Follow - path planning method and legged robot

Abstract

A following path planning method for a legged robot, the following path planning method comprising: obtaining pose information of a target object; forming a virtual obstacle around the target object; identifying physical obstacles in a planning map; planning a pose following path of the legged robot in the planning map according to the pose information, the virtual obstacle and the physical obstacles. The virtual obstacle has the same pose as the target object and encloses the target object therein, which can ensure that the legged robot maintains the same pose as the target object when approaching the target object and optimizes the smoothness of the pose following path. The present invention also provides a legged robot.

Description

Technical Field

[0001] The present invention relates to the field of robot safety protection, and particularly to a following path planning method for a legged robot during movement and a legged robot. Background Art

[0002] With the continuous development of technology, legged robots are widely used in people's lives. Among them, a legged robot can follow a target object to achieve a specific goal, such as following a running human to prevent sudden illness or accident, or following a pet at home to observe the pet in real time. A legged mobile robot with a following function needs to dynamically plan a following path according to multiple conditions such as the pose of the target object, the surrounding environment, and the desired task for following the target object. Among them, the following path is usually calculated based on the Hybrid A* planning algorithm. The following path planned based on the Hybrid A* planning algorithm can only achieve path following and does not consider the pose of the legged robot, which will lead to different poses between the legged robot and the target object when the legged robot approaches the target object, and the specified exploration or obstacle avoidance task cannot be executed. Summary of the Invention

[0003] The main purpose of the present invention is to provide a following path planning method and a legged robot, aiming to solve the problem of different poses of the legged robot when approaching the following target object in the prior art.

[0004] A following path planning method for a legged robot; the legged robot is used to follow a target object; the following path planning method includes:

[0005] Obtain the pose information of the target object;

[0006] Form a virtual obstacle around the target object; the virtual obstacle has the same pose as the target object and encloses the target object;

[0007] Identify the physical obstacles in the planning map; and

[0008] Plan the pose following path of the legged robot in the planning map according to the pose information, the virtual obstacle, and the physical obstacle.

[0009] A legged robot, the legged robot includes:

[0010] A pose acquisition module for obtaining the pose information of the target object;

[0011] A virtual obstacle formation module for forming a virtual obstacle around the target object; the virtual obstacle has the same pose as the target object and encloses the target object within it;

[0012] An obstacle recognition module for recognizing physical obstacles within the planned map; and

[0013] A path planning module for planning a pose following path of the legged robot within the planned map based on the pose information, the virtual obstacle, and the physical obstacle.

[0014] The above-mentioned following path planning method and robot can ensure that the legged robot maintains the same pose as the target object when approaching the target object and optimize the smoothness of the pose following path by setting the virtual obstacle near the target object. Description of the Drawings

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative efforts.

[0016] Figure 1 It is a schematic diagram of the modules of the legged robot of the present invention.

[0017] Figure 2 It is a three-dimensional schematic diagram of the legged robot of the present invention.

[0018] Figure 3 For Figure 1 It is a schematic diagram of the modules of the storage unit described in

[0019] Figure 4 It is a flowchart of the following path planning method of the legged robot of the present invention.

[0020] Figure 5 For Figure 4 It is a detailed flowchart of step S18 in

[0021] Figure 6 For Figure 4 It is a schematic diagram of the pose following path in

[0022] Figure 7 It is a schematic diagram of the inscribed circle and circumscribed circle of the legged robot of the present invention.

[0023] Figure 8 For Figure 4 It is a schematic diagram of the expansion process of the virtual obstacle in step S15 in

