Terrain sensing system and quadruped robot

Abstract

The invention discloses a terrain sensing system and a quadruped robot, relates to the technical field of artificial intelligence, and enriches sensed terrain information and enhances the reliability of trafficability judgment of a bionic leg-foot type robot by adding a force sensor at the foot end of the bionic leg-foot type robot to obtain the hardness of the terrain. The electric quantity sensor is additionally arranged to measure the magnitude of the output current of the joint motor driver of the bionic leg-foot type robot and calculate the friction force between the foot end and the ground, the relation information between the sensed terrain and the bionic leg-foot type robot is enriched, and the trafficability judgment of the bionic leg-foot type robot on snowfields, slopes, wet and slippery road surfaces and the like is facilitated. The height and the width of an obstacle and the distance between the obstacle and the bionic leg-foot type robot are measured by additionally arranging a sound detection sensor and a millimeter wave radar, and the reliability of data measured by a visual perception method is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a terrain perception system and a quadruped robot. Background Art

[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 accurate maps, visible light, lidar, inertial measurement unit, odometer, GPS and other sensors to obtain terrain information to achieve autonomous navigation and dynamic obstacle avoidance.

[0003] Stereo cameras are used to obtain the geometric information and image appearance information of the terrain, which are then used to build a remote visual map and analyze the accessibility of the terrain. The geometric information of the terrain is extracted based on point cloud data for plane evaluation, and the SVM classifier is trained using image color and texture information to classify the terrain. A possibility evaluation function is proposed to reduce the impact of misclassification on terrain accessibility analysis. The plane evaluation is combined with the SVM classification results for close-range accessibility analysis, and used as a reference for long-range terrain accessibility evaluation, and finally a terrain accessibility polar map is obtained.

[0004] A terrain perception method based on three-dimensional point cloud data presented in the form of DEM is used to design a terrain accessibility calculation function, which combines the robot's own motion characteristics and the geometric characteristics of the terrain to calculate the terrain accessibility.

[0005] Quadruped robots face complex terrains other than normal roads, including stairs, plum blossom pile terrain, rocky areas, muddy areas, and other complex terrains, which require higher precision of terrain information. Currently, they mainly rely on SLAM environmental perception technology based on vision / lidar to achieve perception and autonomous obstacle avoidance of extremely rough and steep terrain environments. However, this method cannot perceive the hardness of the terrain, and cannot accurately perceive the distance and height of obstacles.

[0006] It can be seen that the terrain perception method based on visible light is prone to fail under light, affecting the walking of the quadruped robot; the terrain perception method based on lidar cannot perceive the color information of the environment and is difficult to distinguish between grass, snow, land, etc.; the SLAM environment perception method based on vision / lidar cannot perceive the hardness of the terrain, the size of friction and other information, which affects the judgment of the passability of the quadruped robot. Summary of the invention

[0007] In view of the above problems, the present invention provides a terrain perception system and a quadruped robot for overcoming the above problems or at least partially solving the above problems. The system enables the quadruped robot to accurately perceive the terrain by adding millimeter wave radar, force sensor, power sensor, acoustic detection sensor, etc.

[0008] The present invention provides the following scheme:

[0009] A terrain perception system, comprising:

[0010] At least including a laser rangefinder, a millimeter wave radar, a microphone array, a force sensor, and a power sensor, all of which are connected to the bionic leg-foot robot;

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

[0012] The microphone array and the millimeter wave radar are used to calculate the distance between the 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 respectively;

[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 electrical quantity sensor is used to measure the magnitude of the output current of the motor driver of the leg joint 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: it also includes a visible light module, a laser radar, and a navigation and positioning module connected to the bionic leg-foot robot;

[0017] The visible light module is used to perceive environmental color information;

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

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

[0020] Preferably: the navigation and positioning module includes 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, obstacles, and reference objects;

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

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

[0024] Preferably: it also includes a control terminal and a perception processing module that are communicably connected, and the perception processing module is communicably connected with the laser rangefinder, the millimeter wave radar, the microphone array, the force sensor, and the power sensor through an Ethernet bus;

[0025] The perception processing module is used to process the corresponding sensor information received, and feed back the data processing results and the status information of each device to the control terminal through the team self-organizing network measurement and control link.

