Biped robot task navigation method based on image segmentation and related device

Abstract

The invention discloses a biped robot task navigation method based on image segmentation and a related device. The method comprises the following steps: acquiring a plurality of feature objects obtained by performing image segmentation on panoramic image information acquired by a sensing module based on a target location; according to the spatial features of the plurality of feature objects, the spatial features of the biped robot and the spatial features of the target location, determining whether a target idle position exists in the target location; detecting that a target idle position exists in the target location, and determining a target behavior strategy according to the character recognition results of the plurality of feature objects; and controlling the biped robot to execute the target behavior strategy. The feature objects obtained after image segmentation is conducted on the collected panoramic image are detected for multiple times, the target behavior strategy of the robot is determined according to the detection result, the elevator taking delivery task is completed according to condition self-service decision, help is not needed to be provided by other elevator passengers, and the intelligence of the robot for executing the elevator taking delivery task is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent robots, and in particular, to a bipedal robot task navigation method and related device based on image segmentation. Background Art

[0002] With the continuous development of artificial intelligence and intelligent robot technology, in order to meet the growing demand for people's life convenience, it has become a new development direction attracting much attention that robots take elevators and deliver items to users on high floors. However, there are still some challenges for robots in autonomous elevator riding at present. For example, when a robot autonomously takes an elevator, its actions are rather rigid and it needs other elevator riders to actively provide convenience for the robot, resulting in the lack of intelligence when the robot performs the elevator delivery task. Summary of the Invention

[0003] An embodiment of this application provides a bipedal robot task navigation method and related device based on image segmentation. By performing image segmentation on the collected panoramic image, detecting the identified feature objects multiple times, and finally determining the target behavior strategy of the robot according to the detection result, the elevator delivery task is completed through conditional self - decision - making without the need for other elevator riders to provide help, which is beneficial to improving the intelligence of the robot when performing the elevator delivery task.

[0004] In a first aspect, an embodiment of this application provides a bipedal robot task navigation method based on image segmentation, which is applied to a control module of a bipedal robot. The bipedal robot includes the control module and a sensing module communicatively connected to the control module. The method includes: Obtaining a plurality of feature objects obtained by performing image segmentation on the panoramic image information collected by the sensing module based on a target location; determining whether there is a target idle position in the target location according to the spatial features of the plurality of feature objects, the spatial features of the bipedal robot, and the spatial features of the target location; when it is detected that there is a target idle position in the target location, determining a target behavior strategy according to the person recognition result of the plurality of feature objects, where the target behavior strategy is used to complete the elevator task navigation of the bipedal robot; controlling the bipedal robot to execute the target behavior strategy.

[0005] In a second aspect, an embodiment of this application provides a bipedal robot task navigation device based on image segmentation, including: An obtaining module, configured to obtain a plurality of feature objects obtained by performing image segmentation on the panoramic image information collected by the sensing module based on a target location; A processing module, configured to determine whether there is a target idle position in the target location according to the spatial features of the multiple feature objects, the spatial features of the bipedal robot, and the spatial features of the target location; and configured to, when detecting that there is a target idle position in the target location, determine a target behavior strategy according to the person recognition results of the multiple feature objects, where the target behavior strategy is used to complete the elevator-riding task navigation of the bipedal robot; and configured to control the bipedal robot to execute the target behavior strategy.

[0006] In a third aspect, an embodiment of the present application provides a computer, including: A memory, a processor, and executable program code stored on the memory and executable on the processor, where when the processor executes the executable program code, it executes the method according to any one of the first aspect.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a bipedal robot task navigation program based on image segmentation is stored. The bipedal robot task navigation program based on image segmentation includes execution instructions for executing the method according to any one of the first aspect.

[0008] In a fifth aspect, the present application provides a computer program product, which is used to implement the method according to any one of the first aspect when executed by a processor.

[0009] By implementing the embodiments of the present application, the control module of the bipedal robot first obtains multiple feature objects obtained by image segmentation of the panoramic image information collected by the sensing module based on the target location, then determines whether there is a target idle position in the target location according to the spatial features of the multiple feature objects, the spatial features of the bipedal robot, and the spatial features of the target location, and then determines a target behavior strategy according to the person recognition results of the multiple feature objects when detecting that there is a target idle position in the target location. The target behavior strategy is used to complete the elevator-riding task navigation of the bipedal robot, and finally controls the bipedal robot to execute the target behavior strategy. By performing image segmentation on the collected panoramic image, detecting the recognized feature objects multiple times, and finally determining the target behavior strategy of the robot according to the detection results, and completing the elevator-riding delivery task through conditional self-decision-making without the need for help from other elevator riders, which is beneficial to improving the intelligence of the robot in performing the elevator-riding delivery task. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the following will describe the drawings required to be used in the embodiments of the present application or the background art.

[0011] Figure 1It is a schematic diagram of the architecture of a bipedal robot provided by an embodiment of the present application; Figure 2 It is a flowchart of a method for task navigation of a bipedal robot based on image segmentation provided by an embodiment of the present application; Figure 3 It is a schematic diagram of a scene for image segmentation using the SAM2 model provided by an embodiment of the present application; Figure 4 It is a schematic diagram of a scene before a bipedal robot enters an elevator provided by an embodiment of the present application; Figure 5 It is a schematic diagram of a scene after a bipedal robot enters an elevator provided by an embodiment of the present application; Figure 6 It is a schematic diagram of the terminal interface of a teleoperation system for a bipedal robot provided by an embodiment of the present application; Figure 7 It is a schematic diagram of the mode adjustment interface of a bipedal robot provided by an embodiment of the present application; Figure 8 It is a structural diagram of a device for task navigation of a bipedal robot based on image segmentation provided by an embodiment of the present application; Figure 9 It is a structural diagram of a computer provided by an embodiment of the present application. Detailed implementation manners

[0012] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present application.