[0024] Description of Main Component Symbols

[0025] Legged Robot 100

[0026] Mechanical Unit 101

[0027] Communication Unit 102

[0028] Audio Output Unit 103

[0029] Sensing Unit 105

[0030] Display Unit 106

[0031] Input Unit 107

[0032] Interface Unit 108

[0033] Storage Unit 109

[0034] Main Control Unit 110

[0035] Power Supply 111

[0036] Display Panel 1061

[0037] Touch Panel 1071

[0038] Other Input Devices 1072

[0039] Operating System 1

[0040] Safety Protection System 2

[0041] Pose Acquisition Module 10

[0042] Status Management Module 20

[0043] Virtual Obstacle Formation Module 30

[0044] Obstacle Recognition Module 40

[0045] Path Planning Module 50

[0046] Data Processing Module 60

[0047] Update Module 70

[0048] Detection Module 80

[0049] Target Object 200

[0050] Virtual Obstacle 300

[0051] Inner Boundary 301

[0052] Outer Boundary 302

[0053] Side 304

[0054] Solid obstacle 400

[0055] Inscribed circle A

[0056] Circumscribed circle B

[0057] Inscribed radius r1

[0058] Circumscribed radius R

[0059] Specified figure S

[0060] Expansion radius r2

[0061] Pose following path P

[0062] Steps S10 - S19

[0063] The following specific embodiments will further illustrate the present invention in conjunction with the above - mentioned drawings. Specific embodiments

[0064] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] In the following description, suffixes such as "module", "component", or "unit" used to represent components are only for the convenience of describing the present invention and have no specific meaning in themselves. Therefore, "module", "component", or "unit" can be used interchangeably.

[0066] Please refer to Figure 1 , which is a schematic hardware structure diagram of a legged robot 100 for implementing various embodiments of the present invention. The legged robot 100 may include: a mechanical unit 101, a communication unit 102, an audio output unit 103, a sensing unit 105, an interface unit 108, a storage unit 109, a main control unit 110, and a power supply 111 and other components. The various components of the legged robot 100 can be connected in any way, including wired or wireless connections, etc. Those skilled in the art can understand that Figure 1 the structure of the legged robot 100 shown in

[0067] Below, in conjunction with Figure 1 each component of the legged robot 100 will be specifically introduced:

[0068] The mechanical unit 101 is the hardware of the legged robot 100. The mechanical unit 101 may include at least one driving unit, at least one power module, and a mechanical structure module. It should be noted that each component module of the mechanical unit 101 can be one or multiple, and can be set according to specific situations. For example, the leg structure is generally 4 (as Figure 2 shown), and each leg structure is configured with 3 power modules, which respectively correspond to the side swing leg joint, the thigh joint, and the calf joint. The number of power modules corresponding to the legged robot 100 is 12. The driving unit drives the corresponding power module to work by outputting a driving torque. Multiple power modules cooperate with each other to control the mechanical structure module to perform quadruped walking.

[0069] The communication unit 102 can be used for receiving and sending signals, and can also communicate with the network and other devices. For example, after receiving the instruction information sent by a remote control or other legged robots 100 to move in a specific direction at a specific speed according to a specific gait, it is transmitted to the main control unit 110 for processing. The communication unit 102 includes modules such as a WiFi module, a 4G module, a 5G module, a Bluetooth module, and an infrared module.

[0070] The audio output unit 103 can convert the audio data received by the communication unit 102 or stored in the storage unit 109 into an audio signal and output it as sound. The audio output unit 103 can include a speaker, a buzzer, and so on.

[0071] The sensing unit 105 is used to obtain the information data of the surrounding environment of the legged robot 100 and monitor the motion parameters of each component inside the legged robot 100, and send them to the main control unit 110. The sensing unit 105 includes a variety of sensors, such as sensors for obtaining the surrounding environment information: lidar (for remote object detection, distance determination, and / or speed determination), millimeter-wave radar (for short-range object detection, distance determination, and / or speed determination), cameras, infrared cameras, Global Navigation Satellite System (GNSS), etc. Such as sensors for monitoring each component inside the legged robot 100: Inertial Measurement Unit (IMU) (for measuring the values of speed, acceleration, and angular velocity), sole sensors (for monitoring the position of the sole contact point, the sole attitude, the magnitude and direction of the ground contact force), and temperature sensors (for detecting the component temperature), but not limited to this. As for other sensors such as load sensors, touch sensors, motor angle sensors, torque sensors, etc. that the legged robot 100 can also be configured with, they will not be elaborated here.

