Terrain perception system and quadruped robot

Abstract

The application discloses a terrain perception system and a quadruped robot, and relates to the technical field of artificial intelligence, wherein a force sensor is added to the foot end of a bionic leg-foot type robot to obtain the hardness of the terrain, so that the perceived terrain information is enriched, and the reliability of the passability judgment of the bionic leg-foot type robot is enhanced. The friction between the foot end and the ground is calculated by measuring the output current size of the joint motor driver of the bionic leg-foot type robot through the added electric quantity sensor, so that the relationship information between the perceived terrain and the bionic leg-foot type robot is enriched, which is helpful for the passability judgment of the bionic leg-foot type robot on snow, slopes, wet and slippery road surfaces and the like. The height, width and distance between the bionic leg-foot type robot of an obstacle are measured through the added sound detection sensor and millimeter wave radar, and the reliability of the measured data of the visual perception method is increased.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a terrain perception system and a quadruped robot. BACKGROUND

[0002] When animals walk on the ground, avoid obstacles and climb cliffs, they mainly rely on the terrain and topography obtained by the visual system. The terrain perception method of civilian unmanned vehicles is mainly based on precise maps, visible light, laser radar, inertial measurement units, odometers, GPS and other sensors to obtain terrain information to realize autonomous navigation and dynamic obstacle avoidance.

[0003] The stereo camera is used to obtain the geometric information and image appearance information of the terrain, and they are used to establish a remote visible map and analyze the passability of the terrain. The geometric information of the terrain is extracted based on point cloud data to evaluate the plane, and the SVM classifier is trained using picture color and texture information to classify the terrain. A possibility evaluation function is proposed to reduce the influence of false classification on terrain passability analysis. The plane evaluation and SVM classification results are combined to analyze the near-distance passability, and are used as a reference for remote terrain passability evaluation, and finally the passability map of the terrain is obtained.

[0004] The terrain perception method based on three-dimensional point cloud data in the form of DEM presents a terrain passability calculation function, which combines the motion characteristics of the robot itself and the geometric characteristics of the terrain to calculate the passability of the terrain.

[0005] However, quadruped robots face complex terrains other than normal roads, including stairs, plum-blossom stake terrains, rubble, muddy ground and other complex terrains, which require higher precision of terrain information. Currently, the SLAM environment perception technology based on vision / laser radar is mainly used to realize the perception and autonomous obstacle avoidance of extreme rough and steep terrain environments, but this method cannot perceive the hardness of the terrain, and cannot accurately perceive the distance, height and other information of the obstacles.

[0006] It can be seen that the terrain perception method based on visible light is easily invalidated under light, affecting the walking of the quadruped robot; the terrain perception method based on laser radar cannot perceive the color information of the environment, and it is difficult to distinguish grass, snow and land; the SLAM environment perception method based on vision / laser radar cannot perceive the hardness and friction of the terrain, affecting the judgment of the passability of the quadruped robot. SUMMARY

[0007] In view of the above problems, the present application provides a terrain perception system and a quadruped robot for overcoming the above problems or at least partially solving the above problems. The system realizes accurate perception of the terrain of the quadruped robot by adding millimeter wave radar, force sensors, power sensors, acoustic detection sensors and the like.

[0008] The application provides the following solutions:

[0009] A terrain perception system comprises:

[0010] at least a laser range finder, a millimeter wave radar, a microphone array, a force sensor and an electric quantity sensor, all of which are connected to a bionic leg-foot robot;

[0011] The laser range finder is used to measure the distance between an obstacle and the bionic leg-foot robot;

[0012] The microphone array and the millimeter wave radar are respectively used to calculate the distance between an obstacle and the bionic leg-foot robot and the width, height and position information of the obstacle through the reflection of sound waves and microwaves on the surface of the obstacle;

[0013] The force sensor is used to obtain the hardness information of the terrain through the foot end of the bionic leg-foot robot;

[0014] The electric quantity sensor is used to measure the size of the output current of the leg joint motor driver of the bionic leg-foot robot so as to calculate the friction force between the foot end and the ground.