[0013] The terms "first", "second", "third", etc. in the specification, claims and drawings of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0014] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0015] Please refer to Figure 1 , Figure 1 which is a schematic structural diagram of a bipedal robot provided by an embodiment of the present application. As Figure 1 shown, the bipedal robot 100 based on image segmentation includes a perception module 101 and a control module 102. Among them, the perception module 101 includes sensors (such as cameras, depth cameras, lidars, etc.) for acquiring environmental information and surrounding scene images. The perception module 101 is also used to process sensor data, including operations such as preprocessing images, image segmentation, and feature extraction, so as to identify feature objects in the images, including surrounding objects, obstacles, and human users. The control module 102 is communicatively connected to the perception module 101. The control module 102 includes a decision-making function and a control execution function, including making decisions and path planning based on the information provided by the perception module 101, so as to determine the behavior and actions of the robot. The control module 102 is also used to convert the decision output into specific actions and control the specific rotation angles, traveling speeds, and traveling trajectories of execution devices such as robotic arms, wheeled drives, or other motion devices. The control module 102 enables the robot to move, operate, or interact with the outside world by sending control signals.

[0016] Among them, the bipedal robot 100 is a robot designed and constructed to be similar to the structure of human legs. The bipedal robot 100 imitates the gait and movement mode of humans and realizes walking, standing, and performing various tasks through two jointed mechanical legs. A bipedal robot usually consists of multiple electric joints, sensors, and a control system. The multiple electric joints can simulate the degrees of freedom of human joints and achieve balance, walking, and other movements through precise control. The sensors are used to measure environmental information, such as visual sensors, depth sensors, tactile sensors, and inertial measurement units (IMUs), etc. The control system is responsible for calculating and sending instructions to maintain balance, adjust gait, and perform other tasks. The bipedal robot 100 also includes an energy system that provides the required electrical power or other forms of energy for the robot. Preferably, the bipedal robot 100 is a humanoid robot.

[0017] Based on this, the present application provides a method and related device for task navigation of a bipedal robot based on image segmentation. The present application will be described in detail below with reference to the accompanying drawings.

[0018] Please refer to Figure 2 , Figure 2 which is a flowchart of a biped robot task navigation method based on image segmentation provided by an embodiment of the present application. As Figure 2 shown, the method includes the following steps: S201, obtaining a plurality of feature objects obtained by performing image segmentation on the panoramic image information collected by the perception module based on the target location.

[0019] Among them, the perception module for collecting the panoramic image information of the target location can be one or more of devices such as a camera and a depth camera, which is not limited herein.

[0020] Among them, the panoramic image information refers to all visual data captured within the continuously covered range in the horizontal direction of the entire scene or environment seen from the position where the robot is located. These data include visible objects, backgrounds, terrains and other elements in the scene, and can provide rich and detailed visual references. Preferably, in this solution, when the robot performs the task of elevator delivery, the target location is inside the elevator, and the collected panoramic image information is all visual data inside the elevator.

[0021] Among them, the method for performing image segmentation on the panoramic image information can be threshold-based image segmentation, region growing algorithm, edge detection algorithm, deep learning, etc., which is not limited herein.

[0022] In a possible implementation manner, obtaining a plurality of feature objects obtained by performing image segmentation on the panoramic image information collected by the perception module based on the target location includes: obtaining the first panoramic image information collected by the perception module at the target location, where the panoramic image information includes human elements, object elements and background elements; obtaining the second panoramic image information after the perception module performs preprocessing operations on the first panoramic image information, where the preprocessing operations include one or more of denoising, translation and rotation, adjusting the picture size, and adjusting the brightness and contrast; obtaining a plurality of feature objects obtained by the perception module performing image segmentation on the second panoramic image information according to the object segmentation model 2 in the machine learning model.

[0023] Among them, the human element refers to the human figures appearing in the image, including human bodies in different postures and movements such as walking, standing, and sitting, as well as their physical characteristics such as facial expressions, clothing, etc.; the object element refers to other actual objects in the image except humans, and these objects can be various daily necessities, furniture, vehicles, buildings, etc., with different shapes, sizes, and textures. In this solution, the object element refers to all objects inside the elevator except the human element and the background element; the background element is located behind the human and the object, and constitutes the entire scene background in the image. The background usually includes the sky, the ground, the walls, etc. In this solution, the background element refers to the elevator walls and the elevator floor.

[0024] Among them, the preprocessing operation on the first panoramic image information includes one or more of the following steps: Image denoising: Use filters (such as Gaussian filters, median filters) to smooth the image and reduce noise; Image enhancement: Adjust parameters such as the contrast and brightness of the image; Image scaling and cropping: According to needs, scale or crop the image to adapt to specific size requirements or the region of interest; Histogram equalization: Enhance the contrast of the entire image by redistributing the gray levels; Feature extraction: Use computer vision algorithms (such as edge detection, corner detection) to extract key feature points or boundary information for tasks such as object detection and tracking.

[0025] Among them, the Segment Anything Model 2 (SAM2) is an image segmentation model currently used to segment different objects in an unstructured viewfinder frame. SAM2 provides real-time, promptable object segmentation for static images and dynamic video content, unifying image and video segmentation functions into a powerful system. Specifically, SAM2 adopts a streaming memory design and realizes accurate tracking and segmentation of objects in video frames through the combination of a memory encoder, a memory bank, and a memory attention module. The functions of each component are as follows: Memory encoder: Responsible for extracting key information from the input video frames, and this information is used for subsequent object recognition and segmentation.

[0026] Memory bank: Stores the key information and object features learned by the model during the processing of the video for quick matching and segmentation in subsequent frames.

[0027] Memory attention module: Helps the model more accurately locate and segment objects in the video by calculating the correlation between the information in the input frame and the information in the memory bank.

[0028] Exemplarily, please refer toFigure 3 , Figure 3 is a schematic diagram of a scenario for image segmentation using the SAM2 model provided by an embodiment of the present application. As shown in Figure 3 , the target location is inside the elevator. After obtaining the panoramic image of the elevator, the panoramic image of the elevator is segmented based on the SAM2 model. The SAM2 model can identify all object features in the panoramic image and circle them in the form of a square. The feature objects identified in the squares from left to right in the figure are a human object, an object object, a human object, and a human object respectively. Subsequently, the feature objects within the squares can be further analyzed.