[0072] The display unit 106 is configured to display information input by the user or information provided to the user. The display unit 106 may include a display panel 1061, and the display panel 1061 may be configured in the form of, for example, a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc.

[0073] The input unit 107 can be used to receive input numerical or character information. Specifically, the user input unit 107 may include a touch panel 1071. The touch panel 1071, also known as a touch screen, can collect the user's touch operations (such as operations of the user using the palm, finger or a suitable accessory on or near the touch panel 1071), and drive the corresponding connection device according to a pre-set program. The touch panel 1071 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation and the signal brought by the touch operation, and transmits the signal to the touch controller. The touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the main control unit 110, and can also receive and execute the commands sent by the main control unit 110. In addition to the touch panel 1071, the user input unit 107 may further include other input devices 1072. Specifically, the other input devices 1072 may include, but are not limited to, one or more of a remote control operation handle, etc., and are not specifically limited here.

[0074] Furthermore, the touch panel 1071 may cover the display panel 1061. After the touch panel 1071 detects a touch operation on or near it, it transmits the information to the main control unit 110 to determine the type of touch event. Subsequently, the main control unit 110 provides a corresponding visual output on the display panel 1061 according to the type of touch event. Although in Figure 1 the touch panel 1071 and the display panel 1061 are implemented as two independent components to separately realize the input and output functions, in some embodiments, the touch panel 1071 and the display panel 1061 may be integrated to realize the input and output functions, which are not specifically limited here.

[0075] The interface unit 108 can be used to receive inputs (such as data information, power, etc.) from external devices and transmit the received inputs to one or more components within the legged robot 100, or can be used to output (such as data information, power, etc.) to external devices. The interface unit 108 may include a power port, a data port (such as a USB port), a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, etc.

[0076] The storage unit 109 is used to store software programs and various data. The storage unit 109 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system program, a motion control program, application programs (such as a text editor), etc.; the data storage area may store the data generated during the use of the legged robot 100 (such as various sensing data obtained by the sensing unit 105, log file data), etc. In addition, the storage unit 109 may include a high-speed random access memory, and may also include a non-volatile memory, such as a disk memory, a flash memory, or other non-volatile solid-state memories.

[0077] The main control unit 110 is the control center of the legged robot 100, connects all components of the entire legged robot 100 through various interfaces and lines, and controls the entire legged robot 100 by running or executing the software programs stored in the storage unit 109 and calling the data stored in the storage unit 109.

[0078] The power supply 111 is used to supply power to each component. The power supply 111 includes a battery and a power control board. The power control board is used to control functions such as battery charging, discharging, and power consumption management. Optionally, the power supply 111 may be electrically connected to the main control unit 110, the drive unit 1011, and the sensing unit 105 (such as a camera, a radar, a speaker, etc.) respectively. It should be noted that each component may be connected to different power supplies 111, or powered by the same power supply 111.

[0079] In addition, please refer to Figure 3 together, which is a module schematic diagram of the storage unit 109. In the embodiment of the present invention, the storage unit 109 includes:

[0080] A pose acquisition module 10, used to acquire the pose information of the target object 200 (as shown in Figure 6 ).

[0081] In at least one embodiment of the present invention, the pose information may include the position coordinates and attitude angles of the target object 200, etc., but is not limited thereto. The pose acquisition module 10 acquires the pose information of the target object 200 through the sensing unit 105.

[0082] The state management module 20 is configured to identify the scene where the target object 200 is located and set a planning map according to the scene.

[0083] In at least one embodiment of the present invention, the scene may include an indoor scene and an outdoor scene. Among them, the indoor scene is usually a flat road surface, and the outdoor scene is usually an uneven road surface. The state management module 20 identifies the road surface condition of the target object 200 through the sensing unit 105. When the identified road surface condition is a flat road surface, the state management module 20 identifies that the target object 200 is in an indoor scene. When the identified road surface condition is an uneven road surface, the state management module 20 identifies that the target object 200 is in an outdoor scene.

