process indicates that there are no transparent obstacles around the robot, determine that the robot has reached a first position.
[0060] In some embodiments, during the above-mentioned first movement process, if the environmental data at the previous moment indicates that there are transparent obstacles around the robot, and the environmental data at the current moment indicates that there are no transparent obstacles around the robot, it is considered that the robot has reached the end of one side of the transparent obstacle, and the position at the current moment is determined as the first position.
[0061] In an embodiment of the present application, by detecting whether there are transparent obstacles around the robot, it is possible to accurately determine whether the robot has reached one side of the transparent obstacle, and generate a corresponding second motion instruction to start the contour detection process, thereby improving the contour detection efficiency.
[0062] In some embodiments, the first motion instruction is used to instruct the robot to move along a first direction toward one side of the transparent obstacle; the first direction is not parallel to the receiving direction of the ultrasonic data, and the angle between the first direction and the receiving direction of the ultrasonic data is related to the obstacle distance; the obstacle distance is the distance between the robot and the transparent obstacle determined based on the ultrasonic data.
[0063] In some embodiments, the first direction may be a direction perpendicular to the receiving direction of the ultrasonic data (the detection direction of the ultrasonic wave), wherein the receiving direction of the ultrasonic data is opposite to the detection direction of the ultrasonic wave.
[0064] In some embodiments, the second movement instruction is used to instruct the robot to move toward the other side of the transparent obstacle along a second direction, where the second direction is opposite to the first direction.
[0065] In some embodiments, in the process of controlling the robot to move along a first direction toward one side of a transparent obstacle based on a first motion instruction, the change trend between the currently collected obstacle distance and the historically collected obstacle distance can be obtained, and then based on the change trend, the first direction is adjusted so that the obstacle distance approaches the target detection distance.
[0066] The target detection distance is a preset obstacle distance. When the robot maintains the target detection distance to detect the outline of the transparent obstacle, the accuracy of the ultrasonic data can be guaranteed and the robot can be prevented from colliding with the transparent obstacle. In some embodiments, the size of the target detection distance is related to the moving speed corresponding to the second motion instruction. The higher the moving speed, the larger the target detection distance, and the lower the moving speed, the smaller the target detection distance.
[0067] In the above embodiment, the angle between the first direction and the receiving direction of the ultrasonic data is related to the obstacle distance. In fact, the corresponding first direction is generated based on the size relationship between the currently collected obstacle distance and the target detection distance. In the case where the obstacle distance is greater than the target detection distance, the generated first direction is used to control the robot to approach the transparent obstacle; in the case where the obstacle distance is less than the target detection distance, the generated first direction is used to control the robot to stay away from the transparent obstacle.
[0068] In the above embodiment, the obstacle distance is continuously collected and updated during the movement of the robot along the first direction. By comparing the current obstacle distance with the historically collected distance, it can be determined whether the robot is approaching or moving away from the obstacle, and based on the comparison result of the obstacle distance and the target detection distance, the first direction is dynamically adjusted so that the robot always remains within a safe and effective distance range during the detection process. In this way, by combining ultrasonic sensors, dynamic motion command generation and obstacle distance feedback adjustment mechanism, the robot can effectively realize accurate detection and obstacle avoidance of transparent obstacles.
[0069] Figure 3 This is a schematic diagram of the implementation process of a transparent obstacle contour detection method provided in an embodiment of the present application. Figure 3 , the method can be executed by a processor of the robot. Figure 1 , Figure 1 The step S104 in the process of “determining the contour information of the transparent obstacle based on the environmental data of the contour collection process” can be updated to step S301 and step S302, which will be combined with Figure 3The steps shown are explained.
[0070] Step S301: In response to the environmental data during the contour acquisition process indicating that there are transparent obstacles around the robot, a set of position points of the transparent obstacle in the world coordinate system is determined based on the ultrasonic detection direction, the obstacle distance between the robot and the transparent obstacle detected by the ultrasonic wave, and the position of the robot in the world coordinate system.