[0029] It can be seen that in this example, through the panoramic image information collected by the perception module, after preprocessing operations and image segmentation algorithm processing, the acquisition, optimization, and segmentation of the panoramic image information are realized, and then multiple feature objects are obtained, thereby improving the data quality and providing a rich and accurate input basis for subsequent tasks.

[0030] S202. Determine whether there is a target idle position in the target location according to the spatial features of the multiple feature objects, the spatial features of the biped robot, and the spatial features of the target location.

[0031] Among them, the spatial features include occupied space data. Specifically, the occupied space data can be obtained through occupancy matrices, point cloud data, and bounding box information. The occupancy matrix divides the interior of the elevator into a two-dimensional matrix and records whether each position is occupied; the point cloud data uses devices such as depth cameras to collect the point cloud data inside the elevator. Areas without people will show less dense point clusters, while areas with people will show more dense point clusters; if there is a camera monitoring the interior of the elevator, the target detection algorithm can be used to identify any visible objects and obtain their bounding box information.

[0032] In a possible implementation manner, determining whether there is a target idle position in the target location according to the spatial features of the multiple feature objects, the spatial features of the biped robot, and the spatial features of the target location includes: Obtain the first occupied space data of the multiple feature objects within the target location; obtain the second occupied space data of the bipedal robot itself and the carried items, where the second occupied space data is the data with the smallest occupied space obtained after changing the relative positions of the bipedal robot itself and the carried items; obtain the third occupied space data of the target location; obtain the difference between the third occupied space data and the first occupied space data, and the difference is the free space data; when it is detected that the free space data is not less than the second occupied space data and there is a target free position in the free space data, determine that there is a target free position within the target location; when it is detected that the free space data is less than the second occupied space data, and / or there is no such target free position in the free space data, determine that there is no target free position within the target location.

[0033] Among them, the target free position can be set by the user in the control module of the bipedal robot, and the target free position can also be any position within the target location that can accommodate the bipedal robot. For example, the target free position is a position close to the elevator door and close to the elevator floor control panel.

[0034] Among them, please refer to Figure 4 , Figure 4 is a schematic diagram of the scenario before the bipedal robot enters the elevator provided by the embodiment of the present application. As Figure 4 shown, there is a target free position A and an elevator floor control panel B in the target location C. The bipedal robot 100 obtains the occupied space data within the target location C, and then determines whether the target free position A can accommodate itself according to the occupied space data. Specifically, when the bipedal robot 100 determines whether there is a target free position A within the target location C, it can first obtain the difference between the third occupied space data of the target location C and the first occupied space data of other multiple feature objects within the target location C. If the difference is greater than or equal to the data with the smallest occupied space obtained after changing the relative positions of the bipedal robot 100 itself and the carried items, it is considered that there is a target free position A within the target location C.

[0035] Among them, the default carrying method of the bipedal robot and the carried item, that is, the default relative position of the bipedal robot and the carried item can be set by the user in the control module of the bipedal robot. When the bipedal robot enters the target location, it can change its relative position with the carried item on the premise of ensuring the safety and integrity of the carried item, so as to reduce the occupied space of the bipedal robot. Specifically, when the user assigns the task of elevator delivery to the bipedal robot, the allowed carrying method of the item to be delivered can be set in advance, that is, the allowed relative position of the bipedal robot and the carried item can be set in advance. For example, when the carried item is a cake, the user can set in advance that the bipedal robot can only horizontally translate the cake or vertically lift the cake, and rotation operations are not allowed to ensure the integrity of the cake.

[0036] It can be seen that in this example, by comprehensively considering the occupancy space data of multiple feature objects, the bipedal robot itself, the carried item, and the target location, it is determined whether there is a target idle position, so as to realize the intelligent decision-making of the bipedal robot.

[0037] S203. Detect that there is a target idle position in the target location, and determine a target behavior strategy according to the person recognition result of the multiple feature objects.

[0038] Among them, the target behavior strategy is used to complete the elevator task navigation of the bipedal robot.

[0039] Among them, the person recognition result can be the result of recognizing multiple feature objects in the target location to judge whether there is a person, or the person recognition result can be the result of recognizing the person object among multiple feature objects in the target location to judge whether there is a target person. Specifically, when judging whether there is a target person result among the person objects of multiple feature objects, face recognition or feature extraction can be performed on all recognized persons, and then further judgment can be made.

[0040] In a possible implementation manner, the multiple feature objects include a person object and an object object. The determining a target behavior strategy according to the person recognition result of the multiple feature objects includes: Perform person recognition on the multiple feature objects to obtain a person recognition result; detect that the person recognition result is that there is a person object among the multiple feature objects, determine that the target behavior strategy is to output the first speech voice, navigate to the target idle position, and determine the first behavior strategy according to the elevator floor control panel image collected by the acquired perception module; detect that the person recognition result is that there is no person object among the multiple feature objects, and determine that the target behavior strategy is to navigate to the target idle position and press the target floor button of the elevator floor control panel.

[0041] Among them, the first speech voice can be preset by the user and is used to remind the people inside the target location that the bipedal robot is about to enter the elevator. For example, when the target location is the elevator, the first speech voice can be "Please note that the robot is about to enter the elevator. Please avoid it carefully."

[0042] Among them, when the bipedal robot navigates to the target idle position, the path planning algorithm of the bipedal robot can be the A* algorithm, Dijkstra algorithm, Rapidly-exploring Random Tree (RRT), Potential Field algorithm, etc.

[0043] It can be seen that in this example, determining the target behavior strategy in different situations through the person recognition results of multiple feature objects is beneficial to improving the intelligence of the bipedal robot in practical applications.