[0084] Different scenes correspond to different types of planning maps. In at least one embodiment of the present invention, the planning map may include a 2D grid map and a 3D elevation map. When the target object 200 is in the indoor scene, the state management module 20 sets the 2D grid map as the planning map. When the target object 200 is in the outdoor scene, the state management module 20 sets the 3D elevation map as the planning map. Among them, the 3D elevation map is established according to the perception information acquired by the sensing unit 105. When the planning map is a 3D elevation map, the state management module 20 further converts the 3D elevation map into a 2.5D map as the planning map.

[0085] In at least one embodiment of the present invention, the planning map is a local map, a square range centered on the target object 200. Among them, the range of the planning map is 20 meters * 20 meters. In at least one embodiment of the present invention, the resolution of the planning map is 5 centimeters.

[0086] The virtual obstacle formation module 30 is configured to form a virtual obstacle 300 around the target object 200 (as Figure 6 shown).

[0087] In at least one embodiment of the present invention, the virtual obstacle 300 is used to keep the legged robot 100 in the same pose as the target object 200 when the legged robot 100 travels to a preset range of the target object 200.

[0088] The virtual obstacle 300 has the same pose as the target object 200 and encloses the target object 200 therein. In at least one embodiment of the present invention, the virtual obstacle 300 is generally in a U-shaped structure. That is, the opening direction of the virtual obstacle 300 is opposite to the orientation of the target object 200. In at least one embodiment of the present invention, as Figure 7 shown, it is the projection of the legged robot 100 on the bearing surface. The bearing surface is the projection plane of the legged robot 100 when viewed downward from the top view angle of the legged robot 100. The legged robot 100 has an inscribed circle A and a circumscribed circle B. Among them, the inscribed circle A has an inscribed radius r1, and the circumscribed circle B has a circumscribed radius R. The distance W between the inner boundaries 301 of the virtual obstacle 300 (as Figure 8 shown) is greater than twice the inscribed radius r1 of the inscribed circle A corresponding to the legged robot 100 and less than a preset value. In at least one embodiment of the present invention, the preset value is three times the inscribed radius r1 of the inscribed circle A corresponding to the legged robot 100.

[0089] Specifically, the virtual obstacle construction module 30 constructs the virtual obstacle 300 of a specified pattern with the target object 200 as the center.

[0090] The obstacle recognition module 40 is used to recognize the physical obstacle 400 in the map (as Figure 6 shown).

[0091] In at least one embodiment of the present invention, the obstacle recognition module 40 can recognize the physical obstacle 400 located in the planned map through the sensing unit 105 (as Figure 6 shown).

[0092] The path planning module 50 is used to plan the pose following path P of the legged robot 100 in the planned map according to the pose information, the virtual obstacle 300, and the physical obstacle 400 (as Figure 6 shown). In other embodiments, the pose following path P is a global path. During the process of traveling along the pose following path P, the legged robot 100 can also obtain the local map near the legged robot 100, update the current pose of the target object 200 and the information of the physical obstacle 400, and adjust the pose following path P located in the local map according to the above content to achieve timely dynamic obstacle avoidance and motion control of the legged robot 100, thereby realizing the autonomous movement of the legged robot.

[0093] In at least one embodiment of the present invention, the path planning module 50 uses the Hybrid A* algorithm and the Floyd path smoothing algorithm for planning, and uniformly identifies the virtual obstacle 300 and the physical obstacle 400 as obstacles. In addition, the pose following path P has no kinematic constraints and can meet the mobility of the legged robot 100, such as turning in place, etc.

[0094] The path planning module 50 is further configured to send the pose following path P to the mechanical unit 101 through the communication unit 102 to drive the legged robot 100 to travel along the pose following path P.