[0071] In an embodiment of the present application, the starting time point of the above-mentioned contour collection process is the time point when the robot starts to move from one side of the transparent obstacle to the other side in response to the second motion instruction. In some embodiments, the ending time point of the contour collection process is the time point when the collected environmental data indicates that there are no transparent obstacles around the robot during the movement of the robot based on the second motion instruction.
[0072] In some embodiments, during the above-mentioned contour collection process, the robot can obtain environmental data corresponding to multiple time points according to a preset sampling interval, and for the environmental data corresponding to each time point, determine the position point corresponding to each time point based on the ultrasonic detection direction corresponding to the time point, the obstacle distance between the robot and the transparent obstacle, and the position of the robot in the world coordinate system, thereby obtaining a set of position points of the transparent obstacle in the world coordinate system.
[0073] It can be understood that the number of location points in the above location point set increases with time.
[0074] In other embodiments, during the above-mentioned contour acquisition process, when the posture change of the robot relative to the posture of the previous sampling point is greater than a preset posture change threshold, the robot obtains the environmental data at the current moment, and based on the ultrasonic detection direction corresponding to the current moment, the obstacle distance between the robot and the transparent obstacle, and the posture of the robot in the world coordinate system, generates a position point corresponding to the current sampling point, and obtains a set of position points of the transparent obstacle in the world coordinate system by continuously storing the position points corresponding to each sampling point.
[0075] It can be understood that the number of position points in the above position point set increases as the position and posture of the robot changes.
[0076] In some embodiments, when the ultrasonic detection direction is the ultrasonic detection direction in the robot coordinate system, since the orientation angle in the robot's posture is the orientation angle of the robot relative to the world coordinate system, the ultrasonic detection direction in the world coordinate system can be determined based on the ultrasonic detection direction and the orientation angle of the robot relative to the world coordinate system. Since the ultrasonic detection direction in the world coordinate system is the angle between the ultrasonic wave and the X-axis direction in the world coordinate system, the coordinate difference between the coordinate information of the transparent obstacle in the world coordinate system and the coordinate information of the robot in the world coordinate system can be determined based on the obstacle distance between the robot and the transparent obstacle and the angle, using a trigonometric relationship, that is, the difference between the two coordinate information in the X-axis direction and the difference in the Y-axis direction are determined respectively, and then the coordinate information of the corresponding transparent obstacle position point is generated based on the coordinate information of the robot.
[0077] In other embodiments, when the ultrasonic detection direction is the ultrasonic detection direction in the robot coordinate system, the intercept on the X-axis and the intercept on the Y-axis of the transparent obstacle in the robot coordinate system can be calculated in the robot coordinate system using the triangular relationship and the obstacle distance between the robot and the transparent obstacle; then, the intercept on the X-axis and the intercept on the Y-axis are transformed using the transpose matrix of the rotation matrix from the X-axis robot coordinate system to the world coordinate system to obtain the coordinate difference between the coordinate information of the transparent obstacle in the world coordinate system and the coordinate information of the robot in the world coordinate system, that is, the intercept on the X-axis in the robot coordinate system is converted into the difference in the X-axis direction, and the intercept on the Y-axis in the robot coordinate system is converted into the difference in the Y-axis direction.
[0078] For example, the robot moves in a room with a window made of transparent glass as an obstacle. The robot detects multiple position points of the window through ultrasonic sensors, and combines its own position information in the world coordinate system to convert these position points into the world coordinate system to form a set of position points. These sets of position points describe the overall position and shape of the window in the world coordinate system.
[0079] Step S302: Determine contour information of the transparent obstacle based on the set of position points.
[0080] In some embodiments, the above-mentioned determination of the contour information of the transparent obstacle based on the set of position points can be implemented through step S3021.
[0081] Step S3021: During the movement process based on the second motion instruction, in response to the environmental data during the contour acquisition process representing that the robot moves from a position where transparent obstacles exist around it to a position where no transparent obstacles exist, contour information of the transparent obstacles is determined based on the set of position points.
[0082] In an embodiment of the present application, in order to avoid unnecessary data calculation process, the present application adds a stop condition to the above step S302, that is, after reaching the stop condition, the contour information of the corresponding transparent obstacle is directly generated based on the set of position points.