[0015] Preferably, the force sensor is arranged at the foot end of the bionic leg-foot robot.

[0016] Preferably, a visible light module, a laser radar and a navigation positioning module are further connected to the bionic leg-foot robot;

[0017] The visible light module is used to perceive the color information of the environment;

[0018] The laser radar is used to perceive the basic situation of the terrain;

[0019] The navigation positioning module is used to realize the autonomous navigation and dynamic obstacle avoidance of the bionic leg-foot robot.

[0020] Preferably, the navigation positioning module comprises a Beidou module, an inertial measurement unit and an odometer.

[0021] The Beidou module is used to measure or calibrate the positions of the bionic leg-foot robot, an obstacle and a reference object;

[0022] The inertial measurement unit is used to measure the acceleration of the bionic leg-foot robot in a limited environment and calculate the speed, position and attitude information of the bionic leg-foot robot;

[0023] The odometer is used to measure the driving distance of the bionic leg-foot robot in a limited environment.

[0024] Preferably: further comprising a control terminal and a perception processing module in communication, the perception processing module is in communication with the laser range finder, the millimeter wave radar, the microphone array, the force sensor and the electric quantity sensor through an Ethernet bus;

[0025] The perception processing module is used for processing the received corresponding sensor information, and feeding back the data processing result and the state information of each device to the control terminal through the team ad hoc network measurement and control link.

[0026] Preferably: the processing method of the perception processing module on the sensor information comprises:

[0027] Visible light day and night perception is performed during travel, and after it is determined that it is night, terrain perception is performed through the laser radar during travel, and after it is determined that it is not night, terrain perception is performed through the visible light module during travel;

[0028] Whether there is an obstacle is determined through the terrain perception;

[0029] After it is determined that there is an obstacle, the distance of the obstacle is measured through the laser range finder, and the size of the obstacle is measured through the millimeter wave radar and the microphone array, so as to generate an avoidance strategy according to the distance of the obstacle and the size of the obstacle;

[0030] Whether it is a soft road surface is determined through the force sensor during travel;

[0031] After it is determined that it is not a soft road surface, whether it is a wet and slippery road surface is determined through the electric quantity sensor during travel;

[0032] After it is determined that it is a wet and slippery road surface or a soft road surface, whether it can pass through is evaluated and determined;

[0033] After it is determined that it is not a wet and slippery road surface or can pass through, the robot is controlled to travel normally;

[0034] After it is determined that it cannot pass through, the robot is controlled to travel normally after the avoidance strategy is adjusted.

[0035] Preferably: the generated semantic map and the adjusted avoidance strategy are sent to the control terminal.

[0036] A quadruped robot comprising the terrain perception system described above.

[0037] According to the specific embodiments of the present application, the following technical effects are provided:

[0038] The terrain perception system and the quadruped robot provided by the embodiment of the application enrich the perceived terrain information and enhance the reliability of the passability judgment of the bionic leg-foot type robot by adding force sensors at the foot end of the bionic leg-foot type robot to obtain the hardness of the terrain. The relationship information between the perceived terrain and the bionic leg-foot type robot is enriched by adding the electric quantity sensor to measure the output current of the joint motor driver of the bionic leg-foot type robot to calculate the friction between the foot end and the ground, which is helpful for the passability judgment of the bionic leg-foot type robot on snow, slopes, wet and slippery road surfaces and the like. The reliability of the measured data is increased by adding the sound detection sensor and the millimeter wave radar to measure the height, width and distance between the bionic leg-foot type robot of the obstacle, and the visual perception method.

[0039] Of course, implementing any product of the application does not necessarily require all the advantages described above to be achieved at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description only constitute some embodiments of the application, and other drawings can also be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0041] Figure 1 is a structural schematic diagram of a terrain perception system provided by the embodiment of the application;

[0042] Figure 2 is a module connection relationship diagram of a terrain perception system provided by the embodiment of the application;

[0043] Figure 3 is a control flowchart provided by the embodiment of the application.