[0095] The data processing module 60 performs dilation processing on the boundaries of the virtual obstacle 300 and the physical obstacle 400. As Figure 8 shown, the virtual obstacle 300 includes an inner boundary 301 and an outer boundary 302. The inner boundary 301 includes a plurality of side edges 304. The dilation processing is that the virtual obstacle forming module 30 dilates from the inner boundary 301 of two opposite side edges 304 of the virtual obstacle 300 in a direction away from the virtual obstacle 300 by a specified dilation radius r2 to form a plurality of connected specified figures S. In at least one embodiment of the present invention, the specified figure S is a semi-circular arc. The specified dilation radius r2 is greater than or equal to the inscribed radius r1 of the inscribed circle A corresponding to the legged robot 100 and less than half of the distance between the inner boundaries 301 of the virtual obstacle 300, to avoid collisions between the virtual obstacle 300 and the legged robot 100 and enable the legged robot 100 to pass through. In other embodiments, the virtual obstacle forming module 30 may also simultaneously perform dilation processing on the inner boundaries 301 and the outer boundary 302 of all the side edges 304 of the virtual obstacle 300. The dilation processing of the path planning module 50 for the physical obstacle 400 is similar to that for the virtual obstacle 300.

[0096] The update module 70 is configured to update the position of the legged robot 100 on the planned map.

[0097] The detection module 80 is configured to determine whether the legged robot 100 generates a stop instruction. When the legged robot 100 generates a stop instruction, the legged robot 100 stops driving the mechanical unit 101.

[0098] Specifically, the detection module 80 determines whether the legged robot 100 reaches the human body pose point. When the legged robot 100 does not reach the human body pose point, the detection module 80 further determines whether the legged robot 100 receives a stop signal, and the stop signal includes but is not limited to a stop gesture, a voice stop command, etc. When the legged robot 100 reaches the human body pose point or the legged robot 100 receives a stop signal, it is recognized that the legged robot 100 generates the stop command; otherwise, it is recognized that the legged robot 100 does not generate the stop command.

[0099] In other embodiments, the detection module 80 may also first determine whether the legged robot 100 receives a stop signal. When the legged robot 100 does not receive the stop signal, the detection module 80 further determines whether the legged robot 100 reaches the human body pose point. When the legged robot 100 reaches the human body pose point or the legged robot 100 receives a stop signal, it is recognized that the legged robot 100 generates the stop command. When the legged robot 100 does not reach the human body pose point, it is recognized that the legged robot 100 does not generate the stop command.

[0100] In at least one embodiment of the present invention, the human body pose point is a pose point having the same pose as the target object 200 and a straight-line distance equal to a preset distance from the legged robot 100. Wherein, the preset distance is the safety distance between the legged robot 100 and the target object 200, which ensures that the legged robot 100 approaches the target object 200 and avoids the legged robot 100 colliding with the target object 200.

[0101] In at least one embodiment of the present invention, the stop gesture is a gesture formed by the target object 200 recognized by the legged robot 100 through the sensing unit 105. The gesture can be set according to the user's habit. For example, when the target object 200 is a human body, the gesture can be an open palm, a clenched fist, etc., and is not limited thereto.

[0102] In other embodiments, when the stop signal is a voice stop signal, the legged robot 100 recognizes the voice stop signal through the sensing unit 105; the stop signal can also be a signal sent through APP interaction, etc., and is not limited thereto.

[0103] The above-mentioned legged robot 100 can ensure that when the legged robot 100 moves to a preset range near the target object 200, it maintains the same posture as the target object 200 by setting the virtual obstacle near the target object 200, and optimizes the smoothness of the pose following path P.

[0104] Please refer to Figure 4 , which is a flowchart of the following path planning method of the legged robot 100. In at least one embodiment of the present invention, the following path planning method is applied to the legged robot 100. The legged robot 100 may further include Figure 1 or Figure 3 more or fewer other hardware or software, or different component settings. The following path planning method includes the following steps:

[0105] S10. The pose acquisition module 10 acquires the pose information of the target object 200 (as Figure 6 shown).

[0106] In at least one embodiment of the present invention, the pose information may include the position coordinates and attitude angles of the target object 200, etc., but is not limited thereto. The pose acquisition module 10 acquires the pose information of the target object 200 through the sensing unit 105.

[0107] S11. The state management module 20 identifies the scene where the target object 200 is located and sets a planning map according to the scene.