[0083] In some embodiments, the stop condition includes: the environmental data in the contour acquisition process indicates that the robot moves from a position where there are transparent obstacles around to a position where there are no transparent obstacles. That is, in the process of the robot moving in response to the second motion instruction and updating the position point set, as long as the environmental data obtained at a time point / sampling point indicates that there are no transparent obstacles around the robot, it means that the robot has completed the process of moving from one end of the transparent obstacle to the other end, and then directly based on the position point set, the contour information of the transparent obstacle is determined.
[0084] In some embodiments, the contour information includes a grid where transparent obstacles exist in a grid map; the above-mentioned determination of the contour information of the transparent obstacle based on the set of position points can be implemented through step S3022.
[0085] Step S3022: Determine the grids in the grid map where transparent obstacles exist according to the position coordinates of each position point in the position point set in the world coordinate system and the range information of each grid in the grid map.
[0086] In an embodiment of the present application, the target grid in the grid map where the location point falls can be determined based on the location coordinates of the location point in the world coordinate system and the range information of each grid in the grid map, and it can be used as the grid with transparent obstacles in the grid map.
[0087] In some embodiments, the method further includes: modifying the grid state of the grid in which the transparent obstacle exists in the grid map to an occupied state. Therefore, compared with the grid map output in the related art, the grid map provided by the present application also carries the outline information of the transparent obstacle.
[0088] For example, it is assumed that the resolution of the grid map is 0.5 m × 0.5 m per grid, and the range information of each grid has been defined. The set of position points obtained by step S301 includes multiple position points of transparent obstacles in the world coordinate system. According to the coordinates of these position points and the resolution of the grid map, the grid corresponding to each position point can be determined, and these grids are marked as transparent obstacles. Finally, an "obstacle belt" representing the outline of the transparent obstacle is formed on the grid map.
[0089] In the embodiment of the present application, the outline information of the transparent obstacle is represented in the form of a grid map, which is convenient for the robot to perform subsequent path planning and obstacle avoidance decisions. Through the intuitive representation of the grid map, the robot can more easily identify the position and shape of the transparent obstacle, thereby selecting a more appropriate obstacle avoidance strategy.
[0090] The following describes the application of the transparent obstacle contour detection method provided in the embodiment of the present application in actual scenarios, mainly involving transparent obstacle detection based on ultrasonic radar blind spot filling.
[0091] For robot working scenarios with transparent obstacles, such as shopping malls, hospitals, factories and office buildings, there are many glass doors and floor-to-ceiling glass windows. These transparent obstacles will seriously affect the navigation safety of the robot. The method of this application combines the advantages of lidar and ultrasonic radar to realize the detection of transparent obstacles and their boundaries, thereby helping the robot perceive the transparent obstacles in the environment to ensure navigation safety.
[0092] The implementation method of the present application method is as follows: a mobile robot platform is equipped with sensors such as laser radar and ultrasonic detectors, and the environment is traversed using SLAM technology, and the posture information of the robot relative to the environment is determined in real time during the traversal process. During the SLAM process, the status of the laser point cloud and the ultrasonic point cloud are monitored at all times. When it is found that there is no obstacle information in the laser point cloud position area corresponding to the ultrasonic point cloud, it is considered that the robot is located near the transparent obstacle at this time. The robot is controlled to move slowly to one side until the observation results of the ultrasonic point cloud and the laser point cloud are consistent. At this time, it is considered that the robot is located on one side of the boundary of the transparent obstacle. The robot is slowly controlled to move in the opposite direction to calculate the coordinate points of the discrete transparent obstacles relative to the world coordinate system. The grid state corresponding to the coordinates of these transparent obstacles in the grid map is modified to an occupied state, and the grid map with transparent obstacle occupancy information is saved before the end of SLAM.
[0093] The detection flow chart of the transparent obstacle detection method of this application is as follows Figure 4 As shown, the method provided in the present application includes two inputs, namely a laser radar 41 and an ultrasonic sensor 42 , and one output, namely a grid map 43 .