[0044] In the figure: millimeter wave radar 1, microphone array 2, force sensor 3, electric quantity sensor 4, visible light module 5, laser radar 6, navigation positioning module 7, bionic leg-foot type robot 8. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the application will be described clearly and completely in combination with the drawings in the embodiments of the application. Obviously, the described embodiments only constitute some of the embodiments of the application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the application belong to the scope of protection of the application.

[0046] Referring to Figure 1 , a terrain perception system provided by the embodiment of the application, as Figure 1 shown, the system can include:

[0047] a laser range finder, a millimeter wave radar 1, a microphone array 2, a force sensor 3 and a power sensor 4 connected with the bionic leg-foot robot 8;

[0048] The laser range finder is used to measure the distance between the obstacle and the bionic leg-foot robot 8.

[0049] The microphone array 2 and the millimeter wave radar 1 are respectively used to calculate the distance between the obstacle and the bionic leg-foot robot 8 and the width, height and position information of the obstacle through the reflection of sound waves and microwaves on the surface of the obstacle.

[0050] The force sensor 3 is used to obtain the hardness information of the terrain through the foot end of the bionic leg-foot robot 8. In the specific implementation, the force sensor 3 can be arranged at the foot end of the bionic leg-foot robot 8.

[0051] The power sensor 4 is used to measure the output current of the joint motor driver of the leg of the bionic leg-foot robot 8, so as to calculate the friction force between the foot end and the ground.

[0052] The terrain perception system provided by the embodiment of the present application obtains the hardness of the terrain through the force sensor 3 arranged at the foot end of the bionic leg-foot robot 8; measures the friction force between the foot end and the ground by measuring the output current of the joint motor driver of the bionic leg-foot robot 8 through the power sensor 4; and increases the reliability of the visual measurement data by measuring the height, width and distance between the obstacle and the bionic leg-foot robot 8 through the sound detection sensor and the millimeter wave radar 1.

[0053] In order to further enrich the comprehensive perception of the system provided by the present application, the embodiment of the present application can further provide a visible light module 5, a laser radar 6 and a navigation positioning module 7 connected with the bionic leg-foot robot 8.

[0054] The visible light module 5 is used to perceive the color information of the environment.

[0055] The laser radar 6 is used to perceive the basic situation of the terrain.

[0056] The navigation positioning module 7 is used to realize the autonomous navigation and dynamic obstacle avoidance of the bionic leg-foot robot 8.

[0057] Further, the navigation positioning module 7 includes a Beidou module, an inertial measurement unit and an odometer.

[0058] The Beidou module is used to measure or calibrate the positions of the bionic leg-foot robot 8, the obstacle and the reference object.

[0059] The inertial measurement unit is used to measure the acceleration of the bionic leg-foot robot 8 in a restricted environment, and calculate the speed, position, and attitude information of the bionic leg-foot robot 8.

[0060] The odometer is used to measure the travel mileage of the bionic leg-foot robot 8 in a restricted environment.

[0061] The system provided by the embodiments of the present application can be applied to various bionic leg-foot robots 8, for example, the bionic leg-foot robot 8 can be a quadruped robot.

[0062] Next, taking the case that the system is mounted on a quadruped robot as an example, the system is described in detail as shown in the following figure. Figure 2

[0063] The system provided by the embodiments of the present application can be composed of a visible light module 5, a laser radar 6, a navigation positioning module 7 (Beidou module, inertial measurement unit, odometer), laser range finder, millimeter wave radar 1, microphone array 2, force sensor 3, and power sensor 4, which are all mounted on a quadruped robot.

[0064] The laser radar 6 can reliably perceive the terrain without being affected by light, shadow, and other environments.

[0065] The visible light module 5 is prone to failure in light, shadow, and other environments, has few feature points, but can perceive color information of the environment.

[0066] The Beidou module measures or calibrates the positions of the quadruped robot, obstacles, and reference objects.

[0067] The inertial measurement unit measures the acceleration of the quadruped robot in a restricted environment, thereby calculating the speed, position, and attitude information.