[0026] Preferably: the method for processing sensor information by the perception processing module includes:

[0027] Perform visible light day and night perception while traveling, and after determining that it is night time, perform terrain perception through the laser radar while traveling, and after determining that it is not night time, perform terrain perception through the visible light module while traveling;

[0028] Determining whether there are obstacles through the terrain perception;

[0029] After determining that there is an obstacle, the obstacle distance is measured by the laser rangefinder, and the obstacle size is measured by the millimeter wave radar and the microphone array, so as to generate an avoidance strategy according to the obstacle distance and the obstacle size;

[0030] During driving, the force sensor is used to determine whether the road surface is soft;

[0031] Determining that the road is not soft, and determining whether the road is slippery by using the power sensor during driving;

[0032] Determine whether the road surface is slippery or soft and evaluate the passability to determine whether it is passable;

[0033] If it is determined that the road surface is not slippery or passable, the robot is controlled to move normally;

[0034] If it is determined that the robot cannot pass through, the avoidance strategy is adjusted to control the robot to move normally.

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

[0036] A quadruped robot comprises the above-mentioned terrain perception system.

[0037] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0038] The terrain perception system and quadruped robot provided in the embodiments of the present application enrich the perceived terrain information and enhance the reliability of the passability judgment of the bionic leg-legged robot by adding a force sensor to the foot end of the bionic leg-legged robot to obtain the hardness of the terrain. By adding a power sensor to measure the output current of the bionic leg-legged robot joint motor driver to calculate the friction between the foot end and the ground, the relationship information between the perceived terrain and the bionic leg-legged robot is enriched, which helps the bionic leg-legged robot to judge the passability on snow, slopes, slippery roads, etc. By adding an acoustic detection sensor and a millimeter-wave radar to measure the height, width, and distance between the obstacle and the bionic leg-legged robot, the reliability of the data measured by the visual perception method is increased.

[0039] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

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

[0042] Figure 2 It is a connection relationship diagram of modules of a terrain perception system provided by an embodiment of the present invention;

[0043] Figure 3 It is a control flow chart provided by an embodiment of the present invention.

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

[0045] The technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0046] See also Figure 1 , is a terrain perception system provided by an embodiment of the present invention, such as Figure 1 As shown, the system may include:

[0047] A laser rangefinder, a millimeter wave radar 1, a microphone array 2, a force sensor 3 and a power sensor 4, all of which are connected to the bionic leg-foot robot 8;

[0048] The laser rangefinder 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 used to calculate the distance between the obstacle and the bionic legged 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 respectively;

[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 specific implementation, the embodiment of the present application can provide that the force sensor 3 is 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 leg joint motor driver of the bionic leg-foot robot 8 so as to calculate the friction between the foot end and the ground.

[0052] The terrain perception system provided in the embodiment of the present application obtains the hardness of the terrain by adding a force sensor 3 to the foot end of the bionic leg-leg robot 8; measures the output current of the joint motor driver of the bionic leg-leg robot 8 by adding a power sensor 4 to calculate the friction between the foot end and the ground; and measures the height, width, and distance of the obstacle from the bionic leg-leg robot 8 by adding an acoustic detection sensor and a millimeter-wave radar 1 to increase the reliability of visual measurement data.