[0094] In the embodiment of the present application, for a robot platform, the installation positions of its various sensors are known. Therefore, the joint calibration module 44 can use the known sensor installation position information to provide the relative posture relationship between the lidar coordinate system and the ultrasonic coordinate system, thereby facilitating the subsequent synchronous processing of laser point cloud data and ultrasonic data.
[0095] Exemplarily, the calibration result between the laser radar coordinate system and the ultrasonic coordinate system can be expressed by a two-dimensional pose, and the relative pose relationship between the ultrasonic coordinate system and the radar coordinate system is as shown in formula (1).
[0096]
[0097] in, Indicates the conversion from ultrasonic coordinate system to radar coordinate system, x is the lateral offset value, y is the longitudinal offset value, and θ is the yaw angle difference.
[0098] The simultaneous positioning and mapping module 45 senses the environment around the robot and the robot's own motion state through sensors, and determines the robot's position relative to the environment during the perception process. The robot uses simultaneous positioning and mapping technology to generate an environmental map after the robot traverses the environment for a week through sensors such as laser radar or cameras. The environmental map constructed by the simultaneous positioning and mapping module 45 has various forms. The map format generated by the method of this application is a grid map 43.
[0099] In some embodiments, the grid map 43 is a two-dimensional grid map. In other words, the two-dimensional grid map actually uses small square grids to represent a two-dimensional plane, and each small grid has three possible states: occupied state, idle state, and unknown state. Since the camera and the laser radar cannot observe transparent obstacles, the state of the small grid corresponding to the position of the transparent obstacle in the grid map is idle state, and the actual state is occupied state.
[0100] The transparent obstacle detection module 46 detects transparent obstacles around the robot by real-time monitoring of the laser radar and ultrasound. The relative position relationship between the laser radar coordinate system and the ultrasound coordinate system is obtained by the joint calibration module 44. And the relative position relationship between the two Align the laser point cloud and the ultrasonic point cloud. Monitor the ultrasonic point cloud in real time during the robot movement. As shown in formula (2), when the ultrasonic point cloud F U =[u,0,0] T There is obstacle point cloud information, and the laser point cloud corresponds to the location area F′ U =[x′,y′,θ′] T When there is no point cloud, it is judged that there are transparent obstacles around the robot.
[0101]
[0102] When there are transparent obstacles around the robot, the motion control module 47 issues a speed instruction to control the robot to move to one side until the ultrasonic wave cannot detect the obstacle. At this time, it is considered that the robot is located near the boundary of the transparent obstacle.
[0103] The transparent obstacle generating module 48 modifies the state of the grid on the corresponding grid of the grid map to an occupied state according to the laser point cloud and the ultrasonic point cloud, indicating that an obstacle exists at the grid.
[0104] like Figure 5 As shown, first, when the transparent obstacle detection module 46 detects a transparent obstacle when the robot is at position 55, the motion control module 47 controls the robot to move to one side of the transparent obstacle, assuming that it moves to the right side of the transparent obstacle. At this time, the robot comes to the edge of the transparent obstacle (here, it refers to the entire transparent obstacle formed by transparent obstacles 01 to 05, such as transparent doors and windows), that is, it moves from position 510 to position 520. The observation results of the laser point cloud and the ultrasonic point cloud are consistent, and neither of them has detected a transparent obstacle temporarily. At this time, the motion control module 47 controls the robot to move slowly to the left until the transparent obstacle point 01 is detected. At this time, the robot is at position 530.
[0105] See also Figure 6 , assuming that the world coordinate system is (X_world, Y_world), the robot coordinate system is (X_robot, Y_robot), the angle between the left boundary of the ultrasonic detection area (i.e. the position of the transparent obstacle point 01) and the robot coordinate system is θ, the distance of the transparent obstacle detected by the ultrasonic wave is d, and when the robot is at position 530, the position in the world coordinate system is (x_r, y_r, θ_r), then the position (x, y) of the transparent obstacle 01 in the world coordinate system is as shown in formula (3):
[0106]
[0107] Among them, R is the rotation matrix from the robot coordinate system to the world coordinate system, R T is the transposed matrix of the rotation matrix.