[0044] In a possible implementation manner, determining the first behavior strategy according to the elevator floor control panel image collected by the acquired perception module includes: Acquire the elevator floor control panel image collected by the perception module, where the elevator floor control panel image is used to indicate the floor button in the selected state in the elevator floor control panel; judge whether the target floor button in the elevator floor control panel is in the selected state according to the elevator floor control panel image; when it is detected that the target floor button in the elevator floor control panel is not in the selected state, determine that the first behavior strategy is to determine the target floor button pressing strategy according to the obstacle detection result between itself and the elevator floor control panel, keep its own posture until reaching the target floor after determining that the target floor button is in the selected state, and determine the movement mode according to the moving object detection result in front of itself; when it is detected that the target floor button in the elevator floor control panel is in the selected state, determine that the first behavior strategy is to keep its own posture until reaching the target floor and determine the movement mode according to the moving object detection result in front of itself.

[0045] Among them, the steps to press the target floor button on the elevator floor control panel are as follows: Use a visual perception module or sensor, such as a camera, to detect the elevator floor control panel in the elevator and locate the position of the target floor button. Through image processing and computer vision techniques, analyze and process the captured image to identify the target floor button, where object detection, feature matching and other algorithms are used to achieve target recognition; Based on the current position of the robot and the position information of the target floor button, perform path planning to determine how to move to the target position. Navigation algorithms can be used to plan the robot's travel path; According to the path obtained from the motion planning, control the robot to perform corresponding actions to move to the target position; When the robot reaches the target position, press the target floor button precisely and stably in a pre-determined posture through a robotic arm or an indicating device, etc.

[0046] Among them, to detect whether there is a moving object in front of the robot itself, different sensors and technologies can be used to obtain the detection results. The methods are as follows: Moving object detection based on a vision sensor: A bipedal robot can be equipped with vision sensors such as a camera or a depth camera. By capturing images or point cloud data in the environment and analyzing them, computer vision algorithms (such as object detection, motion tracking) can be used to identify and track moving objects.

[0047] Moving object detection based on lidar: Lidar can emit laser beams and receive their reflected signals to obtain the distance and position information of surrounding objects. By continuously scanning the front area and analyzing the returned data, moving objects can be detected.

[0048] Moving object detection based on an infrared sensor: An infrared sensor can detect the infrared radiation generated by an object. By placing an infrared sensor at an appropriate position in front of the robot, it can be determined whether a moving object has passed by.

[0049] Moving object detection based on an ultrasonic sensor: An ultrasonic sensor can send ultrasonic waves and receive their echoes to measure the distance to an obstacle. By arranging an array of ultrasonic sensors at the front of the robot, moving objects that may exist in the front area can be detected.

[0050] It can be seen that in this example, by acquiring and analyzing the image of the elevator floor control panel, it is possible to accurately determine whether the target floor button is in a selected state. This can avoid abnormal behavior or unnecessary movement caused by misjudgment or incorrect operation. Determining the movement mode according to the detection result of the moving object in front of itself enables the robot to flexibly adjust its travel mode according to environmental changes, which is beneficial to improving the intelligence of the robot.

[0051] In a possible implementation, determining a target floor button pressing strategy according to the obstacle detection result between itself and the elevator floor control panel includes: Obtaining the obstacle detection result between itself and the elevator floor control panel; detecting that there is an obstacle between itself and the elevator floor control panel in the obstacle detection result, determining that the target floor button pressing strategy is to output a second speech voice, and the second speech voice is used to ask others to press the target floor button; detecting that there is no obstacle between itself and the elevator floor control panel in the obstacle detection result, determining that the target floor button pressing strategy is to determine the target adjustment angles of its own action joints according to the spatial relationship between itself and the target button to press the target floor button.

[0052] Among them, the obstacle detection result can be obtained in the following ways: by using distance sensors such as ultrasonic sensors, infrared sensors or lidar installed in front of the robot, the distance between the robot and an object (including the elevator floor control panel) can be detected. When the detected distance is less than the set threshold, it can be determined that there is an obstacle; alternatively, a camera or a depth camera and other vision sensors are used to capture an image of the elevator floor control panel, and computer vision technology is used for target detection and segmentation. By analyzing whether there are occluding objects or edge information in the image, it can be inferred whether there is an obstacle.

[0053] Among them, please refer to Figure 5 , Figure 5 is a schematic diagram of the scenario after a biped robot enters the elevator provided by an embodiment of the present application. As Figure 5 shown, after the biped robot 100 enters the target idle position A of the target location C, according to the obstacle detection result, it is determined that there is an obstacle person D between itself and the elevator floor control panel B. At this time, the biped robot 100 outputs a second speech voice through the microphone array carried by itself, and the second speech voice is: "Hello, please help me press the Xth floor, thank you."

[0054] It can be seen that in this example, the target floor button pressing strategy is determined according to the obstacle detection result between itself and the elevator floor control panel. When an obstacle is detected, a second speech voice is output to request others to help press the target floor button. This can intelligently handle the situation where it is impossible to operate directly due to an obstacle.

[0055] In a possible implementation, determining a movement mode according to the detection result of a moving object in front of itself includes: Obtaining the detection result of the moving object in front of itself; detecting that there is a moving object in front of itself in the detection result of the moving object, determining that the movement mode is a following mode; detecting that there is no moving object in front of itself in the detection result of the moving object, determining that the movement mode is an autonomous mode.

[0056] Among them, obtaining the detection result of the moving object in front of itself can be achieved by using a visual sensor, a laser radar or other moving object detection technologies.

[0057] When a moving object is detected in front of the robot, it can enter the follow mode. In this mode, the robot will make corresponding adjustments based on the position and motion trajectory of the moving object to maintain a certain distance and follow it. This mode is suitable for scenarios that require close attention and tracking of specific targets (such as people or objects), such as navigation following human users.

[0058] When the robot detects that there is no moving object in front of it, it can enter autonomous mode. In this mode, the robot will rely on a pre-set path planning algorithm or environmental perception capabilities to navigate and move independently without relying on external targets for guidance. This mode is suitable for situations where there is no specific goal or the task needs to be completed independently, such as patrolling, exploration, etc.