[0053] In order to further enrich the comprehensiveness of the perception of the system provided by the present application, the embodiment of the present application may also provide a visible light module 5, a laser radar 6, and a navigation and positioning module 7 connected to the bionic legged robot 8;

[0054] The visible light module 5 is used to sense environmental color information;

[0055] The laser radar 6 is used to sense the basic conditions of the terrain;

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

[0057] Furthermore, the navigation and 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 legged robot 8, obstacles, and reference objects;

[0059] The inertial measurement unit is used to measure the acceleration of the bionic legged robot 8 in a restricted environment, and calculate the speed, position, and posture information of the bionic legged robot 8;

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

[0061] The system provided in the embodiment of the present application can be applied to a variety of bionic legged and footed robots 8. For example, the bionic legged and footed robot 8 can be a quadruped robot.

[0062] The following takes the system mounted on a quadruped robot as an example. Figure 2 The system is described in detail.

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

[0064] LiDAR 6: Not affected by lighting, shadows and other environmental factors, and can reliably sense terrain;

[0065] Visible light module 5: It is easy to fail in environments such as light and shadow, has few feature points, but can perceive environmental color information;

[0066] Beidou module: measures or calibrates the position of quadruped robots, obstacles, reference objects, etc.;

[0067] Inertial measurement unit: measures the acceleration of the quadruped robot in a constrained environment, thereby calculating information such as speed, position, and posture;

[0068] Odometry: measuring the mileage of a quadruped robot in a constrained environment;

[0069] Laser rangefinder: measures the distance between obstacles and the quadruped robot;

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

[0071] Force sensor 3: The hardness of the terrain is obtained by adding force sensor 3 at the foot end of the quadruped robot;

[0072] Power sensor 4: By adding power sensor 4 to measure the output current of the quadruped robot joint motor driver, the friction between the foot end and the ground is calculated.

[0073] It can be seen that the system realizes the multi-dimensional fusion of navigation data, image data, sound data, force measurement data, current data, etc. through the integration of terrain sensing devices, and can realize accurate perception of the hardness of the terrain, the type and characteristics of the geology, the size of obstacles, and discrete point terrain.

[0074] The quadruped robot uses a terrain perception device composed of multiple types of sensors to collect various types of perception result data and send them to the perception processing module through the Ethernet bus. Each perception processing module receives the corresponding sensor information and performs corresponding processing. The data processing results and the status information of each device are fed back to the control terminal through the team self-organizing network measurement and control link;

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

[0076] When implementing it specifically, Figure 3 As shown, the embodiment of the present application may also provide a control terminal and a perception processing module that are communicably connected, and the perception processing module is communicably connected to the laser rangefinder, the millimeter wave radar, the microphone array, the force sensor, and the power sensor through an Ethernet bus;

[0077] The perception processing module is used to process the corresponding sensor information received, and feed back the data processing results and the status information of each device to the control terminal through the team self-organizing network measurement and control link.

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

[0079] Perform visible light day and night perception while traveling, and after determining that it is night time, perform terrain perception through the laser radar while traveling, and after determining that it is not night time, perform terrain perception through the visible light module while traveling;

[0080] Determining whether there are obstacles through the terrain perception;

[0081] After determining that there is an obstacle, the obstacle distance is measured by the laser rangefinder, and the obstacle size is measured by the millimeter wave radar and the microphone array, so as to generate an avoidance strategy according to the obstacle distance and the obstacle size;

[0082] During driving, the force sensor is used to determine whether the road surface is soft;

[0083] Determining that the road is not soft, and determining whether the road is slippery by using the power sensor during driving;

[0084] Determine whether the road surface is slippery or soft and evaluate the passability to determine whether it is passable;

[0085] If it is determined that the road surface is not slippery or passable, the robot is controlled to move normally;

[0086] If it is determined that the robot cannot pass through, the avoidance strategy is adjusted to control the robot to move normally.