[0108] The above formula (3) actually calculates the X-axis intercept d·cos(θ) and the Y-axis intercept d·sin(θ) of the transparent obstacle in the robot coordinate system by using the trigonometric relationship and the obstacle distance between the robot and the transparent obstacle. Then, the transposed matrix R of the rotation matrix from the X-axis robot coordinate system to the world coordinate system is used. T , convert d·cos(θ) and the intercept d·sin(θ) on the Y axis to obtain the coordinate difference between the coordinate information of the transparent obstacle in the world coordinate system and the coordinate information of the robot in the world coordinate system, that is, convert the intercept on the X axis in the robot coordinate system into the difference d·cos(θ)*R in the X axis direction. T , and the Y-axis intercept in the robot coordinate system is converted to the difference in the Y-axis direction d·sin(θ)*R T .
[0109] The robot continues to move slowly to the left. During the movement, the simultaneous positioning and mapping module 45 provides the robot's position information (x_r, y_r, θ_r). The position of the transparent obstacle in the world coordinate system is calculated by formula (3) until the robot moves to the right boundary of the transparent obstacle (i.e., transparent obstacle point 05) and reaches position 540. The robot continues to move to the left. At this time, the observation results of the laser point cloud and the ultrasonic point cloud are consistent. Neither detects a transparent obstacle. When the robot moves to position 550, the observation results of the laser point cloud and the ultrasonic point cloud are completely consistent. At this point, a continuous discrete position coordinate of the transparent obstacle in the world coordinate system is obtained. Before the simultaneous positioning and mapping module 45 ends, the transparent obstacle generation module 48 inserts these position coordinates into the grid map 43 and modifies the state of the corresponding grid of the grid map to the occupied state.
[0110] Compared with the solution using a single sensor in the related art, the method for detecting the contour of a transparent obstacle provided by the above embodiment can obtain accurate obstacle location information from the lidar point cloud data, and determine whether a transparent obstacle exists from the difference between the ultrasonic point cloud and the laser point cloud, thereby fully combining the measurement advantages of the two sensors. In addition, considering that the ultrasonic point cloud cannot provide the contour information of the obstacle, the related art cannot provide the accurate contour size information of the transparent obstacle, nor can it provide the coordinate information of the transparent obstacle. Although the robot of the related art is moving during the detection process, the detection principle of the related art is to use laser observation point cloud and ultrasonic observation point cloud at a certain moment, which can be considered as the observation result of the robot in a stationary state. The contour detection method of the transparent obstacle provided in the embodiment of the present application can effectively detect the contour size of the transparent obstacle and give its accurate position coordinate information by controlling the robot to slowly move the robot from one side of the boundary of the obstacle to the other side; further, since the size contour information of the transparent obstacle cannot be given in the related scheme, it is difficult to directly use these obstacle coordinate information for optimal path planning during the robot navigation process. The contour detection method of the transparent obstacle provided in the embodiment of the present application recovers the boundary size of the transparent obstacle from the robot movement process, and adds the rasterized coordinates of the transparent obstacle to the grid map to help the robot perform global path planning, thereby improving the navigation efficiency and safety of the robot.
[0111] Based on the foregoing embodiments, the embodiments of the present application provide a contour detection device for a transparent obstacle, which includes the units included and the modules included in the units, which can be implemented by a processor in a robot; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.
[0112] Figure 7 A schematic diagram of the structure of a transparent obstacle contour detection device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the transparent obstacle contour detection device 700 includes: an acquisition module 710, a first generation module 720, a second generation module 730 and a determination module 740, wherein:
[0113] An acquisition module 710, for acquiring environmental data in an obstacle detection process during the process of generating an environmental map through a simultaneous localization and mapping solution;
[0114] A first generating module 720 is configured to generate a first motion instruction in response to the environmental data in the obstacle detection process indicating that there is a transparent obstacle around the robot; the first motion instruction is configured to instruct the robot to move to one side of the transparent obstacle;
[0115] A second generating module 730 is used to generate a second motion instruction in response to the robot reaching one side of the transparent obstacle; the second motion instruction is used to instruct the robot to move from one side of the transparent obstacle to the other side;
[0116] The determination module 740 is used to obtain environmental data of a contour acquisition process during the movement process based on the second motion instruction, and determine contour information of the transparent obstacle based on the environmental data of the contour acquisition process.