[0068] The odometer measures the travel mileage of the quadruped robot in a restricted environment.

[0069] The laser range finder measures the distance between the obstacle and the quadruped robot.

[0070] The microphone array 2 and the millimeter wave radar 1 calculate the distance between the obstacle and the quadruped robot, the width, height, and position of the obstacle, and other information through the reflection of sound waves and microwaves on the surface of the obstacle, respectively.

[0071] The force sensor 3 obtains the hardness of the terrain by adding a force sensor 3 at the foot end of the quadruped robot.

[0072] The power sensor 4 measures the friction between the foot end and the ground by measuring the output current of the joint motor driver of the quadruped robot.

[0073] ​It can be seen that the system realizes the multi-element fusion of navigation data, image data, sound data, force measurement data, current data and the like through the fusion of the terrain perception device, and can realize the accurate perception of the softness and hardness of the terrain, the type characteristics of the geology, the size of the obstacles and the discrete point-like terrain.

[0074] The quadruped robot adopts the terrain perception device composed of various types of sensors to collect various types of perception result data and send the data to the perception processing module through an Ethernet bus. The corresponding sensor information is received by each perception processing module and corresponding processing is performed. The data processing result and the state information of each device are fed back to the control terminal through the team ad hoc network measurement and control link.

[0075] The quadruped robot receives the motion control instruction from the control terminal, and sends its own state to the comprehensive control module periodically, and finally to the control terminal. The control terminal monitors the state information of the quadruped robot in real time and performs real-time control.

[0076] As shown in Figure 3 The control terminal and the perception processing module can be communicatively connected. The perception processing module is communicatively connected with the laser range finder, the millimeter wave radar, the microphone array, the force sensor and the power sensor through the Ethernet bus.

[0077] The perception processing module is configured to perform corresponding processing on the received corresponding sensor information, and feed back the data processing result and the state information of each device to the control terminal through the team ad hoc network measurement and control link.

[0078] The processing method of the sensor information by the perception processing module includes:

[0079] Visible light day and night perception is performed during the travel. After it is determined that it is night, terrain perception is performed through the laser radar during the travel. After it is determined that it is not night, terrain perception is performed through the visible light module during the travel.

[0080] It is determined whether there is an obstacle through the terrain perception.

[0081] After it is determined that there is an obstacle, the distance of the obstacle is measured through the laser range finder, and the size of the obstacle is measured through the millimeter wave radar and the microphone array, so as to generate an avoidance strategy according to the distance of the obstacle and the size of the obstacle.

[0082] It is determined whether it is a soft road surface through the force sensor during the travel.

[0083] After it is determined that it is not a soft road surface, it is determined whether it is a wet and slippery road surface through the power sensor during the travel.

[0084] determining whether the robot can pass through the terrain based on the passability of the terrain;

[0085] determining whether the robot can pass through the terrain based on the passability of the terrain;

[0086] determining whether the robot can pass through the terrain based on the passability of the terrain;

[0087] In summary, the terrain perception system provided in the present application enriches the sensed terrain information and enhances the reliability of the passability judgment of the bionic leg-foot robot by adding force sensors at the foot ends of the bionic leg-foot robot to obtain the hardness of the terrain. The relationship information between the sensed terrain and the bionic leg-foot robot is enriched by adding an electric quantity sensor to measure the friction force between the foot end and the ground by measuring the output current of the joint motor driver of the bionic leg-foot robot, which is helpful for the passability judgment of the bionic leg-foot robot in snow, slopes, wet road surfaces, etc. The reliability of the measured data is increased by adding an acoustic detection sensor and a millimeter wave radar to measure the height, width and distance between the bionic leg-foot robot and the obstacle, and increasing the visual perception method.

[0088] Further, the generated semantic map and the adjusted avoidance strategy are sent to a control terminal.

[0089] The embodiments of the present application can also provide a quadruped robot comprising the terrain perception system described above.