[0087] In summary, the terrain perception system provided by the present application enriches the perceived terrain information and enhances the reliability of the bionic leg-leg robot's passability judgment by adding a force sensor to the foot end of the bionic leg-leg robot to obtain the hardness of the terrain. By adding a power sensor to measure the output current of the bionic leg-leg robot's joint motor driver to calculate the friction between the foot end and the ground, the relationship information between the perceived terrain and the bionic leg-leg robot is enriched, which helps the bionic leg-leg robot to judge its passability on snow, slopes, slippery roads, etc. By adding an acoustic detection sensor and a millimeter-wave radar to measure the height, width, and distance between the obstacle and the bionic leg-leg robot, the reliability of the data measured by the visual perception method is increased.

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

[0089] The embodiment of the present application may also provide a quadruped robot, comprising the above-mentioned terrain perception system.

[0090] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" 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 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, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0091] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0092] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A terrain perception system, characterized in that: At least including a laser rangefinder, a millimeter wave radar, a microphone array, a force sensor, and a power sensor, all of which are connected to the bionic leg-foot robot; The laser rangefinder is used to measure the distance between the obstacle and the bionic leg-foot robot; The microphone array and the millimeter wave radar are used to calculate the distance between the 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 respectively; The force sensor is used to obtain the hardness information of the terrain through the foot end of the bionic leg-foot robot; The electrical quantity sensor is used to measure the magnitude of the output current of the motor driver of the leg joint of the bionic leg-foot robot so as to calculate the friction force between the foot end and the ground.

2. The terrain sensing system according to claim 1, characterized in that: The force sensor is arranged at the foot end of the bionic leg-foot robot.

3. The terrain sensing system according to claim 1, characterized in that: It also includes a visible light module, a laser radar, and a navigation and positioning module connected to the bionic leg-foot robot; The visible light module is used to perceive environmental color information; The laser radar is used to perceive the basic conditions of the terrain; The navigation and positioning module is used to realize autonomous navigation and dynamic obstacle avoidance of the bionic leg-foot robot.

4. The terrain sensing system according to claim 3, characterized in that: The navigation and positioning module includes a Beidou module, an inertial measurement unit, and an odometer; The Beidou module is used to measure or calibrate the positions of the bionic leg-foot robot, obstacles, and reference objects; The inertial measurement unit is used to measure the acceleration of the bionic leg-foot robot in a restricted environment, and calculate the speed, position, and posture information of the bionic leg-foot robot; The odometer is used to measure the mileage of the bionic leg-foot robot in a restricted environment.

5. The terrain sensing system according to claim 4, characterized in that: It also includes a control terminal and a perception processing module that are communicably connected, and the perception processing module is communicably connected to the laser rangefinder, the millimeter wave radar, the microphone array, the force sensor, and the power sensor through an Ethernet bus; The perception processing module is used to process the corresponding sensor information received, and feed back the data processing results and the status information of each device to the control terminal through the team self-organizing network measurement and control link.

6. The terrain sensing system according to claim 5, characterized in that: The method for processing sensor information by the perception processing module includes: Perform visible light day and night perception while traveling, and after determining that it is night time, perform terrain perception through the laser radar while traveling, and after determining that it is not night time, perform terrain perception through the visible light module while traveling; Determining whether there are obstacles through the terrain perception; After determining that there is an obstacle, the obstacle distance is measured by the laser rangefinder, and the obstacle size is measured by the millimeter wave radar and the microphone array, so as to generate an avoidance strategy according to the obstacle distance and the obstacle size; During driving, the force sensor is used to determine whether the road surface is soft; Determining that the road is not soft, and determining whether the road is slippery by using the power sensor during driving; Determine whether the road surface is slippery or soft and evaluate the passability to determine whether it is passable; If it is determined that the road surface is not slippery or passable, the robot is controlled to move normally; If it is determined that the robot cannot pass through, the avoidance strategy is adjusted to control the robot to move normally.

7. The terrain sensing system according to claim 6, characterized in that: The generated semantic map and the adjusted avoidance strategy are sent to the control terminal.

8. A quadruped robot, characterized in that: A terrain sensing system comprising any one of claims 1 to 7.

Images