[0117] In some embodiments, the second generation module 730 is further used to: generate the second motion instruction in response to the robot reaching a first position; wherein the first position is located on one side of the transparent obstacle, and the environmental data obtained at the first position indicates that there is no transparent obstacle around the robot.
[0118] In some embodiments, the second generation module 730 is further used to: collect environmental data of the first movement process when the robot moves toward one side of the transparent obstacle in response to the first motion instruction; and determine that the robot has reached the first position when the environmental data of the first movement process indicates that there are no transparent obstacles around the robot.
[0119] In some embodiments, the first motion instruction is used to instruct the robot to move along a first direction toward one side of the transparent obstacle; the first direction is not parallel to the receiving direction of the ultrasonic data, and the angle between the first direction and the receiving direction of the ultrasonic data is related to the obstacle distance; the obstacle distance is the distance between the robot and the transparent obstacle determined based on the ultrasonic data.
[0120] In some embodiments, the determination module 740 is also used to: in response to the environmental data in the contour acquisition process characterizing the presence of a transparent obstacle around the robot, determine the set of position points of the transparent obstacle in the world coordinate system based on the ultrasonic detection direction, the obstacle distance between the robot and the transparent obstacle detected by the ultrasonic wave, and the position of the robot in the world coordinate system; based on the set of position points, determine the contour information of the transparent obstacle.
[0121] In some embodiments, the determination module 740 is also used to: in the movement process based on the second motion instruction, in response to the environmental data in the contour acquisition process characterizing that the robot moves from a position where there are transparent obstacles around it to a position where there are no transparent obstacles, determine the contour information of the transparent obstacle based on the set of position points.
[0122] In some embodiments, the environment map is a grid map, and the contour information includes grids in the grid map where transparent obstacles exist; the determination module 740 is also used to: determine the grids in the grid map where transparent obstacles exist based on the position coordinates of each position point in the position point set in the world coordinate system and the range information of each grid in the grid map.
[0123] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided in the embodiment of the present application can be used to execute the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.
[0124] It should be noted that in the embodiment of the present application, if the above-mentioned contour detection method of transparent obstacles is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a robot (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific hardware, software or firmware, or any combination of hardware, software, and firmware.
[0125] An embodiment of the present application provides a robot, including a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.
[0126] The embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented. The computer-readable storage medium can be transient or non-transient.
[0127] An embodiment of the present application provides a computer program, including a computer-readable code. When the computer-readable code runs in a robot, a processor in the robot executes some or all of the steps for implementing the above method.
[0128] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.
[0129] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiments of the device, storage medium, computer program and computer program product of this application, please refer to the description of the method embodiment of this application for understanding.
[0130] Figure 8 A schematic diagram of a hardware entity of a robot provided in an embodiment of the present application, such as Figure 8 As shown, the hardware entity of the robot 800 includes: a processor 801 and a memory 802, wherein the memory 802 stores a computer program that can be run on the processor 801, and the processor 801 implements the steps in the method of any of the above embodiments when executing the program.
[0131] The memory 802 stores a computer program that can be run on the processor. The memory 802 is configured to store instructions and applications executable by the processor 801. It can also cache data to be processed or processed by the processor 801 and various modules in the robot 800 (for example, image data, audio data, voice communication data, and video communication data). This can be achieved through flash memory (FLASH) or random access memory (Random Access Memory, RAM).
[0132] When the processor 801 executes the program, the steps of any of the above-mentioned methods for detecting the outline of a transparent obstacle are implemented. The processor 801 generally controls the overall operation of the robot 800 .
[0133] An embodiment of the present application provides a computer storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the steps of the method for detecting the contour of a transparent obstacle in any of the above embodiments.
[0134] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.
[0135] The processor may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understandable that the electronic device that implements the functions of the processor may also be other, and the embodiments of the present application are not specifically limited.
[0136] The above-mentioned computer storage medium / memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM) and the like; it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.
[0137] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.