[0059] It can be seen that in this example, by determining different movement modes according to the mobile object detection results and selecting appropriate behavior strategies in different situations, the robot can respond to various environments more intelligently and flexibly.

[0060] In a possible implementation, the method further includes: It is detected that there is no target idle position in the target location, and it is determined whether there is a person moving in the target location; it is detected that there is a person moving in the target location, and the target behavior strategy is determined to output a third speech voice, and after detecting that there is a target idle position in the target location, it is navigated to the target idle position, and a second behavior strategy is determined according to the elevator floor control board image acquired by the perception module; it is detected that there is no person moving in the target location, and the target behavior strategy is determined to wait for the next elevator; the bipedal robot is controlled to execute the target behavior strategy.

[0061] Among them, when the occupied space data or image segmentation results obtained by the perception module detect that there is no target idle position, it is further judged whether there is a person moving, and after waiting for the person to move, another judgment is made to determine whether there is a target idle position in the target location.

[0062] The third speech voice is used to inform the person in the target location that he is moving to the target free position, or the third speech voice can be used to request the person in the target location to continue moving to make some space for himself. For example, the third speech voice can be "I am entering the elevator, please pay attention to avoid it, thank you."

[0063] It can be seen that in this example, by detecting whether there is a target idle position in the target location and whether there is human movement, and determining the target behavior strategy according to different situations, it is beneficial to make the robot more flexible and intelligent in practical applications.

[0064] In a possible implementation manner, after detecting that there is no human movement in the target location, the method further includes: Determining the target behavior strategy as outputting a fourth speech voice, navigating to the target idle position after detecting that there is a target idle position in the target location, and determining a third behavior strategy according to the elevator floor control panel image collected by the obtained perception module.

[0065] Among them, the fourth speech voice is used to request the people in the target location to move to leave the target idle position. For example, the fourth speech voice can be "Please move to make some space for me, thank you".

[0066] Among them, if after outputting the fourth speech voice, it is detected that there is no human movement in the target location, or there is human movement and there is no target idle position in the target location after the human movement, determine the target behavior strategy as waiting for the next elevator.

[0067] It can be seen that in this example, after detecting that there is no human movement in the target location, outputting the fourth speech voice can effectively inform the user of the current situation or the next plan, and the instant voice feedback can enhance the interaction between the human and the robot and improve the user experience.

[0068] In a possible implementation manner, the method further includes: judging whether the walking path width of the target location exceeds a first width threshold according to the image information collected by the perception module; detecting that the walking path width exceeds the first width threshold, and determining whether there is a target idle position in the target location according to the spatial characteristics of the multiple feature objects, the spatial characteristics of the biped robot, and the spatial characteristics of the target location; when it is detected that the walking path width does not exceed the first width threshold, determining the target behavior strategy as waiting for the next elevator.

[0069] Specifically, the biped robot is equipped with sensors or cameras for real-time monitoring of the width of the target travel path. The sensors can measure the distance between the obstacles on both sides and compare it with the size of the robot itself.

[0070] Among them, the first width threshold can be set by the user in the control module of the biped robot. For example, when the target location is inside the elevator and the first width threshold is 20 cm, before the biped robot is about to enter the elevator, it first detects whether the current elevator door is closing and whether the width left by the elevator door is greater than 20 cm. If it is greater than 20 cm, it continues with subsequent judgments; if the width left by the current elevator door is less than 20 cm, it is considered dangerous to enter the elevator currently, and the target behavior strategy is determined to wait for the next elevator.

[0071] It can be seen that in this example, judging and detecting the width on the walking path based on video information and determining the target behavior strategy of the biped robot according to the relationship between the width and the first width threshold helps to improve the intelligence of the biped robot.

[0072] In a possible implementation manner, the user can also remotely control the biped robot through the client of the remote control system. Specifically, please refer to Figure 6 , Figure 6 is a schematic diagram of the terminal interface of the remote control system of a biped robot provided by an embodiment of the present application. As shown in Figure 6 , the terminal interface of the remote control system is used to display the real-time video collected by the biped robot through the visual sensor. A first operation button E and a second operation button F are respectively set at the lower left corner and the lower right corner of the operation interface. The first operation button E is used to control the left and right turning of the biped robot, and the second operation button F is used to control the forward and backward movement of the biped robot. A status bar G is set at the upper right corner of the operation interface. The status bar G is used to display information such as the current time, communication connection status, and the power of the terminal of the remote control system. A function button H is set in the status bar G. By clicking the function button H on the operation interface, the mode adjustment interface of the biped robot can be opened in the middle of the operation interface. The user can change and set the mode of the biped robot, the display mode of the real-time video collected by the biped robot through the visual sensor, the functions of each operation button, and the button layout of the operation interface.

[0073] Among them, please refer to Figure 7 , Figure 7 is a schematic diagram of the mode adjustment interface of a biped robot provided by an embodiment of the present application. As shown in Figure 7As shown in the figure, at this time, the user can obtain the real-time posture of the biped robot on the left side of the mode adjustment interface, and rotate the real-time posture of the biped robot by using the adjustment button K set below the area for displaying the real-time posture of the biped robot. The parameter box J on the right side of the display interface of the teleoperation system terminal correspondingly displays multiple parameters of the current biped robot, including but not limited to the positions of the joint points of the biped robot, joint angles, the orientation and rotation angle of the biped robot, and the head state information of the biped robot. At the same time, the parameter box J includes the X-frame speed of the current biped robot (the moving speed of the biped robot in the front-back direction on the plane) and the Y-frame speed of the biped robot (the moving speed of the biped robot in the left-right direction on the plane). The user can directly adjust the above multiple parameters in the parameter box J. Among them, the three-dimensional space coordinate position where the biped robot is currently located is usually represented by (x, y, z), and the current orientation and rotation angle of the biped robot can be described using Euler angles, quaternions, or rotation matrices.

[0074] S204, control the biped robot to execute the target behavior strategy.