[0090] It should be noted that, in the present document, the relationship terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0091] Those skilled in the art can clearly understand the application by the description of the above embodiments. The technical solutions of the application can be implemented by means of software plus necessary universal hardware platforms. Based on such an understanding, the technical solutions of the application can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, or an optical disk, and includes a plurality of instructions to cause a computer device (such as a personal computer, a server, or a network device) to execute the methods described in various embodiments or some parts of the embodiments.

[0092] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts of each of the embodiments can be referred to each other. Each of the embodiments mainly describes the difference from other embodiments. In particular, for the system or the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts can be referred to the part of the method embodiment. The system and the system embodiment described above are merely illustrative, and the units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the embodiment. Those skilled in the art can understand and implement without creative labor.

[0093] The above only describes the preferred embodiments of the application, and is not used to limit the protection scope of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application is included in the protection scope of the application.

Claims

1. A terrain perception system, characterized by, At least including laser range finder, millimeter wave radar, microphone array, force sensor and electric quantity sensor connected with the bionic leg-foot robot; The laser range finder is used for measuring the distance between the obstacle and the bionic leg-foot robot; The microphone array and the millimeter wave radar are respectively used for calculating the distance between the obstacle and the bionic leg-foot robot, the width, height and position information of the obstacle through the reflection of sound waves and microwaves on the surface of the obstacle; The force sensor is used for obtaining the hardness information of the terrain through the foot end of the bionic leg-foot robot; The electric quantity sensor is used for measuring the output current of the leg joint motor driver of the bionic leg-foot robot so as to calculate the friction force between the foot end and the ground; Further including visible light module, laser radar and navigation positioning module connected with the bionic leg-foot robot; The visible light module is used for sensing the color information of the environment; The laser radar is used for sensing the basic situation of the terrain; The navigation positioning module is used for realizing the autonomous navigation and dynamic obstacle avoidance of the bionic leg-foot robot; Further including control terminal and sensing processing module connected in communication, the sensing processing module is connected with the laser range finder, the millimeter wave radar, the microphone array, the force sensor and the electric quantity sensor in communication through the Ethernet bus; The sensing processing module is used for processing the received corresponding sensor information, and feeding back the data processing result and the state information of each device to the control terminal through the team ad hoc network measurement and control link; The processing method of the sensing processing module on the sensor information includes: Performing visible light day and night sensing during walking, performing terrain sensing through the laser radar during walking after determining that it is night, and performing terrain sensing through the visible light module during walking after determining that it is not night; Judging whether there is an obstacle through the terrain sensing; Measuring the distance of the obstacle through the laser range finder after determining that there is an obstacle, and measuring the size of the obstacle through the millimeter wave radar and the microphone array, so as to generate an avoidance strategy according to the distance of the obstacle and the size of the obstacle; Judging whether it is soft road surface through the force sensor during walking; Judging whether it is wet and slippery road surface through the electric quantity sensor during walking after determining that it is not soft road surface; Evaluating the passability and judging whether it can be passed after determining that it is wet and slippery road surface or soft road surface; Controlling the robot to walk normally after determining that it is not wet and slippery road surface or can be passed; Controlling the robot to walk normally after adjusting the avoidance strategy after determining that it cannot be passed.

2. The terrain awareness system of claim 1, wherein, The force sensor is arranged at the foot end of the bionic leg-foot robot.

3. The terrain awareness system of claim 1, wherein, The navigation positioning module includes Beidou module, inertial measurement unit and odometer; The Beidou module is used for measuring or calibrating the position of the bionic leg-foot robot, obstacle and reference object; The inertial measurement unit is used for measuring the acceleration of the bionic leg-foot robot in a limited environment, and calculating the speed, position and attitude information of the bionic leg-foot robot; The odometer is used for measuring the driving mileage of the bionic leg-foot robot in a limited environment.

4. The terrain awareness system of claim 1, wherein, The generated semantic map and the adjusted avoidance strategy are sent to the control terminal.

5. A quadruped robot, characterized by, The terrain awareness system of any one of claims 1 to 4.

Images