[0138] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0139] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0140] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0141] In addition, all functional units in the embodiments of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units. A person of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by hardware related to program instructions, and the above program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above method embodiments are executed; and the above storage medium includes: mobile storage devices, read-only memory (ROM), disks or optical disks, etc. Various media that can store program codes.
[0142] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a robot (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.
[0143] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A method for detecting the contour of a transparent obstacle, characterized in that: The method comprises: Acquire environmental data during obstacle detection while generating an environmental map through simultaneous localization and mapping solutions; In response to the environmental data in the obstacle detection process indicating that there is a transparent obstacle around the robot, a first motion instruction is generated; the first motion instruction is used to instruct the robot to move to one side of the transparent obstacle; In response to the robot reaching one side of the transparent obstacle, generating a second motion instruction; the second motion instruction is used to instruct the robot to move from one side of the transparent obstacle to the other side; During the movement process based on the second motion instruction, environmental data of a contour acquisition process is acquired, and contour information of the transparent obstacle is determined based on the environmental data of the contour acquisition process.
2. The method according to claim 1, characterized in that In response to the robot reaching one side of the transparent obstacle, generating a second motion instruction comprises: generating the second motion instruction in response to the robot reaching the first position; The first position is located on one side of the transparent obstacle, and the environmental data acquired at the first position indicates that there is no transparent obstacle around the robot.
3. The method according to claim 2, characterized in that The method further comprises: When the robot moves toward one side of the transparent obstacle in response to the first motion instruction, collecting environmental data of the first movement process; When the environmental data of the first movement process indicates that there are no transparent obstacles around the robot, it is determined that the robot has reached the first position.
4. The method according to any one of claims 1 to 3, characterized in that: The first motion instruction is used to instruct the robot to move along a first direction toward one side of the transparent obstacle; the first direction is not parallel to the receiving direction of the ultrasonic data, and the angle between the first direction and the receiving direction of the ultrasonic data is related to the obstacle distance; the obstacle distance is the distance between the robot and the transparent obstacle determined based on the ultrasonic data.
5. The method according to any one of claims 1 to 4, characterized in that: The determining of the contour information of the transparent obstacle based on the environmental data of the contour acquisition process includes: In response to the environmental data in the contour acquisition process indicating that there is a transparent obstacle around the robot, a set of position points of the transparent obstacle in the world coordinate system is determined based on the ultrasonic detection direction, the obstacle distance between the robot and the transparent obstacle detected by the ultrasonic wave, and the position and posture of the robot in the world coordinate system; Based on the set of position points, contour information of the transparent obstacle is determined.
6. The method according to claim 5, characterized in that The determining, based on the set of position points, contour information of the transparent obstacle includes: During the movement process based on the second motion instruction, in response to the environmental data during the contour acquisition process characterizing that the robot moves from a position where transparent obstacles exist around it to a position where no transparent obstacles exist, contour information of the transparent obstacles is determined based on the set of position points.
7. The method according to claim 5, characterized in that The environment map is a grid map, and the contour information includes grids where transparent obstacles exist in the grid map; and determining the contour information of the transparent obstacles based on the set of position points includes: According to the position coordinates of each position point in the position point set in the world coordinate system and the range information of each grid in the grid map, the grids in the grid map where transparent obstacles exist are determined.
8. A device for detecting the contour of a transparent obstacle, characterized in that: The device comprises: An acquisition module, used to acquire environmental data during obstacle detection in the process of generating an environmental map through a simultaneous localization and mapping solution; A first generating module is used to generate a first motion instruction in response to the environmental data in the obstacle detection process indicating that there is a transparent obstacle around the robot; the first motion instruction is used to instruct the robot to move to one side of the transparent obstacle; a second generating module, configured to generate a second motion instruction in response to the robot reaching one side of the transparent obstacle; the second motion instruction is used to instruct the robot to move from one side of the transparent obstacle to the other side; The determination module is used to obtain environmental data of a contour acquisition process during the movement process based on the second motion instruction, and determine the contour information of the transparent obstacle based on the environmental data of the contour acquisition process.
9. A robot comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the program, the steps in the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Contour detection of transparent obstacle
WO2026046170A1