[0075] It can be seen that in this example, by performing image segmentation on the collected panoramic image, detecting the recognized feature objects multiple times, and finally determining the target behavior strategy of the robot according to the detection results, the elevator ride and delivery task is completed through conditional self-decision-making without the need for help from other elevator riders, which is beneficial to improving the intelligence of the robot in performing the elevator ride and delivery task.

[0076] Please refer to Figure 8 , Figure 8 is a structural diagram of a biped robot task navigation device based on image segmentation provided by an embodiment of the present application. As Figure 8 shown, the biped robot task navigation device 800 based on image segmentation includes: An acquisition module 801, configured to acquire multiple feature objects obtained by performing image segmentation on the panoramic image information collected by the sensing module based on the target location; A processing module 802, configured to determine whether there is a target idle position in the target location according to the spatial features of the multiple feature objects, the spatial features of the biped robot, and the spatial features of the target location; and when it is detected that there is a target idle position in the target location, determine a target behavior strategy according to the person recognition results of the multiple feature objects, where the target behavior strategy is used to complete the elevator ride task navigation of the biped robot; and control the biped robot to execute the target behavior strategy.

[0077] In a possible implementation manner, in terms of obtaining multiple feature objects obtained by performing image segmentation on the panoramic image information collected by the perception module based on the target location, the obtaining module 801 is specifically configured to: obtain the first panoramic image information collected by the perception module at the target location, where the panoramic image information includes human elements, object elements, and background elements; obtain the second panoramic image information after the perception module performs preprocessing operations on the first panoramic image information, where the preprocessing operations include one or more of denoising, translation and rotation, adjusting the picture size, and adjusting the brightness and contrast; obtain multiple feature objects obtained by the perception module performing image segmentation on the second panoramic image information according to the object segmentation model 2 in the machine learning model.

[0078] In a possible implementation manner, the spatial feature includes occupied space data. In terms of determining whether there is a target idle position in the target location according to the spatial features of the multiple feature objects, the spatial features of the bipedal robot, and the spatial features of the target location, the processing module 802 is specifically configured to: obtain the first occupied space data of the multiple feature objects in the target location; obtain the second occupied space data of the bipedal robot itself and the carried items, where the second occupied space data is the data with the smallest occupied space obtained by changing the relative positions of the bipedal robot itself and the carried items; obtain the third occupied space data of the target location; obtain the difference between the third occupied space data and the first occupied space data, where the difference is the idle space data; when it is detected that the idle space data is not less than the second occupied space data and there is a target idle position in the idle space data, determine that there is a target idle position in the target location; when it is detected that the idle space data is less than the second occupied space data, and / or, there is no target idle position in the idle space data, determine that there is no target idle position in the target location.

[0079] In a possible implementation manner, the multiple feature objects include human objects and object objects. In terms of determining the target behavior strategy according to the human recognition results of the multiple feature objects, the processing module 802 is specifically configured to: perform human recognition on the multiple feature objects to obtain human recognition results; when it is detected that the human recognition result is that there are human objects among the multiple feature objects, determine that the target behavior strategy is to output the first speech voice, navigate to the target idle position, and determine the first behavior strategy according to the elevator floor control panel image collected by the obtained perception module; when it is detected that the human recognition result is that there are no human objects among the multiple feature objects, determine that the target behavior strategy is to navigate to the target idle position and press the target floor button of the elevator floor control panel.

[0080] In a possible implementation, in terms of determining the first behavior strategy based on the elevator floor control panel image collected by the acquisition module, the processing module 802 is specifically configured to: obtain the elevator floor control panel image collected by the acquisition module, where the elevator floor control panel image is used to indicate the floor buttons in the selected state on the elevator floor control panel; determine whether the target floor button on the elevator floor control panel is in the selected state according to the elevator floor control panel image; when it is detected that the target floor button on the elevator floor control panel is not in the selected state, determine that the first behavior strategy is to determine the target floor button pressing strategy according to the obstacle detection result between itself and the elevator floor control panel, maintain its own posture until reaching the target floor after determining that the target floor button is in the selected state, and determine the movement mode according to the moving object detection result in front of itself; when it is detected that the target floor button on the elevator floor control panel is in the selected state, determine that the first behavior strategy is to maintain its own posture until reaching the target floor, and determine the movement mode according to the moving object detection result in front of itself.

[0081] In a possible implementation, in terms of determining the target floor button pressing strategy according to the obstacle detection result between itself and the elevator floor control panel, the processing module 802 is specifically configured to: obtain the obstacle detection result between itself and the elevator floor control panel; when it is detected that there is an obstacle between itself and the elevator floor control panel in the obstacle detection result, determine that the target floor button pressing strategy is to output a second speech message, where the second speech message is used to ask others to press the target floor button; when it is detected that there is no obstacle between itself and the elevator floor control panel in the obstacle detection result, determine that the target floor button pressing strategy is to determine the target adjustment angles of its own action joints according to the spatial relationship between itself and the target button to press the target floor button.

[0082] In a possible implementation, in terms of determining the movement mode according to the moving object detection result in front of itself, the processing module 802 is specifically configured to: obtain the moving object detection result in front of itself; when it is detected that there is a moving object in front of itself in the moving object detection result, determine that the movement mode is the following mode; when it is detected that there is no moving object in front of itself in the moving object detection result, determine that the movement mode is the autonomous mode.

[0083] In a possible implementation, after determining whether there is a target idle position in the target location based on the spatial features of the multiple feature objects, the spatial features of the bipedal robot, and the spatial features of the target location, the processing module 802 is further configured to: detect that there is no target idle position in the target location, and determine whether there is a person moving in the target location; detect that there is a person moving in the target location, determine that the target behavior strategy is to output a third speech prompt, navigate to the target idle position after detecting that there is a target idle position in the target location, and determine a second behavior strategy according to the elevator floor control panel image acquired by the obtained sensing module; detect that there is no person moving in the target location, determine that the target behavior strategy is to wait for the next elevator, where the third speech prompt is used to inform the people in the target location that the bipedal robot itself is moving to the target idle position; and control the bipedal robot to execute the target behavior strategy.