[0108] In at least one embodiment of the present invention, the scene may include an indoor scene and an outdoor scene. Among them, the indoor scene is usually a flat road surface, and the outdoor scene is usually an uneven road surface. The state management module 20 identifies the road surface condition of the target object 200 through the sensing unit 105. When the identified road surface condition is a flat road surface, the state management module 20 identifies that the target object 200 is in an indoor scene. When the identified road surface condition is an uneven road surface, the state management module 20 identifies that the target object 200 is in an outdoor scene.

[0109] The different scenarios correspond to different types of the planning maps. In at least one embodiment of the present invention, the planning map may include a 2D grid map and a 3D elevation map. When the target object 200 is in the indoor scene, the state management module 20 sets the 2D grid map as the planning map. When the target object 200 is in the outdoor scene, the state management module 20 sets the 3D elevation map as the planning map. Wherein, the 3D elevation map is established according to the sensing information obtained by the sensing unit 105. When the planning map is a 3D elevation map, the state management module 20 further converts the 3D elevation map into a 2.5D map as the planning map.

[0110] In at least one embodiment of the present invention, the planning map is a local map, a square range centered on the target object 200. Wherein, the range of the planning map is 20 meters * 20 meters. In at least one embodiment of the present invention, the resolution of the planning map is 5 centimeters.

[0111] S12. The virtual obstacle forming module 30 forms a virtual obstacle 300 around the target object 200 (as Figure 6 shown).

[0112] In at least one embodiment of the present invention, the virtual obstacle 300 is used to maintain the same posture as the target object 200 when the legged robot 100 travels to a preset range of the target object 200.

[0113] Please refer to Figure 6 together. The virtual obstacle 300 has the same posture as the target object 200 and encloses the target object 200 therein. In at least one embodiment of the present invention, the virtual obstacle 300 is generally in a U-shaped structure. That is, the opening direction of the virtual obstacle 300 is opposite to the orientation of the target object 200. As Figure 7 shown, it is the projection of the legged robot 100 on the bearing surface. The bearing surface is the projection plane of the legged robot 100 when viewed downward from the top view angle of the legged robot 100. The legged robot 100 has an inscribed circle A and a circumscribed circle B. Wherein, the inscribed circle A has an inscribed radius r1, and the circumscribed circle B has a circumscribed radius R. The distance W between the inner boundaries 301 of the virtual obstacle 300 (as Figure 8 shown) is greater than twice the inscribed radius r1 of the inscribed circle A corresponding to the legged robot 100 and less than a preset value. In at least one embodiment of the present invention, the preset value is three times the inscribed radius r1 of the inscribed circle A corresponding to the legged robot 100.

[0114] In at least one embodiment of the present invention, the virtual obstacle forming module 30 forms the virtual obstacle 300 with a specified pattern centered on the target object 200.

[0115] S13. The obstacle recognition module 40 recognizes the physical obstacle 400 (as Figure 6 shown) within the planned map.

[0116] In at least one embodiment of the present invention, the obstacle recognition module 40 can recognize the physical obstacle 400 located within the planned map through the sensing unit 105.

[0117] S14. The path planning module 50 plans the pose following path P of the legged robot 100 (as Figure 6 shown) within the planned map according to the pose information, the virtual obstacle 300, and the physical obstacle 400. In other embodiments, the pose following path P is a global path. During the process of traveling along the pose following path P, the legged robot 100 can also obtain the local map near the legged robot 100, update the current pose of the target object 200 and the information of the physical obstacle 400, and adjust the pose following path P within the local map according to the above content to achieve timely dynamic obstacle avoidance and motion control of the legged robot 100, thereby realizing the autonomous movement of the legged robot.

[0118] In at least one embodiment of the present invention, the path planning module 50 uses the Hybrid A* algorithm for planning and uniformly recognizes the virtual obstacle 300 and the physical obstacle 400 as obstacles. In addition, the pose following path P has no kinematic constraints and can meet the mobility of the legged robot 100, such as turning in place, etc.

[0119] S15. The data processing module 60 performs dilation processing on the boundaries of the virtual obstacle 300 and the physical obstacle 400.