[0084] In a possible implementation, after detecting that there is no person moving in the target location, the processing module 802 is further configured to: determine that the target behavior strategy is to output a fourth speech prompt, navigate to the target idle position after detecting that there is a target idle position in the target location, and determine a third behavior strategy according to the elevator floor control panel image acquired by the obtained sensing module, where the fourth speech prompt is used to request the people in the target location to move to leave the target idle position.

[0085] It should be noted that, for the specific functional implementation manner of the bipedal robot task navigation device 800 based on image segmentation, please refer to the Figure 2 description of the bipedal robot task navigation method based on image segmentation shown above. For example, the acquisition module 801 is used to implement the relevant content of executing S201, and the processing module 802 is used to implement the relevant content of executing S202 - S204. Each unit or module in the bipedal robot task navigation device 800 based on image segmentation can be separately or all combined into one or several other units or modules to form, or some of the units or modules can be further split into multiple smaller units or modules with more specific functions to form, which can achieve the same operations without affecting the realization of the technical effects of the embodiments of the present invention. The above units or modules are divided based on logical functions. In practical applications, the function of one unit (or module) is implemented by multiple units (or modules), or the functions of multiple units (or modules) are implemented by one unit (or module).

[0086] Based on the description of the above method embodiments and related device embodiments, please refer to Figure 9 , Figure 9 which is a structural diagram of a computer provided by an embodiment of the present application. Figure 9The computer 900 shown includes a processor 901, a memory 902, a communication interface 903, and a bus 904. Among them, the processor 901, the memory 902, and the communication interface 903 are communicatively connected to each other through the bus 904.

[0087] Optionally, the memory 902 is a ROM, a static storage device, a dynamic storage device, or a RAM.

[0088] The memory 902 can store a program. When the executable program code stored in the memory 902 is executed by the processor 901, the processor 901 and the communication interface 903 are used to execute Figure 2 each step of the bipedal robot task navigation method based on image segmentation in the illustrated embodiment.

[0089] The processor 901 uses a general-purpose CPU, a microprocessor, an application-specific integrated circuit ASIC, a GPU, or one or more integrated circuits to execute relevant programs to execute the bipedal robot task navigation method based on image segmentation in the method embodiment of the present application.

[0090] The processor 901 can also be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the bipedal robot task navigation method based on image segmentation of the present application can be completed by the integrated logic circuit in the hardware of the processor 901 or by instructions in software form. Optionally, the processor 901 is a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The processor can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor is a microprocessor or the processor is any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The optional software module is located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, or other mature storage media in the art. This storage media is located in the memory 902, and the processor 901 reads the information in the memory 902 and combines its hardware to complete the functions required to be executed by the acquisition module 801 and the processing module 802 included in a bipedal robot task navigation device 800 based on image segmentation in the embodiments of the present application, or executes the bipedal robot task navigation method based on image segmentation in the method embodiments of the present application.

[0091] The communication interface 903 uses transceiver-related devices such as, but not limited to, a transceiver.

[0092] The bus 904 may include a path for transmitting information between various components of the computer 900 (e.g., the memory 902, the processor 901, the communication interface 903).

[0093] It should be noted that although Figure 9 the computer 900 shown only shows the memory, the processor, and the communication interface, in the specific implementation process, those skilled in the art should understand that the computer 900 also includes other devices necessary for normal operation. At the same time, based on specific needs, those skilled in the art should understand that the computer 900 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the computer 900 may also only include the devices necessary for implementing the embodiments of the present application, and do not necessarily include Figure 9 all the devices shown in

[0094] Embodiments of the present application provide a computer-readable storage medium, in which a computer program for electronic data exchange is stored. The computer program includes execution instructions, and the execution instructions are used to execute some or all of the steps of any one of the bipedal robot task navigation methods based on image segmentation described in the foregoing embodiments of the bipedal robot task navigation method based on image segmentation. The above computer includes an electronic terminal device.

[0095] Embodiments of the present application provide a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to cause a computer to perform some or all of the steps of any one of the bipedal robot task navigation methods based on image segmentation described in the foregoing method embodiments. The computer program product may be a software installation package.

[0096] It should be noted that for any of the foregoing embodiments of the bipedal robot task navigation method based on image segmentation, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, some steps may be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present application.

[0097] The above has introduced the embodiments of the present application in detail. In this article, specific examples are used to elaborate on the principles and implementation manners of a bipedal robot task navigation method and related devices based on image segmentation of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of a bipedal robot task navigation method and related devices based on image segmentation of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of the methods, hardware products, and computer program products of the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0099] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks. The memory can include: a flash drive, a read-only memory (abbreviation: ROM), a random access memory (abbreviation: RAM), a magnetic disk, or an optical disk, etc.

[0100] Although the present application is described in combination with the embodiments herein, however, in the process of implementing the claimed present application, those skilled in the art can understand and implement other changes of the disclosed embodiments by viewing the drawings, the disclosed content, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude the case of multiple. Certain measures are recited in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0101] Those of ordinary skill in the art can understand that all or part of the steps in the various method embodiments of any of the above bipedal robot task navigation methods based on image segmentation can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory (abbreviation: ROM), a random access memory (abbreviation: RAM), a magnetic disk, an optical disk, etc.

[0102] It can be understood that any product that is controlled or configured to execute the processing method of the flowchart described in an embodiment of a bipedal robot task navigation method based on image segmentation of the present application, such as the device in the above flowchart and the computer program product, all belong to the category of the related products described in the present application.

[0103] Obviously, those skilled in the art can make various changes and modifications to a bipedal robot task navigation method and related devices provided by the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. A biped robot task navigation method based on image segmentation, characterized in that, A control module applied to the biped robot, the biped robot includes the control module and a perception module communicatively connected to the control module, and the method includes: Obtaining a plurality of feature objects obtained by image segmentation of the panoramic image information collected by the perception module based on the target location; Determining whether there is a target idle position in the target location according to the spatial features of the plurality of feature objects, the spatial features of the biped robot, and the spatial features of the target location; When it is detected that there is a target idle position in the target location, determining a target behavior strategy according to the person recognition results of the plurality of feature objects, the target behavior strategy being used to complete the elevator-riding task navigation of the biped robot; Controlling the biped robot to execute the target behavior strategy.

2. The method according to claim 1, characterized in that, The obtaining a plurality of feature objects obtained by image segmentation of the panoramic image information collected by the perception module based on the target location includes: Obtaining first panoramic image information collected by the perception module at the target location, the panoramic image information including human elements, object elements, and background elements; Obtaining second panoramic image information after the perception module performs preprocessing operations on the first panoramic image information, the preprocessing operations including one or more of denoising, translation and rotation, adjusting the picture size, and adjusting the brightness and contrast; Obtaining a plurality of feature objects obtained by the perception module performing image segmentation on the second panoramic image information according to the object segmentation model 2 in the machine learning model.

3. The method according to claim 1, characterized in that, The spatial features include occupied space data, and the determining whether there is a target idle position in the target location according to the spatial features of the plurality of feature objects, the spatial features of the biped robot, and the spatial features of the target location includes: Obtaining first occupied space data of the plurality of feature objects in the target location; Obtaining second occupied space data of the biped robot itself and the carried items, the second occupied space data being the occupied space minimum data obtained by changing the relative positions of the biped robot itself and the carried items; Obtaining third occupied space data of the target location; Obtaining a difference between the third occupied space data and the first occupied space data, the difference being idle space data; When it is detected that the idle space data is not less than the second occupied space data and there is a target idle position in the idle space data, determining that there is a target idle position in the target location; when it is detected that the idle space data is less than the second occupied space data, and / or there is no target idle position in the idle space data, determining that there is no target idle position in the target location.

4. The method according to claim 1, characterized in that The plurality of feature objects include human objects and object objects, and the determining a target behavior strategy according to the person recognition results of the plurality of feature objects includes: Performing person recognition on the plurality of feature objects to obtain person recognition results; It is detected that there is a human object among the multiple feature objects in the human recognition result, and the target behavior strategy is determined to output the first speech voice, navigate to the target idle position, and determine the first behavior strategy according to the elevator floor control panel image collected by the obtained perception module; It is detected that there is no human object among the multiple feature objects in the human recognition result, and the target behavior strategy is determined to navigate to the target idle position and press the target floor button on the elevator floor control panel.

5. The method according to claim 4, wherein The determining of the first behavior strategy according to the elevator floor control panel image collected by the obtained perception module includes: Obtain the elevator floor control panel image collected by the perception module, where the elevator floor control panel image is used to indicate the floor button in the selected state on the elevator floor control panel; Judge whether the target floor button on the elevator floor control panel is in the selected state according to the elevator floor control panel image; It is detected that the target floor button on the elevator floor control panel is not in the selected state, and the first behavior strategy is determined to determine the target floor button pressing strategy according to the obstacle detection result between itself and the elevator floor control panel, keep its own posture until reaching the target floor after determining that the target floor button is in the selected state, and determine the movement mode according to the moving object detection result in front of itself; It is detected that the target floor button on the elevator floor control panel is in the selected state, and the first behavior strategy is determined to keep its own posture until reaching the target floor and determine the movement mode according to the moving object detection result in front of itself.

6. The method according to claim 5, wherein The determining of the target floor button pressing strategy according to the obstacle detection result between itself and the elevator floor control panel includes: Obtain the obstacle detection result between itself and the elevator floor control panel; It is detected that there is an obstacle between itself and the elevator floor control panel in the obstacle detection result, and the target floor button pressing strategy is determined to output the second speech voice, where the second speech voice is used to ask others to press the target floor button; It is detected that there is no obstacle between itself and the elevator floor control panel in the obstacle detection result, and the target floor button pressing strategy is determined to determine the target adjustment angle of each action joint of itself according to the spatial relationship between itself and the target button to press the target floor button.

7. The method according to claim 5, characterized in that The determining of the movement mode according to the moving object detection result in front of itself includes: Obtain the moving object detection result in front of itself; It is detected that there is a moving object in front of itself in the moving object detection result, and the movement mode is determined to be the following mode; It is detected that there is no moving object in front of itself in the moving object detection result, and the movement mode is determined to be the autonomous mode.

8. The method according to any one of claims 1-7, characterized in that, After determining whether there is a target idle position in the target location according to the spatial features of the multiple feature objects, the spatial features of the biped robot, and the spatial features of the target location, the method further includes: It is detected that there is no target idle position in the target location, and it is judged whether there is human movement in the target location; It is detected that there is a person moving in the target location, and the target behavior strategy is determined to output a third speech voice. After detecting that there is a target idle position in the target location, the target idle position is navigated to, and the second behavior strategy is determined according to the elevator floor control board image acquired by the perception module; it is detected that there is no person moving in the target location, and the target behavior strategy is determined to wait for the next elevator, and the third speech voice is used to inform the person in the target location that he is moving to the target idle position; The bipedal robot is controlled to execute the target behavior strategy.

9. The method according to claim 8, wherein After detecting that no person moves in the target location, the method further includes: The target behavior strategy is determined to be outputting a fourth speech voice, navigating to the target idle position after detecting that there is a target idle position in the target location, and determining a third behavior strategy based on the elevator floor control board image acquired by the perception module, wherein the fourth speech voice is used to request a person in the target location to move to leave the target idle position.

10. A bipedal robot task navigation device based on image segmentation, characterized in that, The device comprises: An acquisition module, used for acquiring a plurality of feature objects obtained by performing image segmentation based on the panoramic image information collected by the perception module at the target location; A processing module, for determining whether there is a target idle position in the target location based on the spatial features of the multiple feature objects, the spatial features of the bipedal robot and the spatial features of the target location; and for detecting the existence of the target idle position in the target location, determining a target behavior strategy based on the character recognition results of the multiple feature objects, the target behavior strategy being used to complete the elevator task navigation of the bipedal robot; and for controlling the bipedal robot to execute the target behavior strategy.

Images