[0120] As Figure 8As shown, the virtual obstacle 300 includes an inner boundary 301 and an outer boundary 302. The inner boundary 301 includes a plurality of side edges 304. The inflation process is that the virtual obstacle forming module 30 inflates from the inner boundary 301 of two opposite side edges 304 of the virtual obstacle 300 in a direction away from the virtual obstacle 300 to inflate with a specified inflation radius r2, so as to form a plurality of specified figures S arranged in connection. In at least one embodiment of the present invention, the specified figure S is a semi-circular arc. The specified inflation radius r2 is greater than or equal to the inscribed radius r1 of the inscribed circle A corresponding to the legged robot 100, and less than half of the distance between the inner boundaries 301 of the virtual obstacle 300, so as to avoid collision between the virtual obstacle 300 and the legged robot 100, and enable the legged robot 100 to pass through. In other embodiments, the virtual obstacle forming module 30 can also perform inflation processing on the inner boundaries 301 and the outer boundary 302 of all the side edges 304 of the virtual obstacle 300 at the same time. The inflation processing of the path planning module 50 for the physical obstacle 400 is similar to the inflation processing of the virtual obstacle 300.

[0121] S16. The path planning module 50 sends the pose following path P to the mechanical unit 101 through the communication unit 102 to drive the legged robot 100 to travel along the pose following path P.

[0122] S17. The update module 70 updates the position of the legged robot 100 on the planned map.

[0123] S18. The detection module 80 determines whether the legged robot 100 generates a stop instruction.

[0124] Please refer to Figure 5 , in at least one embodiment of the present invention, the step of the detection module 80 determining whether the legged robot 100 generates a stop instruction includes:

[0125] S181. Determine whether the legged robot 100 reaches the human pose point;

[0126] S182. When the legged robot 100 does not reach the human pose point, determine whether the legged robot 100 receives a stop signal.

[0127] When the legged robot 100 reaches the human pose point or the legged robot 100 receives a stop signal, it is recognized that the legged robot 100 generates the stop instruction and enters step S19;

[0128] When the legged robot 100 has not reached the human body pose point and the legged robot 100 has not received the stop signal, it is recognized that the legged robot 100 has not generated the stop command, and the process returns to step S10.

[0129] In at least one embodiment of the present invention, the human body pose point is a pose point that has the same pose as the target object 200 and the straight-line distance between the legged robot 100 is equal to a preset distance. Wherein, the preset distance is the safety distance between the legged robot 100 and the target object 200, which ensures that the legged robot 100 approaches the target object 200 and avoids the legged robot 100 colliding with the target object 200.

[0130] In at least one embodiment of the present invention, the stop signal includes but is not limited to a stop gesture, a voice stop command, etc. When the stop signal is a stop gesture, the legged robot 100 recognizes the gesture formed by the target object 200 through the sensing unit 105. The gesture can be set according to the user's habit. For example, when the target object 200 is a human body, the gesture can be an open palm, a clenched fist, etc., and is not limited thereto. When the stop signal is a voice stop signal, the legged robot 100 recognizes the voice stop signal through the sensing unit 105; the stop signal can also be a signal sent through APP interaction, etc., and is not limited thereto.

[0131] In other embodiments, the detection module 80 can also first determine whether the legged robot 100 has received a stop signal. When the legged robot 100 has not received the stop signal, the detection module 80 further determines whether the legged robot 100 has reached the human body pose point. When the legged robot 100 reaches the human body pose point or the legged robot 100 receives a stop signal, it is recognized that the legged robot 100 has generated the stop command, otherwise, it is recognized that the legged robot 100 has not generated the stop command.

[0132] S19. When the legged robot 100 generates a stop command, the legged robot 100 stops driving the mechanical unit 101.

[0133] The above-mentioned following path planning method can ensure that the legged robot 100 maintains the same posture as the target object 200 when it travels within the preset range of the target object 200 by setting the virtual obstacle near the target object 200, and optimizes the smoothness of the pose following path P.

[0134] It should be noted that in this document, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising that element.

[0135] The serial numbers of the embodiments of the present invention described above are for description only and do not represent the superiority or inferiority of the embodiments.

[0136] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0137] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope protected by the claims of the present invention. These all fall within the protection scope of the present invention.

Claims

1. A following path planning method for a legged robot, the legged robot being used to follow a target object; characterized in that: The described following path planning method includes: Obtaining the pose information of the target object; Forming a virtual obstacle around the target object; the virtual obstacle has the same pose as the target object and encloses the target object; Identifying the physical obstacles in the planning map; and Planning the pose following path of the legged robot in the planning map according to the pose information, the virtual obstacle, and the physical obstacles; The forming a virtual obstacle around the target object includes: Constructing the virtual obstacle with a specified pattern centered on the target object.

2. The following path planning method according to claim 1, wherein, The virtual obstacle is generally in a U-shaped structure and has an inner boundary and an outer boundary; the opening direction of the virtual obstacle is opposite to the orientation of the target object; the projection of the legged robot on the bearing surface has an inscribed circle; the inscribed circle has an inscribed radius; the distance between the inner boundaries of the two opposite sides of the virtual obstacle is greater than twice the inscribed radius of the corresponding inscribed circle of the legged robot and less than a predetermined distance.

3. The following path planning method according to claim 1, wherein, Before planning the pose following path of the legged robot in the planning map according to the pose information, the virtual obstacle, and the physical obstacles, the following path planning method further includes: Performing dilation processing on the boundaries of the virtual obstacle and the physical obstacles.

4. The following path planning method according to claim 1, wherein The following path planning method further includes: Sending the pose following path to the mechanical unit through the communication unit to drive the legged robot to travel along the pose following path; Updating the position of the legged robot on the planning map; Judging whether the legged robot generates a stop instruction; When the legged robot generates a stop instruction, the legged robot stops driving the mechanical unit.

5. The following path planning method according to claim 4, wherein The step of judging whether the legged robot generates a stop instruction includes: Judging that when the legged robot reaches the human pose point or the legged robot receives a stop signal, it is recognized that the legged robot generates the stop instruction.

6. A legged robot, characterized in that, The legged robot includes: A pose acquisition module for obtaining the pose information of the target object; A virtual obstacle formation module for forming a virtual obstacle around the target object; the virtual obstacle has the same pose as the target object and encloses the target object; An obstacle identification module for identifying the physical obstacles in the planning map; and A path planning module for planning the pose following path of the legged robot in the planning map according to the pose information, the virtual obstacle, and the physical obstacles; The specific way for the virtual obstacle formation module to form a virtual obstacle around the target object includes: constructing the virtual obstacle with a specified pattern centered on the target object.

7. The legged robot according to claim 6, wherein The virtual obstacle is generally in a U-shaped structure and has an inner boundary and an outer boundary; the opening direction of the virtual obstacle is opposite to the orientation of the target object; the projection of the legged robot on the bearing surface has an inscribed circle; the inscribed circle has an inscribed radius; the distance between the inner boundaries of two opposite sides of the virtual obstacle is greater than twice the inscribed radius of the corresponding inscribed circle of the legged robot and less than a predetermined distance.

8. The legged robot according to claim 6, characterized in that, The legged robot further includes a data processing module. Before planning the pose following path of the legged robot in the planning map according to the pose information, the virtual obstacle and the physical obstacle, the data processing module performs dilation processing on the boundaries of the virtual obstacle and the physical obstacle.

9. The legged robot according to claim 6, characterized in that, The legged robot further includes: The path planning module is further configured to send the pose following path to the mechanical unit through the communication unit to drive the legged robot to travel along the pose following path; The updating module is configured to update the position of the legged robot on the planning map; The detection module is configured to determine whether the legged robot generates a stop instruction; When the legged robot generates a stop instruction, the legged robot stops driving the mechanical unit.

10. The legged robot according to claim 9, characterized in that, When the detection module determines that the legged robot reaches the human pose point or the legged robot receives a stop signal, the detection module identifies that the legged robot generates the stop instruction.

Images